Search

New insights from the Dark Energy Spectroscopic Instrument (DESI) 2024 baryon acoustic oscillations (BAO) data, in conjunction with cosmic microwave background (CMB) and Type Ia supernova (SN) data, suggest that dark energy may not be a cosmological constant. In this work, we investigate the cosmological implications of holographic dark energy (HDE) and interacting holographic dark energy (IHDE) models, utilizing CMB, DESI BAO, and SN data. By considering the combined DESI BAO and SN data, we determine that in the IHDE model, the parameter $c > 1$ and the dark-energy equation of state $w$ does not cross $-1$ at the $1\sigma$ confidence level, whereas in the HDE model, it marginally falls below this threshold. Upon incorporating CMB data, we observe that in the HDE model, the parameter $c < 1$ and $w$ crosses $-1$ at a level beyond $10\sigma$. Conversely, for the IHDE model, the likelihood of $w$ crossing $-1$ is considerably diminished, implying that the introduction of interaction within the HDE model could potentially resolve or mitigate the cosmic big rip conundrum. Furthermore, our analysis reveals that the HDE and IHDE models are statistically as viable as the $\Lambda$CDM model when assessing Bayesian evidence with DESI BAO data combined with SN data. However, when CMB data are added, the HDE and IHDE models are significantly less favored compared to the $\Lambda$CDM model. Our findings advocate for further exploration of the HDE and IHDE models using forthcoming, more precise late-universe observations., Comment: 13 pages, 5 figures

The cosmic curvature $\Omega_{K}$ is an important parameter related to the inflationary cosmology and the ultimate fate of the universe. In this work, we adopt the non-CMB observations to constrain $\Omega_{K}$ in the $\Lambda$CDM model and its extensions. The DESI baryon acoustic oscillation, DES type Ia supernova, cosmic chronometer, and strong gravitational lensing time delay data are considered. We find that the data combination favors an open universe in the $\Lambda$CDM model, specifically $\Omega_{K}=0.108\pm0.056$ at the $1\sigma$ confidence level, which is in $2.6\sigma$ tension with the Planck CMB result supporting our universe being slightly closed. In the $\Lambda$CDM extensions, the data combination is consistent with a spatially flat universe. However, the central value of $\Omega_{K}$ is positive and has a significant deviation from zero. We adopt the Akaike information criterion to compare different cosmological models. The result shows that non-flat models fit the observational data better that the flat $\Lambda$CDM model, which adds evidence to the argument that flat $\Lambda$CDM is not the ultimate model of cosmology., Comment: 9 pages, 3 figures

One of the main challenges of federated learning (FL) is handling non-independent and identically distributed (non-IID) client data, which may occur in practice due to unbalanced datasets and use of different data sources across clients. Knowledge sharing and model personalization are key strategies for addressing this issue. Clustered federated learning is a class of FL methods that groups clients that observe similarly distributed data into clusters, such that every client is typically associated with one data distribution and participates in training a model for that distribution along their cluster peers. In this paper, we present a unified Bayesian framework for clustered FL which associates clients to clusters. Then we propose several practical algorithms to handle the, otherwise growing, data associations in a way that trades off performance and computational complexity. This work provides insights on client-cluster associations and enables client knowledge sharing in new ways. The proposed framework circumvents the need for unique client-cluster associations, which is seen to increase the performance of the resulting models in a variety of experiments.

A symmetric nonnegative matrix factorization algorithm based on self-paced learning was proposed to improve the clustering performance of the model. It could make the model better distinguish normal samples from abnormal samples in an error-driven way. A weight variable that could measure the degree of difficulty to all samples was assigned in this method, and the variable was constrained by adopting both hard-weighting and soft-weighting strategies to ensure the rationality of the model. Cluster analysis was carried out on multiple data sets such as images and texts, and the experimental results showed the effectiveness of the proposed algorithm., Comment: in Chinese language

Feature selection technology is a key technology of data dimensionality reduction. Becauseof the lack of label information of collected data samples, unsupervised feature selection has attracted more attention. The universality and stability of many unsupervised feature selection algorithms are very low and greatly affected by the dataset structure. For this reason, many researchers have been keen to improve the stability of the algorithm. This paper attempts to preprocess the data set and use an interval method to approximate the data set, experimentally verifying the advantages and disadvantages of the new interval data set. This paper deals with these data sets from the global perspective and proposes a new algorithm-unsupervised feature selection algorithm based on neighborhood interval disturbance fusion(NIDF). This method can realize the joint learning of the final score of the feature and the approximate data interval. By comparing with the original unsupervised feature selection methods and several existing feature selection frameworks, the superiority of the proposed model is verified., Comment: in Chinese language

In recent years, the study of adversarial robustness in object detection systems, particularly those based on deep neural networks (DNNs), has become a pivotal area of research. Traditional physical attacks targeting object detectors, such as adversarial patches and texture manipulations, directly manipulate the surface of the object. While these methods are effective, their overt manipulation of objects may draw attention in real-world applications. To address this, this paper introduces a more subtle approach: an inconspicuous adversarial trigger that operates outside the bounding boxes, rendering the object undetectable to the model. We further enhance this approach by proposing the Feature Guidance (FG) technique and the Universal Auto-PGD (UAPGD) optimization strategy for crafting high-quality triggers. The effectiveness of our method is validated through extensive empirical testing, demonstrating its high performance in both digital and physical environments. The code and video will be available at: https://github.com/linToTao/Out-of-bbox-attack., Comment: ECCV 2024

Recommending items solely catering to users' historical interests narrows users' horizons. Recent works have considered steering target users beyond their historical interests by directly adjusting items exposed to them. However, the recommended items for direct steering might not align perfectly with users' interests evolution, detrimentally affecting target users' experience. To avoid this issue, we propose a new task named Proactive Recommendation in Social Networks (PRSN) that indirectly steers users' interest by utilizing the influence of social neighbors, i.e., indirect steering by adjusting the exposure of a target item to target users' neighbors. The key to PRSN lies in answering an interventional question: what would a target user's feedback be on a target item if the item is exposed to the user's different neighbors? To answer this question, we resort to causal inference and formalize PRSN as: (1) estimating the potential feedback of a user on an item, under the network interference by the item's exposure to the user's neighbors; and (2) adjusting the exposure of a target item to target users' neighbors to trade off steering performance and the damage to the neighbors' experience. To this end, we propose a Neighbor Interference Recommendation (NIRec) framework with two key modules: (1)an interference representation-based estimation module for modeling potential feedback; and (2) a post-learning-based optimization module for optimizing a target item's exposure to trade off steering performance and the neighbors' experience by greedy search. We conduct extensive semi-simulation experiments based on three real-world datasets, validating the steering effectiveness of NIRec.

Video anomaly detection (VAD) aims to discover behaviors or events deviating from the normality in videos. As a long-standing task in the field of computer vision, VAD has witnessed much good progress. In the era of deep learning, with the explosion of architectures of continuously growing capability and capacity, a great variety of deep learning based methods are constantly emerging for the VAD task, greatly improving the generalization ability of detection algorithms and broadening the application scenarios. Therefore, such a multitude of methods and a large body of literature make a comprehensive survey a pressing necessity. In this paper, we present an extensive and comprehensive research review, covering the spectrum of five different categories, namely, semi-supervised, weakly supervised, fully supervised, unsupervised and open-set supervised VAD, and we also delve into the latest VAD works based on pre-trained large models, remedying the limitations of past reviews in terms of only focusing on semi-supervised VAD and small model based methods. For the VAD task with different levels of supervision, we construct a well-organized taxonomy, profoundly discuss the characteristics of different types of methods, and show their performance comparisons. In addition, this review involves the public datasets, open-source codes, and evaluation metrics covering all the aforementioned VAD tasks. Finally, we provide several important research directions for the VAD community., Comment: This work has been submitted to the IEEE for possible publication

A class of quasi-distribution evaluation criteria based on piecewise Bezier curves is proposed to address the issue of the inability to objectively evaluate finite element models. During the optimization design of mechanical parts, finite element modeling is performed on their stress deformation, and the mesh node shape variable values are converted into distribution histogram data for piecewise Bezier curve fitting. Being dealt with area normalization method, the fitting curve could be regarded as a kind of probability density function (PDF), and its variance could be used to evaluate the finite element modeling results. The situation with the minimum variance is the optimal choice for overall deformation. Numerical experiments have indicated that the new method demonstrated the intrinsic characteristics of the finite element models of difference mechanical parts. As an objective appraisal method for evaluating finite element models, it is both effective and feasible.

We innovate a systematic investigation of the Weak Cosmic Censorship Conjecture (WCCC) using gedanken experiments involving black hole perturbations by test particles. We classify various WCCC violation scenarios proposed in recent decades, including Hubeny, mixed, and the latest Sorce-Wald (SW). We provide general formulae in each case, and resolve contradictions in numerous studies. Following SW type, our analysis reveals that WCCC depends on the sign choice of the parameter $W\equiv \big(\frac{\partial S}{\partial T}\big)_{Q_i; T=0}$ of the extremal black holes. $W > 0$ preserves WCCC and $W < 0$ would indicate potential violation. We show explicitly that $W>0$ for spherically-symmetric and static black holes, and for general case, we argue that it is protected by the black hole no-hair theorem. We also consider asymptotically-(A)dS black holes and argue that there can be no violation either., Comment: 23 pages

In view of existing automatic driving is difficult to accurately and timely obtain the status and driving intention of other vehicles and the safety risk and urgency of autonomous vehicles in the absence of collision are evaluated. As a result, while vehicles generally maintain safe distances, accidents still frequently occur, particularly in merging areas. To ensure safety, improve road efficiency, this paper presents a pre-programmed technique for managing vehicles' spatiotemporal trajectories to proactively mitigate conflicts among vehicles. Firstly, the study focuses on the calculation of safe distances under varying spatiotemporal conditions, taking into account differences in vehicle speed. Subsequently, an evaluation model for vehicle conflict risk is developed, which incorporates critical parameters such as collision acceleration and emergency acceleration. The methodology further identifies the main line vehicles that are potentially in conflict with on-ramp vehicles and determines the target gap for the latter. Based on this selected target gap, a cooperative control method is formulated, enabling the pre-programming of vehicle trajectories. Using highway ramp merging as a case study, the paper introduces a mainline priority spatiotemporal cooperative control method and validates its efficacy through rigorous simulations. The analysis indicates that the average delay time can be reduced by 97.96%, and fuel consumption by 6.01%. The mainline priority strategy demonstrates increased speed, low latency and low fuel consumption.

Current weakly supervised video anomaly detection (WSVAD) task aims to achieve frame-level anomalous event detection with only coarse video-level annotations available. Existing works typically involve extracting global features from full-resolution video frames and training frame-level classifiers to detect anomalies in the temporal dimension. However, most anomalous events tend to occur in localized spatial regions rather than the entire video frames, which implies existing frame-level feature based works may be misled by the dominant background information and lack the interpretation of the detected anomalies. To address this dilemma, this paper introduces a novel method called STPrompt that learns spatio-temporal prompt embeddings for weakly supervised video anomaly detection and localization (WSVADL) based on pre-trained vision-language models (VLMs). Our proposed method employs a two-stream network structure, with one stream focusing on the temporal dimension and the other primarily on the spatial dimension. By leveraging the learned knowledge from pre-trained VLMs and incorporating natural motion priors from raw videos, our model learns prompt embeddings that are aligned with spatio-temporal regions of videos (e.g., patches of individual frames) for identify specific local regions of anomalies, enabling accurate video anomaly detection while mitigating the influence of background information. Without relying on detailed spatio-temporal annotations or auxiliary object detection/tracking, our method achieves state-of-the-art performance on three public benchmarks for the WSVADL task., Comment: Accepted by ACMMM2024

Precise cosmological measurements are essential for understanding the evolution of the universe and the nature of dark energy. The Five-hundred-meter Aperture Spherical Telescope (FAST), the most sensitive single-dish radio telescope, has the potential to provide the precise cosmological measurements through neutral hydrogen 21-cm intensity mapping sky survey. This paper primarily explores the potential of technological upgrades for FAST in cosmology. The most crucial upgrade begins with equipping FAST with a wide-band receiver ($0 < z < 2.5$). This upgrade can enable FAST to achieve higher precision in cosmological parameter estimation than the Square Kilometre Array Phase-1 Mid frequency. On this basis, expanding to a FAST array (FASTA) consisting of six identical FAST would offer significant improvements in precision compared to FAST. Additionally, compared with the current results from the data combination of cosmic microwave background, baryon acoustic oscillations (optical galaxy surveys), and type Ia supernovae, FASTA can provide comparable constraints. Specifically, for the dark-energy equation-of-state parameters, FASTA can achieve $\sigma(w_0) = 0.09$ and $\sigma(w_a) = 0.33$., Comment: 9 pages, 5 figures

Recently, DESI has released baryon acoustic oscillation (BAO) data, and DES has also published its five-year supernova (SN) data. These observations, combined with cosmic microwave background (CMB) data, support a dynamically evolving dark energy at a high confidence level. When using cosmological observations to weigh neutrinos, the results of weighing neutrinos will be significantly affected by the measurement of dark energy due to the degeneracy between neutrino mass and the dark-energy equation of state. Therefore, we need to understand how the dynamical evolution of dark energy in the current situation will affect the measurement of neutrino mass. In this work, we utilize these latest observations and other additional distance measurements to discuss the mutual influence between neutrinos and dark energy, then calculate the Bayes factor to compare models. We consider three neutrino mass hierarchies including degenerate hierarchy (DH), normal hierarchy (NH), and inverted hierarchy (IH), as well as three dark energy models including $\Lambda \rm CDM$, $w\rm CDM$, and $w_0w_a \rm CDM$ models. Cosmological data combined with the prior of particle physics experiments can provide strong to decisive evidence favoring the $w_0w_a {\rm CDM}+\sum m_\nu$ model with NH. In the $w_0w_a \rm CDM$ model, using the CMB+DESI+DESY5 data, we obtain constraints on the total neutrino mass, $\sum m_\nu<0.171\ \rm eV,\ 0.204\ \rm eV,\ 0.220\ \rm eV$, for DH, NH, and IH, respectively. Furthermore, taking into account the neutrino hierarchy or incorporating additional distance measurements results in a more pronounced deviation from the $\Lambda$CDM model for dark energy. The latter, particularly, exhibits a deviation at a confidence level that surpasses $4\sigma$., Comment: 10 pages, 4 figures

The recent results from the first year baryon acoustic oscillations (BAO) data released by the Dark Energy Spectroscopic Instrument (DESI), combined with cosmic microwave background (CMB) and type Ia supernova (SN) data, have shown a detection of significant deviation from a cosmological constant for dark energy. In this work, we utilize the latest DESI BAO data in combination with the SN data from the full five-year observations of the Dark Energy Survey and the CMB data from the Planck satellite to explore potential interactions between dark energy and dark matter. We consider four typical forms of the interaction term $Q$. Our findings suggest that interacting dark energy (IDE) models with $Q \propto \rho_{\rm de}$ support the presence of an interaction where dark energy decays into dark matter. Specifically, the deviation from $\Lambda$CDM for the IDE model with $Q=\beta H_0\rho_{\rm de}$ reaches the $3\sigma$ level. These models yield a lower value of Akaike information criterion than the $\Lambda$CDM model, indicating a preference for these IDE models based on the current observational data. For IDE models with $Q\propto\rho_{\rm c}$, the existence of interaction depends on the form of the proportionality coefficient $\Gamma$. The IDE model with $Q=\beta H\rho_{\rm c}$ yields $\beta=0.0003\pm 0.0011$, which essentially does not support the presence of the interaction. In general, whether the observational data support the existence of interaction is closely related to the model. Our analysis helps to elucidate which type of IDE model can better explain the current observational data., Comment: 11 pages, 4 figures; published in ApJ

Causal attribution, which aims to explain why events or behaviors occur, is crucial in causal inference and enhances our understanding of cause-and-effect relationships in scientific research. The probabilities of necessary causation (PN) and sufficient causation (PS) are two of the most common quantities for attribution in causal inference. While many works have explored the identification or bounds of PN and PS, efficient estimation remains unaddressed. To fill this gap, this paper focuses on obtaining semiparametric efficient estimators of PN and PS under two sets of identifiability assumptions: strong ignorability and monotonicity, and strong ignorability and conditional independence. We derive efficient influence functions and semiparametric efficiency bounds for PN and PS under the two sets of identifiability assumptions, respectively. Based on this, we propose efficient estimators for PN and PS, and show their large sample properties. Extensive simulations validate the superiority of our estimators compared to competing methods. We apply our methods to a real-world dataset to assess various risk factors affecting stroke.

Open-Vocabulary Video Instance Segmentation (VIS) is attracting increasing attention due to its ability to segment and track arbitrary objects. However, the recent Open-Vocabulary VIS attempts obtained unsatisfactory results, especially in terms of generalization ability of novel categories. We discover that the domain gap between the VLM features (e.g., CLIP) and the instance queries and the underutilization of temporal consistency are two central causes. To mitigate these issues, we design and train a novel Open-Vocabulary VIS baseline called OVFormer. OVFormer utilizes a lightweight module for unified embedding alignment between query embeddings and CLIP image embeddings to remedy the domain gap. Unlike previous image-based training methods, we conduct video-based model training and deploy a semi-online inference scheme to fully mine the temporal consistency in the video. Without bells and whistles, OVFormer achieves 21.9 mAP with a ResNet-50 backbone on LV-VIS, exceeding the previous state-of-the-art performance by 7.7. Extensive experiments on some Close-Vocabulary VIS datasets also demonstrate the strong zero-shot generalization ability of OVFormer (+ 7.6 mAP on YouTube-VIS 2019, + 3.9 mAP on OVIS). Code is available at https://github.com/fanghaook/OVFormer., Comment: ECCV 2024

The accessibility of vast volumes of unlabeled data has sparked growing interest in semi-supervised learning (SSL) and covariate shift transfer learning (CSTL). In this paper, we present an inference framework for estimating regression coefficients in conditional mean models within both SSL and CSTL settings, while allowing for the misspecification of conditional mean models. We develop an augmented inverse probability weighted (AIPW) method, employing regularized calibrated estimators for both propensity score (PS) and outcome regression (OR) nuisance models, with PS and OR models being sequentially dependent. We show that when the PS model is correctly specified, the proposed estimator achieves consistency, asymptotic normality, and valid confidence intervals, even with possible OR model misspecification and high-dimensional data. Moreover, by suppressing detailed technical choices, we demonstrate that previous methods can be unified within our AIPW framework. Our theoretical findings are verified through extensive simulation studies and a real-world data application.

Most Fake News Detection (FND) methods often struggle with data scarcity for emerging news domain. Recently, prompt learning based on Pre-trained Language Models (PLM) has emerged as a promising approach in domain adaptive few-shot learning, since it greatly reduces the need for labeled data by bridging the gap between pre-training and downstream task. Furthermore, external knowledge is also helpful in verifying emerging news, as emerging news often involves timely knowledge that may not be contained in the PLM's outdated prior knowledge. To this end, we propose COOL, a Comprehensive knOwledge enhanced prOmpt Learning method for domain adaptive few-shot FND. Specifically, we propose a comprehensive knowledge extraction module to extract both structured and unstructured knowledge that are positively or negatively correlated with news from external sources, and adopt an adversarial contrastive enhanced hybrid prompt learning strategy to model the domain-invariant news-knowledge interaction pattern for FND. Experimental results demonstrate the superiority of COOL over various state-of-the-arts.

Discovering causal relationships from observational data, particularly in the presence of latent variables, poses a challenging problem. While current local structure learning methods have proven effective and efficient when the focus lies solely on the local relationships of a target variable, they operate under the assumption of causal sufficiency. This assumption implies that all the common causes of the measured variables are observed, leaving no room for latent variables. Such a premise can be easily violated in various real-world applications, resulting in inaccurate structures that may adversely impact downstream tasks. In light of this, our paper delves into the primary investigation of locally identifying potential parents and children of a target from observational data that may include latent variables. Specifically, we harness the causal information from m-separation and V-structures to derive theoretical consistency results, effectively bridging the gap between global and local structure learning. Together with the newly developed stop rules, we present a principled method for determining whether a variable is a direct cause or effect of a target. Further, we theoretically demonstrate the correctness of our approach under the standard causal Markov and faithfulness conditions, with infinite samples. Experimental results on both synthetic and real-world data validate the effectiveness and efficiency of our approach.

Recommender systems learn personalized user preferences from user feedback like clicks. However, user feedback is usually biased towards partially observed interests, leaving many users' hidden interests unexplored. Existing approaches typically mitigate the bias, increase recommendation diversity, or use bandit algorithms to balance exploration-exploitation trade-offs. Nevertheless, they fail to consider the potential rewards of recommending different categories of items and lack the global scheduling of allocating top-N recommendations to categories, leading to suboptimal exploration. In this work, we propose an Uplift model-based Recommender (UpliftRec) framework, which regards top-N recommendation as a treatment optimization problem. UpliftRec estimates the treatment effects, i.e., the click-through rate (CTR) under different category exposure ratios, by using observational user feedback. UpliftRec calculates group-level treatment effects to discover users' hidden interests with high CTR rewards and leverages inverse propensity weighting to alleviate confounder bias. Thereafter, UpliftRec adopts a dynamic programming method to calculate the optimal treatment for overall CTR maximization. We implement UpliftRec on different backend models and conduct extensive experiments on three datasets. The empirical results validate the effectiveness of UpliftRec in discovering users' hidden interests while achieving superior recommendation accuracy., Comment: Accepted to SIGIR 2024

We adopt the Reall-Santos method to obtain the quadratic curvature corrections to the thermodynamics of Myers-Perry rotating black holes in diverse dimensions. We consider the corrections in canonical and grand canonical ensembles, and also for fixed mass and angular momenta. We find that there exist inevitable divergences for generic rotation parameters so that the perturbative approach breaks down. We present a simple and universal formula to determine where these divergences could arise, and argue, using an explicit example, that these divergences are artefact of perturbation and may not exist in the full nonlinear theory., Comment: LaTeX, 34 pages, some typos were corrected and a new subsection on the sign of \Delta S was added

Empirical researchers and decision-makers spanning various domains frequently seek profound insights into the long-term impacts of interventions. While the significance of long-term outcomes is undeniable, an overemphasis on them may inadvertently overshadow short-term gains. Motivated by this, this paper formalizes a new framework for learning the optimal policy that effectively balances both long-term and short-term rewards, where some long-term outcomes are allowed to be missing. In particular, we first present the identifiability of both rewards under mild assumptions. Next, we deduce the semiparametric efficiency bounds, along with the consistency and asymptotic normality of their estimators. We also reveal that short-term outcomes, if associated, contribute to improving the estimator of the long-term reward. Based on the proposed estimators, we develop a principled policy learning approach and further derive the convergence rates of regret and estimation errors associated with the learned policy. Extensive experiments are conducted to validate the effectiveness of the proposed method, demonstrating its practical applicability.

Selection bias in recommender system arises from the recommendation process of system filtering and the interactive process of user selection. Many previous studies have focused on addressing selection bias to achieve unbiased learning of the prediction model, but ignore the fact that potential outcomes for a given user-item pair may vary with the treatments assigned to other user-item pairs, named neighborhood effect. To fill the gap, this paper formally formulates the neighborhood effect as an interference problem from the perspective of causal inference and introduces a treatment representation to capture the neighborhood effect. On this basis, we propose a novel ideal loss that can be used to deal with selection bias in the presence of neighborhood effect. We further develop two new estimators for estimating the proposed ideal loss. We theoretically establish the connection between the proposed and previous debiasing methods ignoring the neighborhood effect, showing that the proposed methods can achieve unbiased learning when both selection bias and neighborhood effect are present, while the existing methods are biased. Extensive semi-synthetic and real-world experiments are conducted to demonstrate the effectiveness of the proposed methods., Comment: ICLR 24

Debiased collaborative filtering aims to learn an unbiased prediction model by removing different biases in observational datasets. To solve this problem, one of the simple and effective methods is based on the propensity score, which adjusts the observational sample distribution to the target one by reweighting observed instances. Ideally, propensity scores should be learned with causal balancing constraints. However, existing methods usually ignore such constraints or implement them with unreasonable approximations, which may affect the accuracy of the learned propensity scores. To bridge this gap, in this paper, we first analyze the gaps between the causal balancing requirements and existing methods such as learning the propensity with cross-entropy loss or manually selecting functions to balance. Inspired by these gaps, we propose to approximate the balancing functions in reproducing kernel Hilbert space and demonstrate that, based on the universal property and representer theorem of kernel functions, the causal balancing constraints can be better satisfied. Meanwhile, we propose an algorithm that adaptively balances the kernel function and theoretically analyze the generalization error bound of our methods. We conduct extensive experiments to demonstrate the effectiveness of our methods, and to promote this research direction, we have released our project at https://github.com/haoxuanli-pku/ICLR24-Kernel-Balancing., Comment: ICLR 24 Spotlight

This paper reviews the NTIRE 2024 low light image enhancement challenge, highlighting the proposed solutions and results. The aim of this challenge is to discover an effective network design or solution capable of generating brighter, clearer, and visually appealing results when dealing with a variety of conditions, including ultra-high resolution (4K and beyond), non-uniform illumination, backlighting, extreme darkness, and night scenes. A notable total of 428 participants registered for the challenge, with 22 teams ultimately making valid submissions. This paper meticulously evaluates the state-of-the-art advancements in enhancing low-light images, reflecting the significant progress and creativity in this field., Comment: NTIRE 2024 Challenge Report

In real-world scenarios, images captured often suffer from blurring, noise, and other forms of image degradation, and due to sensor limitations, people usually can only obtain low dynamic range images. To achieve high-quality images, researchers have attempted various image restoration and enhancement operations on photographs, including denoising, deblurring, and high dynamic range imaging. However, merely performing a single type of image enhancement still cannot yield satisfactory images. In this paper, to deal with the challenge above, we propose the Composite Refinement Network (CRNet) to address this issue using multiple exposure images. By fully integrating information-rich multiple exposure inputs, CRNet can perform unified image restoration and enhancement. To improve the quality of image details, CRNet explicitly separates and strengthens high and low-frequency information through pooling layers, using specially designed Multi-Branch Blocks for effective fusion of these frequencies. To increase the receptive field and fully integrate input features, CRNet employs the High-Frequency Enhancement Module, which includes large kernel convolutions and an inverted bottleneck ConvFFN. Our model secured third place in the first track of the Bracketing Image Restoration and Enhancement Challenge, surpassing previous SOTA models in both testing metrics and visual quality., Comment: This paper is accepted by CVPR2024 Workshop, Code: https://github.com/CalvinYang0/CRNet

In real-world scenarios, due to a series of image degradations, obtaining high-quality, clear content photos is challenging. While significant progress has been made in synthesizing high-quality images, previous methods for image restoration and enhancement often overlooked the characteristics of different degradations. They applied the same structure to address various types of degradation, resulting in less-than-ideal restoration outcomes. Inspired by the notion that high/low frequency information is applicable to different degradations, we introduce HLNet, a Bracketing Image Restoration and Enhancement method based on high-low frequency decomposition. Specifically, we employ two modules for feature extraction: shared weight modules and non-shared weight modules. In the shared weight modules, we use SCConv to extract common features from different degradations. In the non-shared weight modules, we introduce the High-Low Frequency Decomposition Block (HLFDB), which employs different methods to handle high-low frequency information, enabling the model to address different degradations more effectively. Compared to other networks, our method takes into account the characteristics of different degradations, thus achieving higher-quality image restoration., Comment: This paper is accepted by CVPR 2024 Workshop, code: https://github.com/chengeng0613/HLNet

Weakly supervised video anomaly detection (WSVAD) is a challenging task. Generating fine-grained pseudo-labels based on weak-label and then self-training a classifier is currently a promising solution. However, since the existing methods use only RGB visual modality and the utilization of category text information is neglected, thus limiting the generation of more accurate pseudo-labels and affecting the performance of self-training. Inspired by the manual labeling process based on the event description, in this paper, we propose a novel pseudo-label generation and self-training framework based on Text Prompt with Normality Guidance (TPWNG) for WSVAD. Our idea is to transfer the rich language-visual knowledge of the contrastive language-image pre-training (CLIP) model for aligning the video event description text and corresponding video frames to generate pseudo-labels. Specifically, We first fine-tune the CLIP for domain adaptation by designing two ranking losses and a distributional inconsistency loss. Further, we propose a learnable text prompt mechanism with the assist of a normality visual prompt to further improve the matching accuracy of video event description text and video frames. Then, we design a pseudo-label generation module based on the normality guidance to infer reliable frame-level pseudo-labels. Finally, we introduce a temporal context self-adaptive learning module to learn the temporal dependencies of different video events more flexibly and accurately. Extensive experiments show that our method achieves state-of-the-art performance on two benchmark datasets, UCF-Crime and XD-Viole, Comment: Accepted to CVPR2024

Deep neural networks (DNNs) are known to be sensitive to adversarial input perturbations, leading to a reduction in either prediction accuracy or individual fairness. To jointly characterize the susceptibility of prediction accuracy and individual fairness to adversarial perturbations, we introduce a novel robustness definition termed robust accurate fairness. Informally, robust accurate fairness requires that predictions for an instance and its similar counterparts consistently align with the ground truth when subjected to input perturbations. We propose an adversarial attack approach dubbed RAFair to expose false or biased adversarial defects in DNN, which either deceive accuracy or compromise individual fairness. Then, we show that such adversarial instances can be effectively addressed by carefully designed benign perturbations, correcting their predictions to be accurate and fair. Our work explores the double-edged sword of input perturbations to robust accurate fairness in DNN and the potential of using benign perturbations to correct adversarial instances.

The low-rank quaternion matrix approximation has been successfully applied in many applications involving signal processing and color image processing. However, the cost of quaternion models for generating low-rank quaternion matrix approximation is sometimes considerable due to the computation of the quaternion singular value decomposition (QSVD), which limits their application to real large-scale data. To address this deficiency, an efficient quaternion matrix CUR (QMCUR) method for low-rank approximation is suggested, which provides significant acceleration in color image processing. We first explore the QMCUR approximation method, which uses actual columns and rows of the given quaternion matrix, instead of the costly QSVD. Additionally, two different sampling strategies are used to sample the above-selected columns and rows. Then, the perturbation analysis is performed on the QMCUR approximation of noisy versions of low-rank quaternion matrices. Extensive experiments on both synthetic and real data further reveal the superiority of the proposed algorithm compared with other algorithms for getting low-rank approximation, in terms of both efficiency and accuracy.

Understanding treatment heterogeneity is crucial for reliable decision-making in treatment evaluation and selection. While the conditional average treatment effect (CATE) is commonly used to capture treatment heterogeneity induced by covariates and design individualized treatment policies, it remains an averaging metric within subpopulations. This limitation prevents it from unveiling individual-level risks, potentially leading to misleading results. This article addresses this gap by examining individual risk for binary outcomes, specifically focusing on the fraction negatively affected (FNA) conditional on covariates -- a metric assessing the percentage of individuals experiencing worse outcomes with treatment compared to control. Under the strong ignorability assumption, FNA is unidentifiable, and we find that previous bounds are wide and practically unattainable except in certain degenerate cases. By introducing a plausible positive correlation assumption for the potential outcomes, we obtain significantly improved bounds compared to previous studies. We show that even with a positive and statistically significant CATE, the lower bound on FNA can be positive, i.e., in the best-case scenario many units will be harmed if receiving treatment. We establish a nonparametric sensitivity analysis framework for FNA using the Pearson correlation coefficient as the sensitivity parameter, thereby exploring the relationships among the correlation coefficient, FNA, and CATE. We also present a practical and tractable method for selecting the range of correlation coefficients. Furthermore, we propose flexible estimators for refined FNA bounds and prove their consistency and asymptotic normality.

Low-Light Image Enhancement (LLIE) task tends to restore the details and visual information from corrupted low-light images. Most existing methods learn the mapping function between low/normal-light images by Deep Neural Networks (DNNs) on sRGB and HSV color space. Nevertheless, enhancement involves amplifying image signals, and applying these color spaces to low-light images with a low signal-to-noise ratio can introduce sensitivity and instability into the enhancement process. Consequently, this results in the presence of color artifacts and brightness artifacts in the enhanced images. To alleviate this problem, we propose a novel trainable color space, named Horizontal/Vertical-Intensity (HVI). It not only decouples brightness and color from RGB channels to mitigate the instability during enhancement but also adapts to low-light images in different illumination ranges due to the trainable parameters. Further, we design a novel Color and Intensity Decoupling Network (CIDNet) with two branches dedicated to processing the decoupled image brightness and color in the HVI space. Within CIDNet, we introduce the Lightweight Cross-Attention (LCA) module to facilitate interaction between image structure and content information in both branches, while also suppressing noise in low-light images. Finally, we conducted 22 quantitative and qualitative experiments to show that the proposed CIDNet outperforms the state-of-the-art methods on 11 datasets. The code is available at https://github.com/Fediory/HVI-CIDNet., Comment: Qingsen Yan, Yixu Feng, Cheng Zhang contributed equally to this work. Corresponding author: Yanning Zhang