Search

Segment Anything Model (SAM) is an advanced foundational model for image segmentation, widely applied to remote sensing images (RSIs). Due to the domain gap between RSIs and natural images, traditional methods typically use SAM as a source pre-trained model and fine-tune it with fully supervised masks. Unlike these methods, our work focuses on fine-tuning SAM using more convenient and challenging point annotations. Leveraging SAM's zero-shot capabilities, we adopt a self-training framework that iteratively generates pseudo-labels for training. However, if the pseudo-labels contain noisy labels, there is a risk of error accumulation. To address this issue, we extract target prototypes from the target dataset and use the Hungarian algorithm to match them with prediction prototypes, preventing the model from learning in the wrong direction. Additionally, due to the complex backgrounds and dense distribution of objects in RSI, using point prompts may result in multiple objects being recognized as one. To solve this problem, we propose a negative prompt calibration method based on the non-overlapping nature of instance masks. In brief, we use the prompts of overlapping masks as corresponding negative signals, resulting in refined masks. Combining the above methods, we propose a novel Pointly-supervised Segment Anything Model named PointSAM. We conduct experiments on RSI datasets, including WHU, HRSID, and NWPU VHR-10, and the results show that our method significantly outperforms direct testing with SAM, SAM2, and other comparison methods. Furthermore, we introduce PointSAM as a point-to-box converter and achieve encouraging results, suggesting that this method can be extended to other point-supervised tasks. The code is available at https://github.com/Lans1ng/PointSAM., Comment: 15 pages

Query reformulation is a well-known problem in Information Retrieval (IR) aimed at enhancing single search successful completion rate by automatically modifying user's input query. Recent methods leverage Large Language Models (LLMs) to improve query reformulation, but often generate limited and redundant expansions, potentially constraining their effectiveness in capturing diverse intents. In this paper, we propose GenCRF: a Generative Clustering and Reformulation Framework to capture diverse intentions adaptively based on multiple differentiated, well-generated queries in the retrieval phase for the first time. GenCRF leverages LLMs to generate variable queries from the initial query using customized prompts, then clusters them into groups to distinctly represent diverse intents. Furthermore, the framework explores to combine diverse intents query with innovative weighted aggregation strategies to optimize retrieval performance and crucially integrates a novel Query Evaluation Rewarding Model (QERM) to refine the process through feedback loops. Empirical experiments on the BEIR benchmark demonstrate that GenCRF achieves state-of-the-art performance, surpassing previous query reformulation SOTAs by up to 12% on nDCG@10. These techniques can be adapted to various LLMs, significantly boosting retriever performance and advancing the field of Information Retrieval.

Few-shot Named Entity Recognition (NER) aims to extract named entities using only a limited number of labeled examples. Existing contrastive learning methods often suffer from insufficient distinguishability in context vector representation because they either solely rely on label semantics or completely disregard them. To tackle this issue, we propose a unified label-aware token-level contrastive learning framework. Our approach enriches the context by utilizing label semantics as suffix prompts. Additionally, it simultaneously optimizes context-context and context-label contrastive learning objectives to enhance generalized discriminative contextual representations.Extensive experiments on various traditional test domains (OntoNotes, CoNLL'03, WNUT'17, GUM, I2B2) and the large-scale few-shot NER dataset (FEWNERD) demonstrate the effectiveness of our approach. It outperforms prior state-of-the-art models by a significant margin, achieving an average absolute gain of 7% in micro F1 scores across most scenarios. Further analysis reveals that our model benefits from its powerful transfer capability and improved contextual representations.

In human-computer interaction, it is crucial for agents to respond to human by understanding their emotions. Unraveling the causes of emotions is more challenging. A new task named Multimodal Emotion-Cause Pair Extraction in Conversations is responsible for recognizing emotion and identifying causal expressions. In this study, we propose a multi-stage framework to generate emotion and extract the emotion causal pairs given the target emotion. In the first stage, Llama-2-based InstructERC is utilized to extract the emotion category of each utterance in a conversation. After emotion recognition, a two-stream attention model is employed to extract the emotion causal pairs given the target emotion for subtask 2 while MuTEC is employed to extract causal span for subtask 1. Our approach achieved first place for both of the two subtasks in the competition.

In this paper, we consider a kind of shallow water wave model called the Kadomtsev-Petviashvili-Benjamin-Bona-Mahony (KP-BBM) equation. We firstly consider the unperturbed KP-BBM equation. Then by using the geometric singular perturbation (GSP) theory, especially the invariant manifold theory, method of dynamical system and Melnikov function, the existence of solitary wave solutions of perturbed KP-BBM equation is proved. In other words, we dissuss the equation under different nonlinear terms. Finally, we validate our results with numerical simulations., Comment: We declare that the authors are ranked in alphabetic order of their names and all of them have the same contributions to this paper

This article explores the significant advancements in Short-Range Correlation (SRC) research enabled by the latest Chinese nuclear physics facilities- CSR at HIRFL, HIAF, SHINE, and the upcoming EicC. These facilities introduce cutting-edge technologies and methodologies, addressing existing challenges and broadening the scope for SRC studies. By providing detailed insights into the capabilities and expected contributions of each facility, the paper highlights China's emerging role in the global nuclear physics landscape. The collaborative potential, alongside complementary global efforts, positions these facilities to deeply influence our understanding of nuclear matter's fundamental properties and interactions., Comment: 16 pages, 14 figures, to be submitted to EPJA Topical Collection: Short-Range Correlations and the EMC Effect

Multi-view surface reconstruction is an ill-posed, inverse problem in 3D vision research. It involves modeling the geometry and appearance with appropriate surface representations. Most of the existing methods rely either on explicit meshes, using surface rendering of meshes for reconstruction, or on implicit field functions, using volume rendering of the fields for reconstruction. The two types of representations in fact have their respective merits. In this work, we propose a new hybrid representation, termed Sur2f, aiming to better benefit from both representations in a complementary manner. Technically, we learn two parallel streams of an implicit signed distance field and an explicit surrogate surface Sur2f mesh, and unify volume rendering of the implicit signed distance function (SDF) and surface rendering of the surrogate mesh with a shared, neural shader; the unified shading promotes their convergence to the same, underlying surface. We synchronize learning of the surrogate mesh by driving its deformation with functions induced from the implicit SDF. In addition, the synchronized surrogate mesh enables surface-guided volume sampling, which greatly improves the sampling efficiency per ray in volume rendering. We conduct thorough experiments showing that Sur$^2$f outperforms existing reconstruction methods and surface representations, including hybrid ones, in terms of both recovery quality and recovery efficiency., Comment: 18 pages, 16 figures

The success of large language models has inspired the computer vision community to explore image segmentation foundation model that is able to zero/few-shot generalize through prompt engineering. Segment-Anything(SAM), among others, is the state-of-the-art image segmentation foundation model demonstrating strong zero/few-shot generalization. Despite the success, recent studies reveal the weakness of SAM under strong distribution shift. In particular, SAM performs awkwardly on corrupted natural images, camouflaged images, medical images, etc. Motivated by the observations, we aim to develop a self-training based strategy to adapt SAM to target distribution. Given the unique challenges of large source dataset, high computation cost and incorrect pseudo label, we propose a weakly supervised self-training architecture with anchor regularization and low-rank finetuning to improve the robustness and computation efficiency of adaptation. We validate the effectiveness on 5 types of downstream segmentation tasks including natural clean/corrupted images, medical images, camouflaged images and robotic images. Our proposed method is task-agnostic in nature and outperforms pre-trained SAM and state-of-the-art domain adaptation methods on almost all downstream tasks with the same testing prompt inputs., Comment: 20 pages, 12 figures

Large-scale pre-trained language models have achieved impressive results on a wide range of downstream tasks recently. However, fine-tuning an extremely large-scale pre-trained language model on limited target datasets is often plagued by overfitting and representation degradation. In this paper, we propose a Dynamic Parameter Selection (DPS) algorithm for the large-scale pre-trained models during fine-tuning, which adaptively selects a more promising subnetwork to perform staging updates based on gradients of back-propagation. Experiments on the GLUE benchmark show that DPS outperforms previous fine-tuning methods in terms of overall performance and stability, and consistently achieves better results with variable pre-trained language models. In addition, DPS brings a large magnitude of improvement in out-of-domain transferring experiments and low-resource scenarios, which shows that it can maintain stable general contextual features and reduce the representation collapse. We release our code at https://github.com/ZhangHaojie077/DPS, Comment: NeurIPS 2022

In this work, we revisit the Transformer-based pre-trained language models and identify two different types of information confusion in position encoding and model representations, respectively. Firstly, we show that in the relative position encoding, the joint modeling about relative distances and directions brings confusion between two heterogeneous information. It may make the model unable to capture the associative semantics of the same distance and the opposite directions, which in turn affects the performance of downstream tasks. Secondly, we notice the BERT with Mask Language Modeling (MLM) pre-training objective outputs similar token representations (last hidden states of different tokens) and head representations (attention weights of different heads), which may make the diversity of information expressed by different tokens and heads limited. Motivated by the above investigation, we propose two novel techniques to improve pre-trained language models: Decoupled Directional Relative Position (DDRP) encoding and MTH pre-training objective. DDRP decouples the relative distance features and the directional features in classical relative position encoding. MTH applies two novel auxiliary regularizers besides MLM to enlarge the dissimilarities between (a) last hidden states of different tokens, and (b) attention weights of different heads. These designs allow the model to capture different categories of information more clearly, as a way to alleviate information confusion in representation learning for better optimization. Extensive experiments and ablation studies on GLUE benchmark demonstrate the effectiveness of our proposed methods., Comment: EACL 2023(Findings)

We study continuous variable coherence of phase-dependent squeezed state based on an extended Hanbury Brown-Twiss scheme. High-order coherence is continuously varied by adjusting squeezing parameter $r$, displacement $\alpha $, and squeezing phase $\theta $. We also analyze effects of background noise $\gamma $ and detection efficiency $\eta $ on the measurements. As the squeezing phase shifts from 0 to $\pi $, the photon statistics of the squeezed state continuously change from the anti-bunching ($g^{(n)}<1$) to super-bunching ($g^{(n)}>n!$) which shows a transition from particle nature to wave nature. The experiment feasibility is also examined. It provides a practical method to generate phase-dependent squeezed states with high-order continuous-variable coherence by tuning squeezing phase $\theta $. The controllable coherence source can be applied to sensitivity improvement in gravitational wave detection and quantum imaging., Comment: 13 pages, 6 figures

Time-delay signature (TDS) suppression of semiconductor lasers with external optical feedback is necessary to ensure the security of chaos-based secure communications. Here we numerically and experimentally demonstrate a technique to effectively suppress the TDS of chaotic lasers using quantum noise. The TDS and dynamical complexity are quantified using the autocorrelation function and normalized permutation entropy at the feedback delay time, respectively. Quantum noise from quadrature fluctuations of vacuum state is prepared through balanced homodyne measurement. The effects of strength and bandwidth of quantum noise on chaotic TDS suppression and complexity enhancement are investigated numerically and experimentally. Compared to the original dynamics, the TDS of this quantum-noise improved chaos is suppressed up to 94% and the bandwidth suppression ratio of quantum noise to chaotic laser is 1:25. The experiment agrees well with the theory. The improved chaotic laser is potentially beneficial to chaos-based random number generation and secure communication., Comment: 4 pages, 5 figures

By frequency-band extracting, we experimentally and theoretically investigate time-delay signature (TDS) suppression and entropy growth enhancement of a chaotic optical-feedback semiconductor laser under different injection currents and feedback strengths. The TDS and entropy growth are quantified by the peak value of autocorrelation function and the difference of permutation entropy at the feedback delay time. At the optimal extracting bandwidth, the measured TDS is suppressed up to 96% compared to the original chaos, and the entropy growth is higher than the noise-dominated threshold indicating that the dynamical process is noisy. The effects of extracting bandwidth and radio frequencies on the TDS and entropy growth are also clarified experimentally and theoretically. The experimental results are in good agreements with the theoretical results. The skewness of the laser intensity distribution is effectively improved to 0.001 with the optimal extracting bandwidth. This technique provides a promising tool to extract randomness and prepare desired entropy sources for chaotic secure communication and random number generation., Comment: 11 pages, 8 figures