Search

In computer vision, traditional ensemble learning methods exhibit either a low training efficiency or the limited performance to enhance the reliability of deep neural networks. In this paper, we propose a lightweight, loss-function-free, and architecture-agnostic ensemble learning by the Decorrelating Structure via Adapters (DSA) for various visual tasks. Concretely, the proposed DSA leverages the structure-diverse adapters to decorrelate multiple prediction heads without any tailed regularization or loss. This allows DSA to be easily extensible to architecture-agnostic networks for a range of computer vision tasks. Importantly, the theoretically analysis shows that the proposed DSA has a lower bias and variance than that of the single head based method (which is adopted by most of the state of art approaches). Consequently, the DSA makes deep networks reliable and robust for the various real-world challenges, \textit{e.g.}, data corruption, and label noises. Extensive experiments combining the proposed method with FreeMatch achieved the accuracy improvements of 5.35% on CIFAR-10 dataset with 40 labeled data and 0.71% on CIFAR-100 dataset with 400 labeled data. Besides, combining the proposed method with DualPose achieved the improvements in the Percentage of Correct Keypoints (PCK) by 2.08% on the Sniffing dataset with 100 data (30 labeled data), 5.2% on the FLIC dataset with 100 data (including 50 labeled data), and 2.35% on the LSP dataset with 200 data (100 labeled data).

Orbital degrees of freedom play an important role for understanding the emergence of unconventional quantum phases. Ultracold atomic gases in optical lattices provide a wonderful platform to simulate orbital physics. In this work, we consider spinless fermionic atoms loaded into $p$-orbital bands of a two-dimensional frustrated triangular lattice. The system can be described by an extended Fermi-Hubbard model, which is numerically solved by using the orbital version of real-space dynamical mean-field theory. Low-temperature phase diagrams are obtained, which contain stripe-, ferro- and para-orbital ordered quantum phases, due to the interplay of anisotropic hoppings and geometrical frustration. In order to understand the underlying mechanics of competing orbital orders, we derive an effective orbital-exchange model, which yields consistent explanation with our main numerical results., Comment: 9 pages, 7 figures

How to bridge generative procedural art and visual generative artificial intelligence (AI) for visual content creation is an under-explored topic. On the one hand, there are many cases where creative programmers can make use of generative AI, including stylizing canvas content and creating new content based on the existing styles of certain procedural art (style learning). On the other hand, existing approaches don't support creative programmers to flexibly leverage visual generative AI methods within the creative coding environment. In this work, we explore how to bridge generative procedural art creation and visual generative AI (specifically diffusion models) by programming functionalities integrated into the creative environment. Specifically, we want to explore methodologies to condition/stylize art content and perform style learning upon procedural art via accessible interactions for artists and programmers. We proposed two methods: GenP5, a novel p5.js library enabling generative procedural art creation with flexibly stylizing canvas content and conveniently condition art creation with pre-determined patterns; and P52Style, an extended library built upon p5.gui allowing flexible adjustment of art content and leverage of visual generative AI for style learning tasks.

Crack detection has become an indispensable, interesting yet challenging task in the computer vision community. Specially, pavement cracks have a highly complex spatial structure, a low contrasting background and a weak spatial continuity, posing a significant challenge to an effective crack detection method. In this paper, we address these problems from a view that utilizes contexts of the cracks and propose an end-to-end deep learning method to model the context information flow. To precisely localize crack from an image, it is critical to effectively extract and aggregate multi-granularity context, including the fine-grained local context around the cracks (in spatial-level) and the coarse-grained semantics (in segment-level). Concretely, in Convolutional Neural Network (CNN), low-level features extracted by the shallow layers represent the local information, while the deep layers extract the semantic features. Additionally, a second main insight in this work is that the semantic context should be an guidance to local context feature. By the above insights, the proposed method we first apply the dilated convolution as the backbone feature extractor to model local context, then we build a context guidance module to leverage semantic context to guide local feature extraction at multiple stages. To handle label alignment between stages, we apply the Multiple Instance Learning (MIL) strategy to align the high-level feature to the low-level ones in the stage-wise context flow. In addition, compared with these public crack datasets, to our best knowledge, we release the largest, most complex and most challenging Bitumen Pavement Crack (BPC) dataset. The experimental results on the three crack datasets demonstrate that the proposed method performs well and outperforms the current state-of-the-art methods.

Semi-supervised learning (SSL) is a practical challenge in computer vision. Pseudo-label (PL) methods, e.g., FixMatch and FreeMatch, obtain the State Of The Art (SOTA) performances in SSL. These approaches employ a threshold-to-pseudo-label (T2L) process to generate PLs by truncating the confidence scores of unlabeled data predicted by the self-training method. However, self-trained models typically yield biased and high-variance predictions, especially in the scenarios when a little labeled data are supplied. To address this issue, we propose a lightweight channel-based ensemble method to effectively consolidate multiple inferior PLs into the theoretically guaranteed unbiased and low-variance one. Importantly, our approach can be readily extended to any SSL framework, such as FixMatch or FreeMatch. Experimental results demonstrate that our method significantly outperforms state-of-the-art techniques on CIFAR10/100 in terms of effectiveness and efficiency.

Existing Quantization-Aware Training (QAT) methods intensively depend on the complete labeled dataset or knowledge distillation to guarantee the performances toward Full Precision (FP) accuracies. However, empirical results show that QAT still has inferior results compared to its FP counterpart. One question is how to push QAT toward or even surpass FP performances. In this paper, we address this issue from a new perspective by injecting the vicinal data distribution information to improve the generalization performances of QAT effectively. We present a simple, novel, yet powerful method introducing an Consistency Regularization (CR) for QAT. Concretely, CR assumes that augmented samples should be consistent in the latent feature space. Our method generalizes well to different network architectures and various QAT methods. Extensive experiments demonstrate that our approach significantly outperforms the current state-of-the-art QAT methods and even FP counterparts., Comment: 11 pages, 5 figures

Both semi-supervised classification and regression are practically challenging tasks for computer vision. However, semi-supervised classification methods are barely applied to regression tasks. Because the threshold-to-pseudo label process (T2L) in classification uses confidence to determine the quality of label. It is successful for classification tasks but inefficient for regression tasks. In nature, regression also requires unbiased methods to generate high-quality labels. On the other hand, T2L for classification often fails if the confidence is generated by a biased method. To address this issue, in this paper, we propose a theoretically guaranteed constraint for generating unbiased labels based on Chebyshev's inequality, combining multiple predictions to generate superior quality labels from several inferior ones. In terms of high-quality labels, the unbiased method naturally avoids the drawback of T2L. Specially, we propose an Unbiased Pseudo-labels network (UBPL network) with multiple branches to combine multiple predictions as pseudo-labels, where a Feature Decorrelation loss (FD loss) is proposed based on Chebyshev constraint. In principle, our method can be used for both classification and regression and can be easily extended to any semi-supervised framework, e.g. Mean Teacher, FixMatch, DualPose. Our approach achieves superior performance over SOTAs on the pose estimation datasets Mouse, FLIC and LSP, as well as the classification datasets CIFAR10/100 and SVHN.

Semi-supervised pose estimation is a practically challenging task for computer vision. Although numerous excellent semi-supervised classification methods have emerged, these methods typically use confidence to evaluate the quality of pseudo-labels, which is difficult to achieve in pose estimation tasks. For example, in pose estimation, confidence represents only the possibility that a position of the heatmap is a keypoint, not the quality of that prediction. In this paper, we propose a simple yet efficient framework to estimate the quality of pseudo-labels in semi-supervised pose estimation tasks from the perspective of modeling the uncertainty of the pseudo-labels. Concretely, under the dual mean-teacher framework, we construct the two maximum discrepant students (MDSs) to effectively push two teachers to generate different decision boundaries for the same sample. Moreover, we create multiple uncertainties to assess the quality of the pseudo-labels. Experimental results demonstrate that our method improves the performance of semi-supervised pose estimation on three datasets.

Creating stylized visualization requires going beyond the limited, abstract, geometric marks produced by most tools. Rather, the designer builds stylized idioms where the marks are both transformed (e.g., photographs of candles instead of bars) and also synthesized into a 'scene' that pushes the boundaries of traditional visualizations. To support this, we introduce viz2viz, a system for transforming visualizations with a textual prompt to a stylized form. The system follows a high-level recipe that leverages various generative methods to produce new visualizations that retain the properties of the original dataset. While the base recipe is consistent across many visualization types, we demonstrate how it can be specifically adapted to the creation of different visualization types (bar charts, area charts, pie charts, and network visualizations). Our approach introduces techniques for using different prompts for different marks (i.e., each bar can be something completely different) while still retaining image "coherence." We conclude with an evaluation of the approach and discussion on extensions and limitations., Comment: 17 pages

Eliminating ghosting artifacts due to moving objects is a challenging problem in high dynamic range (HDR) imaging. In this letter, we present a hybrid model consisting of a convolutional encoder and a Transformer decoder to generate ghost-free HDR images. In the encoder, a context aggregation network and non-local attention block are adopted to optimize multi-scale features and capture both global and local dependencies of multiple low dynamic range (LDR) images. The decoder based on Swin Transformer is utilized to improve the reconstruction capability of the proposed model. Motivated by the phenomenal difference between the presence and absence of artifacts under the field of structure tensor (ST), we integrate the ST information of LDR images as auxiliary inputs of the network and use ST loss to further constrain artifacts. Different from previous approaches, our network is capable of processing an arbitrary number of input LDR images. Qualitative and quantitative experiments demonstrate the effectiveness of the proposed method by comparing it with existing state-of-the-art HDR deghosting models. Codes are available at https://github.com/pandayuanyu/HSTHdr.

Capturing highly appreciated star field images is extremely challenging due to light pollution, the requirements of specialized hardware, and the high level of photographic skills needed. Deep learning-based techniques have achieved remarkable results in low-light image enhancement (LLIE) but have not been widely applied to star field image enhancement due to the lack of training data. To address this problem, we construct the first Star Field Image Enhancement Benchmark (SFIEB) that contains 355 real-shot and 854 semi-synthetic star field images, all having the corresponding reference images. Using the presented dataset, we propose the first star field image enhancement approach, namely StarDiffusion, based on conditional denoising diffusion probabilistic models (DDPM). We introduce dynamic stochastic corruptions to the inputs of conditional DDPM to improve the performance and generalization of the network on our small-scale dataset. Experiments show promising results of our method, which outperforms state-of-the-art low-light image enhancement algorithms. The dataset and codes will be open-sourced.

The fusion of images taken by heterogeneous sensors helps to enrich the information and improve the quality of imaging. In this article, we present a hybrid model consisting of a convolutional encoder and a Transformer-based decoder to fuse multimodal images. In the encoder, a non-local cross-modal attention block is proposed to capture both local and global dependencies of multiple source images. A branch fusion module is designed to adaptively fuse the features of the two branches. We embed a Transformer module with linear complexity in the decoder to enhance the reconstruction capability of the proposed network. Qualitative and quantitative experiments demonstrate the effectiveness of the proposed method by comparing it with existing state-of-the-art fusion models. The source code of our work is available at https://github.com/pandayuanyu/HCFusion.

Sub-femtosecond x-ray burst is powerful tool for probing and imaging electronic and concomitant atomic motion in attosecond physics. For years, x-ray source (above 2 keV) had mainly been obtained from X-ray free electron laser (XFEL) or synchrotron radiation, which are high energy consumption, high cost and huge volume. Here we propose a low-cost and small-size method to generate X-ray source. We experimentally obtained high photon energy spectrum (~ 5.2 keV) through both atom and multiple valence state ions using a near-infrared 1.45 {\mu}m driving laser interacting with krypton gas, according to our knowledge, which is the highest photon energy generated through high-order harmonic generation up to now. In our scheme, multi-keV photon energy can be achieved with a relaxed requirement on experimental conditions, and make time-resolved studies more accessible to many laboratories that are capable of producing high energy photon extending to hard x-ray region. Furthermore, our scheme minimizes the influence of X-ray fluorescence process on detection, and can also be utilized to study the quantum-optical nature of high-order harmonic generation., Comment: 11 pages, 4 figures, research article,submitted to Optica