Point cloud quality assessment (PCQA) is essential for reliable 3D visual applications. While point-based methods face challenges in characterizing distortions due to point cloud disorder, projection-based approaches offer better efficiency but suffer from geometric distortion insensitivity and texture representation blind spots. This study proposes SAF-Net, a multi-view structure-aware feature fusion network for PCQA. We first identify two key limitations in projection-based methods: insufficient geometric distortion perception and representation blind spots (RBS) in texture images. To address these issues, SAF-Net innovatively integrates object mask maps and local binary pattern (LBP) maps. The mask maps enhance geometric distortion perception by extracting edge sharpness and curvature variations, while LBP maps capture essential structural information to overcome RBS and align with human visual system (HVS) sensitivity. SAF-Net employs a hybrid CNN-ViT architecture to balance local feature extraction and global context modeling, along with a progressive fusion strategy to optimize cross-modal feature interaction. Extensive experiments demonstrate the superior performance of SAF-Net on multiple benchmarks, establishing new state-of-the-art results in PCQA.

The increasing complexity of software systems has made them more prone to bugs, prompting the development of automated bug localization techniques to ensure software reliability. Despite these techniques having demonstrated notable success at the file level, their application and optimization at the function level often encounter serious performance cliffs. This limitation underscores the urgent need for a dedicated framework for function-level bug localization, which we address through FunLoc, a novel framework that takes coarse-grained source files as input units and identifies fine-grained buggy functions as output. To address the critical challenges of handling domain-specific bug reports and managing vast function-level sample space, we introduce two key innovations that are seamlessly integrated into FunLoc. First, we design a contrastive learning-based domain-adaptive language model to enhance the framework's ability to process and interpret specialized bug reports effectively. Second, we propose an active learning-based dynamic negative sampling strategy to address the scalability issues arising from the extensive function-level sample space. To evaluate the effectiveness of our approach, we extend and release a function-level bug localization dataset derived from large-scale real-world projects. Extensive experiments demonstrate that our approach outperforms state-of-the-art techniques.

Existing blind image quality assessment (BIQA) models are susceptible to biases related to distortion intensity and domain. Intensity bias refers to the relatively accurate perception of severe distortions but larger estimation errors for mild distortions, while domain bias stems from the discrepancies between synthetic and authentic distortion properties. This work introduces a unified learning framework towards addressing these distortion biases. We integrate distortion perception and restoration methods to mitigate intensity bias, where images with minor distortions, which are easily restorable, serve as references for mildly distorted images, while severe distortions benefit directly from distortion perception. The restoration modules employ a combined image-level and feature-level denoising approach, and then an intensity-aware cross-attention mechanism is designed for adaptive handling of intensity bias. To tackle domain bias, we introduce a distortion domain recognition task based on the intrinsic differences between distortion domains and use intra-domain similarity for weighting the quality scores from these domains. Experimental results show that the proposed method achieves state-of-the-art performance on multiple synthetic and authentic distortion datasets. Code and models will be available at https://github.com/xxVENTAZEDxx/Distortion-Debiased-BIQA

Abstract Contrastive learning has emerged as an essential approach in self-supervised visual representation learning. Its main goal is to maximize the similarities between augmented versions of the same image (positive pairs), while minimizing the similarities between different images (negative pairs). Recent studies have demonstrated that harder negative samples, i.e., those that are more challenging to differentiate from the anchor sample perform a more crucial function in contrastive learning. However, many existing contrastive learning methods ignore the role of hard negative samples. In order to provide harder negative samples for the network model more efficiently. This paper proposes a novel feature-level sample sampling method, namely sampling synthetic hard negative samples for contrastive learning (SSCL). Specifically, we generate more and harder negative samples by mixing them through linear combination and ensure their reliability by debiasing. Finally, we execute weighted sampling of these negative samples. Compared to state-of-the-art methods, our method can provide more high-quality negative samples. Experiments show that SSCL improves the classification performance on different image datasets and can be readily integrated into existing methods.

Deep neural networks have achieved remarkable results across various tasks. However, they are susceptible to adversarial examples, which are generated by adding adversarial perturbations to original data. Adversarial training (AT) is the most effective defense mechanism against adversarial examples and has received significant attention. Recent studies highlight the importance of example exploitation, where the model’s learning intensity is altered for specific examples to extend classic AT approaches. However, the analysis methodologies employed by these studies are varied and contradictory, which may lead to confusion in future research. To address this issue, we provide a comprehensive summary of representative strategies focusing on exploiting examples within a unified framework. Furthermore, we investigate the role of examples in AT and find that examples which contribute primarily to accuracy or robustness are distinct. Based on this finding, we propose a novel example-exploitation idea that can further improve the performance of advanced AT methods. This new idea suggests that critical challenges in AT, such as the accuracy-robustness trade-off, robust overfitting, and catastrophic overfitting, can be alleviated simultaneously from an example-exploitation perspective. The code can be found in https://github.com/geyao1995/advancing-example-exploitation-in-adversarial-training.

Vector of Locally Aggregated Descriptors (VLAD) method, which aggregates descriptors and produces a compact image representation, has achieved great success in the field of image classification and retrieval. However, the original VLAD method is a hard assignment strategy that only assigns each descriptor to the nearest neighbor visual word in dictionary, which leads to large quantization error. In this paper, improved VLAD based on adaptive bases and saliency weights is proposed to solve the above problem. The new method considers the local density distribution when assigning local descriptors, adaptively selects several nearest neighbor visual words, and takes the coding coefficients obtained by utilizing saliency as the weights of the selected visual words. Experimental results on Corel 10, 15 Scenes and UIUC Sports Event datasets show that the new coding method proposed in this paper achieves better classification performance compared with the existing five VLAD based methods and two commonly used representation methods.

Visual Question Answering (VQA) is a hot-spot in the intersection of computer vision and natural language processing research and its progress has enabled many in high-level applications. This work aims to describe a novel VQA model based on semantic concept network construction and deep walk. Extracting visual image semantic representation is a significant and effective method for spanning the semantic gap. Moreover, current research has shown that co-occurrence patterns of concepts can enhance semantic representation. This work is motivated by the challenge that semantic concepts have complex interrelations and the relationships are similar to a network. Therefore, we construct a semantic concept network adopted by leveraging Word Activation Forces (WAFs), and mine the co-occurrence patterns of semantic concepts using deep walk. Then the model performs polynomial logistic regression on the basis of the extracted deep walk vector along with the visual image feature and question feature. The proposed model effectively integrates visual and semantic features of the image and natural language question. The experimental results show that our algorithm outperforms competitive baselines on three benchmark image QA datasets. Furthermore, through experiments in image annotation refinement and semantic analysis on pre-labeled LabelMe dataset, we test and verify the effectiveness of our constructed concept network for mining concept co-occurrence patterns, sensible concept clusters, and hierarchies.

Concept Factorization (CF) divides a matrix into the product of three matrices. It is considered as one variant of Non-negative Matrix Factorization (NMF). The biggest difference between the two methods is that CF can be executed in a kernel space. Because of this characteristic, many schemes based on CF have been proposed in computer vision and pattern recognition fields. Recent studies have shown that high dimensional data is often located in a low dimensional manifold space, in order to improve the performance and reduce the storage space, how to find the mapping function is particularly important. In addition, the development of supervised learning methods show that label information is critical to enhance the model's ability. In this paper, a supervised graph regularized discriminative concept factorization (SGDCF) method is presented for image clustering. In the SGDCF, we make use of local manifold geometry structure and label information. The corresponding multiplicative update solutions and convergence verification are given. Clustering results on four image data sets reveal that the SGDCF outperforms the state-of-the-art algorithms in terms of accuracy and normalized mutual information.

A fragile software watermarking scheme for integrity verification of software is proposed in this paper. The algorithm uses the idea of semantic-preserving code substitution for embedding the watermark. With the system, the generated watermark relates closely to the content of software, and the scheme has highly sensitive to different types of attacks. Furthermore, both watermark generating controlled by a key and watermark embedding position under the control of another key enhance the security of watermarking scheme. The scheme not only can effectively detect tampering, but also has the ability to identify the type of tampering clearly.