Fully supervised salient object detection (SOD) has made considerable progress based on expensive and time-consuming data with pixel-wise annotations. Recently, to relieve the labeling burden while maintaining performance, some scribble-based SOD methods have been proposed. However, learning precise boundary details from scribble annotations that lack edge information is still difficult. In this paper, we propose to learn precise boundaries from our designed synthetic images and labels without introducing any extra auxiliary data. The synthetic image creates boundary information by inserting synthetic concave regions that simulate the real concave regions of salient objects. Furthermore, we propose a novel self-consistent framework that consists of a global integral branch (GIB) and a boundary-aware branch (BAB) to train a saliency detector. GIB aims to identify integral salient objects, whose input is the original image. BAB aims to help predict accurate boundaries, whose input is the synthetic image. These two branches are connected through a self-consistent loss to guide the saliency detector to predict precise boundaries while identifying salient objects. Experimental results on five benchmarks demonstrate that our method outperforms the state-of-the-art weakly supervised SOD methods and further narrows the gap with the fully supervised methods.

基于3DCNN，ConvlSTM或光流的先前方法在视频显着对象检测（VSOD）方面取得了巨大成功。但是，它们仍然遭受高计算成本或产生的显着图质量较差的困扰。为了解决这些问题，我们设计了一个基于时空存储器（STM）网络，该网络从相邻帧中提取当前帧的有用时间信息作为VSOD的时间分支。此外，以前的方法仅考虑无时间关联的单帧预测。结果，模型可能无法充分关注时间信息。因此，我们最初将框架间的对象运动预测引入VSOD。我们的模型遵循标准编码器 - 编码器体系结构。在编码阶段，我们通过使用电流及其相邻帧的高级功能来生成高级的时间特征。这种方法比基于光流的方法更有效。在解码阶段，我们提出了一种有效的空间和时间分支融合策略。高级特征的语义信息用于融合低级特征中的对象细节，然后逐步获得时空特征以重建显着性图。此外，受图像显着对象检测（ISOD）中常用的边界监督的启发，我们设计了一种运动感知损失，用于预测对象边界运动，并同时对VSOD和对象运动预测执行多任务学习，这可以进一步促进模型以提取提取的模型时空特征准确并保持对象完整性。在几个数据集上进行的广泛实验证明了我们方法的有效性，并且可以在某些数据集上实现最新指标。所提出的模型不需要光流或其他预处理，并且在推理过程中可以达到近100 fps的速度。

当测试图像提出看不见的分布时，深层分割模型通常会面临故障风险。改善模型鲁棒性针对这些风险的鲁棒性对于深层模型的大规模临床应用至关重要。在这项研究中，受到人类学习周期的启发，我们提出了一个新颖的在线反思学习框架（REFSEG），以改善细分鲁棒性。基于启用概念的反射概念，我们的refseg首先驱动了深层模型以采取行动以获得语义分割。然后，refseg触发模型以反映自身。因为使深层模型在测试过程中意识到他们的细分失败是具有挑战性的，所以RefSeg合成了从语义面具中综合的逼真的代理图像，以帮助深层模型构建直观有效的反射。该代理翻译并强调了分割缺陷。通过最大程度地提高原始输入和代理之间的结构相似性，可以改善分割鲁棒性的反射循环。 REFSEG在测试阶段运行，并且是分割模型的一般性。通过公共心脏MR数据集和两个内部大型超声数据集对三个医疗图像细分任务进行了广泛的验证，这表明我们的refseg显着提高了模型的鲁棒性，并报告了与强大竞争对手有关的最先进的表现。

深度学习技术导致了通用对象检测领域的显着突破，近年来产生了很多场景理解的任务。由于其强大的语义表示和应用于场景理解，场景图一直是研究的焦点。场景图生成（SGG）是指自动将图像映射到语义结构场景图中的任务，这需要正确标记检测到的对象及其关系。虽然这是一项具有挑战性的任务，但社区已经提出了许多SGG方法并取得了良好的效果。在本文中，我们对深度学习技术带来了近期成就的全面调查。我们审查了138个代表作品，涵盖了不同的输入方式，并系统地将现有的基于图像的SGG方法从特征提取和融合的角度进行了综述。我们试图通过全面的方式对现有的视觉关系检测方法进行连接和系统化现有的视觉关系检测方法，概述和解释SGG的机制和策略。最后，我们通过深入讨论当前存在的问题和未来的研究方向来完成这项调查。本调查将帮助读者更好地了解当前的研究状况和想法。

This paper focuses on designing efficient models with low parameters and FLOPs for dense predictions. Even though CNN-based lightweight methods have achieved stunning results after years of research, trading-off model accuracy and constrained resources still need further improvements. This work rethinks the essential unity of efficient Inverted Residual Block in MobileNetv2 and effective Transformer in ViT, inductively abstracting a general concept of Meta-Mobile Block, and we argue that the specific instantiation is very important to model performance though sharing the same framework. Motivated by this phenomenon, we deduce a simple yet efficient modern \textbf{I}nverted \textbf{R}esidual \textbf{M}obile \textbf{B}lock (iRMB) for mobile applications, which absorbs CNN-like efficiency to model short-distance dependency and Transformer-like dynamic modeling capability to learn long-distance interactions. Furthermore, we design a ResNet-like 4-phase \textbf{E}fficient \textbf{MO}del (EMO) based only on a series of iRMBs for dense applications. Massive experiments on ImageNet-1K, COCO2017, and ADE20K benchmarks demonstrate the superiority of our EMO over state-of-the-art methods, \eg, our EMO-1M/2M/5M achieve 71.5, 75.1, and 78.4 Top-1 that surpass \textbf{SoTA} CNN-/Transformer-based models, while trading-off the model accuracy and efficiency well.

Decompilation aims to transform a low-level program language (LPL) (eg., binary file) into its functionally-equivalent high-level program language (HPL) (e.g., C/C++). It is a core technology in software security, especially in vulnerability discovery and malware analysis. In recent years, with the successful application of neural machine translation (NMT) models in natural language processing (NLP), researchers have tried to build neural decompilers by borrowing the idea of NMT. They formulate the decompilation process as a translation problem between LPL and HPL, aiming to reduce the human cost required to develop decompilation tools and improve their generalizability. However, state-of-the-art learning-based decompilers do not cope well with compiler-optimized binaries. Since real-world binaries are mostly compiler-optimized, decompilers that do not consider optimized binaries have limited practical significance. In this paper, we propose a novel learning-based approach named NeurDP, that targets compiler-optimized binaries. NeurDP uses a graph neural network (GNN) model to convert LPL to an intermediate representation (IR), which bridges the gap between source code and optimized binary. We also design an Optimized Translation Unit (OTU) to split functions into smaller code fragments for better translation performance. Evaluation results on datasets containing various types of statements show that NeurDP can decompile optimized binaries with 45.21% higher accuracy than state-of-the-art neural decompilation frameworks.

Image Virtual try-on aims at replacing the cloth on a personal image with a garment image (in-shop clothes), which has attracted increasing attention from the multimedia and computer vision communities. Prior methods successfully preserve the character of clothing images, however, occlusion remains a pernicious effect for realistic virtual try-on. In this work, we first present a comprehensive analysis of the occlusions and categorize them into two aspects: i) Inherent-Occlusion: the ghost of the former cloth still exists in the try-on image; ii) Acquired-Occlusion: the target cloth warps to the unreasonable body part. Based on the in-depth analysis, we find that the occlusions can be simulated by a novel semantically-guided mixup module, which can generate semantic-specific occluded images that work together with the try-on images to facilitate training a de-occlusion try-on (DOC-VTON) framework. Specifically, DOC-VTON first conducts a sharpened semantic parsing on the try-on person. Aided by semantics guidance and pose prior, various complexities of texture are selectively blending with human parts in a copy-and-paste manner. Then, the Generative Module (GM) is utilized to take charge of synthesizing the final try-on image and learning to de-occlusion jointly. In comparison to the state-of-the-art methods, DOC-VTON achieves better perceptual quality by reducing occlusion effects.

In recent years, the Transformer architecture has shown its superiority in the video-based person re-identification task. Inspired by video representation learning, these methods mainly focus on designing modules to extract informative spatial and temporal features. However, they are still limited in extracting local attributes and global identity information, which are critical for the person re-identification task. In this paper, we propose a novel Multi-Stage Spatial-Temporal Aggregation Transformer (MSTAT) with two novel designed proxy embedding modules to address the above issue. Specifically, MSTAT consists of three stages to encode the attribute-associated, the identity-associated, and the attribute-identity-associated information from the video clips, respectively, achieving the holistic perception of the input person. We combine the outputs of all the stages for the final identification. In practice, to save the computational cost, the Spatial-Temporal Aggregation (STA) modules are first adopted in each stage to conduct the self-attention operations along the spatial and temporal dimensions separately. We further introduce the Attribute-Aware and Identity-Aware Proxy embedding modules (AAP and IAP) to extract the informative and discriminative feature representations at different stages. All of them are realized by employing newly designed self-attention operations with specific meanings. Moreover, temporal patch shuffling is also introduced to further improve the robustness of the model. Extensive experimental results demonstrate the effectiveness of the proposed modules in extracting the informative and discriminative information from the videos, and illustrate the MSTAT can achieve state-of-the-art accuracies on various standard benchmarks.

It has been observed in practice that applying pruning-at-initialization methods to neural networks and training the sparsified networks can not only retain the testing performance of the original dense models, but also sometimes even slightly boost the generalization performance. Theoretical understanding for such experimental observations are yet to be developed. This work makes the first attempt to study how different pruning fractions affect the model's gradient descent dynamics and generalization. Specifically, this work considers a classification task for overparameterized two-layer neural networks, where the network is randomly pruned according to different rates at the initialization. It is shown that as long as the pruning fraction is below a certain threshold, gradient descent can drive the training loss toward zero and the network exhibits good generalization performance. More surprisingly, the generalization bound gets better as the pruning fraction gets larger. To complement this positive result, this work further shows a negative result: there exists a large pruning fraction such that while gradient descent is still able to drive the training loss toward zero (by memorizing noise), the generalization performance is no better than random guessing. This further suggests that pruning can change the feature learning process, which leads to the performance drop of the pruned neural network. Up to our knowledge, this is the \textbf{first} generalization result for pruned neural networks, suggesting that pruning can improve the neural network's generalization.

This work studies training one-hidden-layer overparameterized ReLU networks via gradient descent in the neural tangent kernel (NTK) regime, where, differently from the previous works, the networks' biases are trainable and are initialized to some constant rather than zero. The first set of results of this work characterize the convergence of the network's gradient descent dynamics. Surprisingly, it is shown that the network after sparsification can achieve as fast convergence as the original network. The contribution over previous work is that not only the bias is allowed to be updated by gradient descent under our setting but also a finer analysis is given such that the required width to ensure the network's closeness to its NTK is improved. Secondly, the networks' generalization bound after training is provided. A width-sparsity dependence is presented which yields sparsity-dependent localized Rademacher complexity and a generalization bound matching previous analysis (up to logarithmic factors). As a by-product, if the bias initialization is chosen to be zero, the width requirement improves the previous bound for the shallow networks' generalization. Lastly, since the generalization bound has dependence on the smallest eigenvalue of the limiting NTK and the bounds from previous works yield vacuous generalization, this work further studies the least eigenvalue of the limiting NTK. Surprisingly, while it is not shown that trainable biases are necessary, trainable bias helps to identify a nice data-dependent region where a much finer analysis of the NTK's smallest eigenvalue can be conducted, which leads to a much sharper lower bound than the previously known worst-case bound and, consequently, a non-vacuous generalization bound.