Query：
学者姓名：刘文犀
Refining：
Year
Type
Indexed by
Source
Complex
Co-
Language
Clean All
Abstract ：
Ultra-high resolution image segmentation poses a formidable challenge for UAVs with limited computation resources. Moreover, with multiple deployed tasks (e.g., mapping, localization, and decision making), the demand for a memory efficient model becomes more urgent. This letter delves into the intricate problem of achieving efficient and effective segmentation of ultra-high resolution UAV imagery, while operating under stringent GPU memory limitation. To address this problem, we propose a GPU memory-efficient and effective framework. Specifically, we introduce a novel and efficient spatial-guided high-resolution query module, which enables our model to effectively infer pixel-wise segmentation results by querying nearest latent embeddings from low-resolution features. Additionally, we present a memory-based interaction scheme with linear complexity to rectify semantic bias beneath the high-resolution spatial guidance via associating cross-image contextual semantics. For evaluation, we perform comprehensive experiments over public benchmarks under both conditions of small and large GPU memory usage limitations. Notably, our model gains around 3% advantage against SOTA in mIoU using comparable memory. Furthermore, we show that our model can be deployed on the embedded platform with less than 8 G memory like Jetson TX2.
Keyword ：
Aerial Systems: Perception and Autonomy Aerial Systems: Perception and Autonomy Autonomous aerial vehicles Autonomous aerial vehicles Deep Learning for Visual Perception Deep Learning for Visual Perception Graphics processing units Graphics processing units Image resolution Image resolution Memory management Memory management Semantics Semantics Semantic segmentation Semantic segmentation Spatial resolution Spatial resolution
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Li, Qi , Cai, Jiaxin , Luo, Jiexin et al. Memory-Constrained Semantic Segmentation for Ultra-High Resolution UAV Imagery [J]. | IEEE ROBOTICS AND AUTOMATION LETTERS , 2024 , 9 (2) : 1708-1715 . |
| MLA | Li, Qi et al. "Memory-Constrained Semantic Segmentation for Ultra-High Resolution UAV Imagery" . | IEEE ROBOTICS AND AUTOMATION LETTERS 9 . 2 (2024) : 1708-1715 . |
| APA | Li, Qi , Cai, Jiaxin , Luo, Jiexin , Yu, Yuanlong , Gu, Jason , Pan, Jia et al. Memory-Constrained Semantic Segmentation for Ultra-High Resolution UAV Imagery . | IEEE ROBOTICS AND AUTOMATION LETTERS , 2024 , 9 (2) , 1708-1715 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Domain Generalization (DG) aims to generalize a model trained on multiple source domains to an unseen target domain. The source domains always require precise annotations, which can be cumbersome or even infeasible to obtain in practice due to the vast amount of data involved. Web data, namely web -crawled images, offers an opportunity to access large amounts of unlabeled images with rich style information, which can be leveraged to improve DG. From this perspective, we introduce a novel paradigm of DG, termed as Semi -Supervised Domain Generalization (SSDG), to explore how the labeled and unlabeled source domains can interact, and establish two settings, including the close -set and open -set SSDG. The close -set SSDG is based on existing public DG datasets, while the open -set SSDG, built on the newly -collected web -crawled datasets, presents a novel yet realistic challenge that pushes the limits of current technologies. A natural approach of SSDG is to transfer knowledge from labeled data to unlabeled data via pseudo labeling, and train the model on both labeled and pseudo -labeled data for generalization. Since there are conflicting goals between domain -oriented pseudo labeling and out -of -domain generalization, we develop a pseudo labeling phase and a generalization phase independently for SSDG. Unfortunately, due to the large domain gap, the pseudo labels provided in the pseudo labeling phase inevitably contain noise, which has negative affect on the subsequent generalization phase. Therefore, to improve the quality of pseudo labels and further enhance generalizability, we propose a cyclic learning framework to encourage a positive feedback between these two phases, utilizing an evolving intermediate domain that bridges the labeled and unlabeled domains in a curriculum learning manner. Extensive experiments are conducted to validate the effectiveness of our method. It is worth highlighting that web -crawled images can promote domain generalization as demonstrated by the experimental results.
Keyword ：
Domain generalization Domain generalization Semi-supervised learning Semi-supervised learning Transfer learning Transfer learning Unsupervised domain adaptation Unsupervised domain adaptation
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Lin, Luojun , Xie, Han , Sun, Zhishu et al. Semi-supervised domain generalization with evolving intermediate domain [J]. | PATTERN RECOGNITION , 2024 , 149 . |
| MLA | Lin, Luojun et al. "Semi-supervised domain generalization with evolving intermediate domain" . | PATTERN RECOGNITION 149 (2024) . |
| APA | Lin, Luojun , Xie, Han , Sun, Zhishu , Chen, Weijie , Liu, Wenxi , Yu, Yuanlong et al. Semi-supervised domain generalization with evolving intermediate domain . | PATTERN RECOGNITION , 2024 , 149 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Nighttime semantic segmentation is an important but challenging research problem for autonomous driving. The major challenges lie in the small objects or regions from the under-/over-exposed areas or suffer from motion blur caused by the camera deployed on moving vehicles. To resolve this, we propose a novel hard-class-aware module that bridges the main network for full-class segmentation and the hard-class network for segmenting aforementioned hard-class objects. In specific, it exploits the shared focus of hard-class objects from the dual-stream network, enabling the contextual information flow to guide the model to concentrate on the pixels that are hard to classify. In the end, the estimated hard-class segmentation results will be utilized to infer the final results via an adaptive probabilistic fusion refinement scheme. Moreover, to overcome over-smoothing and noise caused by extreme exposures, our model is modulated by a carefully crafted pretext task of constructing an exposure-aware semantic gradient map, which guides the model to faithfully perceive the structural and semantic information of hard-class objects while mitigating the negative impact of noises and uneven exposures. In experiments, we demonstrate that our unique network design leads to superior segmentation performance over existing methods, featuring the strong ability of perceiving hard-class objects under adverse conditions. © 2024 Copyright held by the owner/author(s). Publication rights licensed to ACM.
Keyword ：
Classification (of information) Classification (of information) Semantics Semantics Semantic Segmentation Semantic Segmentation
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Liu, Wenxi , Cai, Jiaxin , Li, Qi et al. Learning Nighttime Semantic Segmentation the Hard Way [J]. | ACM Transactions on Multimedia Computing, Communications and Applications , 2024 , 20 (7) . |
| MLA | Liu, Wenxi et al. "Learning Nighttime Semantic Segmentation the Hard Way" . | ACM Transactions on Multimedia Computing, Communications and Applications 20 . 7 (2024) . |
| APA | Liu, Wenxi , Cai, Jiaxin , Li, Qi , Liao, Chenyang , Cao, Jingjing , He, Shengfeng et al. Learning Nighttime Semantic Segmentation the Hard Way . | ACM Transactions on Multimedia Computing, Communications and Applications , 2024 , 20 (7) . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Semantic segmentation is one of the directions in image research. It aims to obtain the contours of objects of interest, facilitating subsequent engineering tasks such as measurement and feature selection. However, existing segmentation methods still lack precision in class edge, particularly in multi -class mixed region. To this end, we present the Feature Enhancement Network (FE -Net), a novel approach that leverages edge label and pixel -wise weights to enhance segmentation performance in complex backgrounds. Firstly, we propose a Smart Edge Head (SE -Head) to process shallow -level information from the backbone network. It is combined with the FCN-Head and SepASPP-Head, located at deeper layers, to form a transitional structure where the loss weights gradually transition from edge labels to semantic labels and a mixed loss is also designed to support this structure. Additionally, we propose a pixel -wise weight evaluation method, a pixel -wise weight block, and a feature enhancement loss to improve training effectiveness in multi -class regions. FE -Net achieves significant performance improvements over baselines on publicly datasets Pascal VOC2012, SBD, and ATR, with best mIoU enhancements of 15.19%, 1.42% and 3.51%, respectively. Furthermore, experiments conducted on Pole&Hole match dataset from our laboratory environment demonstrate the superior effectiveness of FE -Net in segmenting defined key pixels.
Keyword ：
Edge label Edge label Key pixels Key pixels Multi-class mixed region Multi-class mixed region Pixel-wise weight Pixel-wise weight Semantic segmentation Semantic segmentation
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Zhao, Zhangyan , Chen, Xiaoming , Cao, Jingjing et al. FE-Net: Feature enhancement segmentation network [J]. | NEURAL NETWORKS , 2024 , 174 . |
| MLA | Zhao, Zhangyan et al. "FE-Net: Feature enhancement segmentation network" . | NEURAL NETWORKS 174 (2024) . |
| APA | Zhao, Zhangyan , Chen, Xiaoming , Cao, Jingjing , Zhao, Qiangwei , Liu, Wenxi . FE-Net: Feature enhancement segmentation network . | NEURAL NETWORKS , 2024 , 174 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
HD map reconstruction is crucial for autonomous driving. LiDAR-based methods are limited due to expensive sensors and time-consuming computation. Camera-based methods usually need to perform road segmentation and view transformation separately, which often causes distortion and missing content. To push the limits of the technology, we present a novel framework that reconstructs a local map formed by road layout and vehicle occupancy in the bird's-eye view given a front-view monocular image only. We propose a front-to-top view projection (FTVP) module, which takes the constraint of cycle consistency between views into account and makes full use of their correlation to strengthen the view transformation and scene understanding. In addition, we apply multi-scale FTVP modules to propagate the rich spatial information of low-level features to mitigate spatial deviation of the predicted object location. Experiments on public benchmarks show that our method achieves various tasks on road layout estimation, vehicle occupancy estimation, and multi-class semantic estimation, at a performance level comparable to the state-of-the-arts, while maintaining superior efficiency. IEEE
Keyword ：
Autonomous driving Autonomous driving BEV perception BEV perception Estimation Estimation Feature extraction Feature extraction Layout Layout Roads Roads segmentation segmentation Task analysis Task analysis Three-dimensional displays Three-dimensional displays Transformers Transformers
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Liu, W. , Li, Q. , Yang, W. et al. Monocular BEV Perception of Road Scenes Via Front-to-Top View Projection [J]. | IEEE Transactions on Pattern Analysis and Machine Intelligence , 2024 , 46 (9) : 1-17 . |
| MLA | Liu, W. et al. "Monocular BEV Perception of Road Scenes Via Front-to-Top View Projection" . | IEEE Transactions on Pattern Analysis and Machine Intelligence 46 . 9 (2024) : 1-17 . |
| APA | Liu, W. , Li, Q. , Yang, W. , Cai, J. , Yu, Y. , Ma, Y. et al. Monocular BEV Perception of Road Scenes Via Front-to-Top View Projection . | IEEE Transactions on Pattern Analysis and Machine Intelligence , 2024 , 46 (9) , 1-17 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Nuclei segmentation and classification play a crucial role in pathology diagnosis, enabling pathologists to analyze cellular characteristics accurately. Overlapping cluster nuclei, misdetection of small-scale nuclei, and pleomorphic nuclei-induced misclassification have always been major challenges in the nuclei segmentation and classification tasks. To this end, we introduce an auxiliary task of nuclei boundary-guided contrastive learning to enhance the representativeness and discriminative power of visual features, particularly for addressing the challenge posed by the unclear contours of adherent nuclei and small nuclei. In addition, misclassifications resulting from pleomorphic nuclei often exhibit low classification confidence, indicating a high level of uncertainty. To mitigate misclassification, we capitalize on the characteristic clustering of similar cells to propose a locality-aware class embedding module, offering a regional perspective to capture category information. Moreover, we address uncertain classification in densely aggregated nuclei by designing a top-k uncertainty attention module that leverages deep features to enhance shallow features, thereby improving the learning of contextual semantic information. We demonstrate that the proposed network outperforms the off-the-shelf methods in both nuclei segmentation and classification experiments, achieving the state-of-the-art performance. © 2024 Elsevier Ltd
Keyword ：
Classification (of information) Classification (of information) Computer aided diagnosis Computer aided diagnosis Deep learning Deep learning Image classification Image classification Semantics Semantics Semantic Segmentation Semantic Segmentation
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Liu, Wenxi , Zhang, Qing , Li, Qi et al. Contrastive and uncertainty-aware nuclei segmentation and classification [J]. | Computers in Biology and Medicine , 2024 , 178 . |
| MLA | Liu, Wenxi et al. "Contrastive and uncertainty-aware nuclei segmentation and classification" . | Computers in Biology and Medicine 178 (2024) . |
| APA | Liu, Wenxi , Zhang, Qing , Li, Qi , Wang, Shu . Contrastive and uncertainty-aware nuclei segmentation and classification . | Computers in Biology and Medicine , 2024 , 178 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
伪装目标检测旨在检测隐藏在复杂环境中的高度隐蔽物体，在医学、农业等多个领域有重要应用价值.现有方法结合边界先验过分强调边界区域，对伪装目标内部信息的表征不足，导致模型对伪装目标的内部区域检测不准确.同时，已有方法缺乏对伪装目标前景特征的有效挖掘，使背景区域被误检为伪装目标.为解决上述问题，本文提出一种基于边界特征融合和前景引导的伪装目标检测方法，该方法由特征提取、边界特征融合、主干特征增强和预测等若干个阶段构成.在边界特征融合阶段，首先，通过边界特征提取模块获得边界特征并预测边界掩码；然后，边界特征融合模块将边界特征和边界掩码与最低层次的主干特征有效融合；同时，加强伪装目标边界位置及内部区域特征.此外，设计前景引导模块，利用预测的伪装目标掩码增强主干特征，即将前一层特征预测的伪装目标掩码作为当前层特征的前景注意力，并对特征执行空间交互，提升网络对空间关系的识别能力，使网络关注精细而完整的伪装目标区域.本文在4个广泛使用的基准数据集上的实验结果表明，提出的方法优于对比的19个主流方法，对伪装目标检测任务具有更强鲁棒性和泛化能力.
Keyword ：
伪装目标检测 伪装目标检测 前景引导 前景引导 空间交互 空间交互 边界先验 边界先验 边界掩码 边界掩码 边界特征 边界特征
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 刘文犀 , 张家榜 , 李悦洲 et al. 基于边界特征融合和前景引导的伪装目标检测 [J]. | 电子学报 , 2024 , 52 (07) : 2279-2290 . |
| MLA | 刘文犀 et al. "基于边界特征融合和前景引导的伪装目标检测" . | 电子学报 52 . 07 (2024) : 2279-2290 . |
| APA | 刘文犀 , 张家榜 , 李悦洲 , 赖宇 , 牛玉贞 . 基于边界特征融合和前景引导的伪装目标检测 . | 电子学报 , 2024 , 52 (07) , 2279-2290 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
In recent years, the rapid advancement of image generation techniques has resulted in the widespread abuse of manipulated images, leading to a crisis of trust and affecting social equity. Thus, the goal of our work is to detect and localize tampered regions in images. Many deep learning based approaches have been proposed to address this problem, but they can hardly handle the tampered regions that are manually fine-tuned to blend into image background. By observing that the boundaries of tempered regions are critical to separating tampered and non-tampered parts, we present a novel boundary-guided approach to image manipulation detection, which introduces an inherent bias towards exploiting the boundary information of tampered regions. Our model follows an encoder-decoder architecture, with multi-scale localization mask prediction, and is guided to utilize the prior boundary knowledge through an attention mechanism and contrastive learning. In particular, our model is unique in that 1) we propose a boundary-aware attention module in the network decoder, which predicts the boundary of tampered regions and thus uses it as crucial contextual cues to facilitate the localization; and 2) we propose a multi-scale contrastive learning scheme with a novel boundary-guided sampling strategy, leading to more discriminative localization features. Our state-of-art performance on several public benchmarks demonstrates the superiority of our model over prior works.
Keyword ：
Contrastive learning Contrastive learning Decoding Decoding Deepfakes Deepfakes Feature extraction Feature extraction Image manipulation detection/localization Image manipulation detection/localization Location awareness Location awareness Task analysis Task analysis Visualization Visualization
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Liu, Wenxi , Zhang, Hao , Lin, Xinyang et al. Attentive and Contrastive Image Manipulation Localization With Boundary Guidance [J]. | IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY , 2024 , 19 : 6764-6778 . |
| MLA | Liu, Wenxi et al. "Attentive and Contrastive Image Manipulation Localization With Boundary Guidance" . | IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY 19 (2024) : 6764-6778 . |
| APA | Liu, Wenxi , Zhang, Hao , Lin, Xinyang , Zhang, Qing , Li, Qi , Liu, Xiaoxiang et al. Attentive and Contrastive Image Manipulation Localization With Boundary Guidance . | IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY , 2024 , 19 , 6764-6778 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Graph neural networks (GNNs) are widely used for analyzing graph-structural data and solving graph-related tasks due to their powerful expressiveness. However, existing off-the-shelf GNN-based models usually consist of no more than three layers. Deeper GNNs usually suffer from severe performance degradation due to several issues including the infamous "over-smoothing" issue, which restricts the further development of GNNs. In this article, we investigate the over-smoothing issue in deep GNNs. We discover that over-smoothing not only results in indistinguishable embeddings of graph nodes, but also alters and even corrupts their semantic structures, dubbed semantic over-smoothing. Existing techniques, e.g., graph normalization, aim at handling the former concern, but neglect the importance of preserving the semantic structures in the spatial domain, which hinders the further improvement of model performance. To alleviate the concern, we propose a cluster-keeping sparse aggregation strategy to preserve the semantic structure of embeddings in deep GNNs (especially for spatial GNNs). Particularly, our strategy heuristically redistributes the extent of aggregations for all the nodes from layers, instead of aggregating them equally, so that it enables aggregate concise yet meaningful information for deep layers. Without any bells and whistles, it can be easily implemented as a plug-and-play structure of GNNs via weighted residual connections. Last, we analyze the over-smoothing issue on the GNNs with weighted residual structures and conduct experiments to demonstrate the performance comparable to the state-of-the-arts.
Keyword ：
Aggregates Aggregates Brain modeling Brain modeling Clustering Clustering Convolution Convolution deep graph neural networks (GNNs) deep graph neural networks (GNNs) Degradation Degradation node classification node classification Numerical models Numerical models over-smoothing over-smoothing Semantics Semantics sparse aggregation strategy sparse aggregation strategy Task analysis Task analysis
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Li, Jin , Zhang, Qirong , Liu, Wenxi et al. Another Perspective of Over-Smoothing: Alleviating Semantic Over-Smoothing in Deep GNNs [J]. | IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS , 2024 . |
| MLA | Li, Jin et al. "Another Perspective of Over-Smoothing: Alleviating Semantic Over-Smoothing in Deep GNNs" . | IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2024) . |
| APA | Li, Jin , Zhang, Qirong , Liu, Wenxi , Chan, Antoni B. , Fu, Yang-Geng . Another Perspective of Over-Smoothing: Alleviating Semantic Over-Smoothing in Deep GNNs . | IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS , 2024 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Diagnostic pathology, historically dependent on visual scrutiny by experts, is essential for disease detection. Advances in digital pathology and developments in computer vision technology have led to the application of artificial intelligence (AI) in this field. Despite these advancements, the variability in pathologists’ subjective interpretations of diagnostic criteria can lead to inconsistent outcomes. To meet the need for precision in cancer therapies, there is an increasing demand for accurate pathological diagnoses. Consequently, traditional diagnostic pathology is evolving towards “next-generation diagnostic pathology”, prioritizing on the development of a multi-dimensional, intelligent diagnostic approach. Using nonlinear optical effects arising from the interaction of light with biological tissues, multiphoton microscopy (MPM) enables high-resolution label-free imaging of multiple intrinsic components across various human pathological tissues. AI-empowered MPM further improves the accuracy and efficiency of diagnosis, holding promise for providing auxiliary pathology diagnostic methods based on multiphoton diagnostic criteria. In this review, we systematically outline the applications of MPM in pathological diagnosis across various human diseases, and summarize common multiphoton diagnostic features. Moreover, we examine the significant role of AI in enhancing multiphoton pathological diagnosis, including aspects such as image preprocessing, refined differential diagnosis, and the prognostication of outcomes. We also discuss the challenges and perspectives faced by the integration of MPM and AI, encompassing equipment, datasets, analytical models, and integration into the existing clinical pathways. Finally, the review explores the synergy between AI and label-free MPM to forge novel diagnostic frameworks, aiming to accelerate the adoption and implementation of intelligent multiphoton pathology systems in clinical settings. © The Author(s) 2024.
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Wang, S. , Pan, J. , Zhang, X. et al. Towards next-generation diagnostic pathology: AI-empowered label-free multiphoton microscopy [J]. | Light: Science and Applications , 2024 , 13 (1) . |
| MLA | Wang, S. et al. "Towards next-generation diagnostic pathology: AI-empowered label-free multiphoton microscopy" . | Light: Science and Applications 13 . 1 (2024) . |
| APA | Wang, S. , Pan, J. , Zhang, X. , Li, Y. , Liu, W. , Lin, R. et al. Towards next-generation diagnostic pathology: AI-empowered label-free multiphoton microscopy . | Light: Science and Applications , 2024 , 13 (1) . |
| Export to | NoteExpress RIS BibTex |
Version ：
Export
| Results： |
Selected to |
| Format： |
