Leveraging semantically precise pseudo masks derived from image-level class knowledge for segmentation, namely image-level Weakly Supervised Semantic Segmentation (WSSS), still remains challenging. While Class Activation Maps (CAMs) using CNNs have steadily been contributing to the success of WSSS, the resulting activation maps often narrowly focus on class-specific parts (e.g., only face of human). On the other hand, recent works based on vision transformers (ViT) have shown promising results based on their self-attention mechanism to capture the semantic parts but fail in capturing complete class-specific details (e.g., entire body parts of human but also with a dog nearby). In this work, we propose Complementary Branch (CoBra), a novel dual branch framework consisting of two distinct architectures which provide valuable complementary knowledge of class (from CNN) and semantic (from ViT) to each branch. In particular, we learn Class-Aware Projection (CAP) for the CNN branch and Semantic-Aware Projection (SAP) for the ViT branch to explicitly fuse their complementary knowledge and facilitate a new type of extra patch-level supervision. Our model, through CoBra, fuses CNN and ViT's complementary outputs to create robust pseudo masks that integrate both class and semantic information effectively. Extensive experiments qualitatively and quantitatively investigate how CNN and ViT complement each other on the PASCAL VOC 2012 dataset, showing a state-of-the-art WSSS result. This includes not only the masks generated by our model, but also the segmentation results derived from utilizing these masks as pseudo labels.
State Key Laboratory for Novel Software Technology, Nanjing University（南京大学计算机软件新技术国家重点实验室）；Southeast University（东南大学）；Nanjing University（南京大学）；University of Sydney（悉尼大学）；University of Wollongong（伍伦贡大学）；Shandong University（山东大学）；Shandong Chest Hospital（山东省胸科医院）
Accurate image segmentation plays a crucial role in medical image analysis, yet it faces great challenges of various shapes, diverse sizes, and blurry boundaries. To address these difficulties, square kernel-based encoder-decoder architecture has been proposed and widely used, but its performance remains still unsatisfactory. To further cope with these challenges, we present a novel double-branch encoder architecture. Our architecture is inspired by two observations: 1) Since the discrimination of features learned via square convolutional kernels needs to be further improved, we propose to uti…
Medical image segmentation - the prerequisite of numerous clinical needs - has been significantly prospered by recent advances in convolutional neural networks (CNNs). However, it exhibits general limitations on modeling explicit long-range relation, and existing cures, resorting to building deep encoders along with aggressive downsampling operations, leads to redundant deepened networks and loss of localized details. Hence, the segmentation task awaits a better solution to improve the efficiency of modeling global contexts while maintaining a strong grasp of low-level details. In this paper, …
Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University（西安交通大学人工智能与机器人研究所）；the Second Academy of CASIC（中国航天科工集团第二研究院）
Point clouds and images could provide complementary information when representing 3D objects. Fusing the two kinds of data usually helps to improve the detection results. However, it is challenging to fuse the two data modalities, due to their different characteristics and the interference from the non-interest areas. To solve this problem, we propose a Multi-Branch Deep Fusion Network (MBDF-Net) for 3D object detection. The proposed detector has two stages. In the first stage, our multi-branch feature extraction network utilizes Adaptive Attention Fusion (AAF) modules to produce cross-modal f…
The University of Hong Kong（香港大学）；Advanced Biomedical Instrumentation Centre（先进生物医学仪器中心）
In recent years, self-supervised monocular depth estimation has drawn much attention since it frees of depth annotations and achieved remarkable results on standard benchmarks. However, most of existing methods only focus on either daytime or nighttime images, thus their performance degrades on the other domain because of the large domain shift between daytime and nighttime images. To address this problem, in this paper we propose a two-branch network named GlocalFuse-Depth for self-supervised depth estimation of all-day images. The daytime and nighttime image in input image pair are fed into …
Salient Object Detection is the task of predicting the human attended region in a given scene. Fusing depth information has been proven effective in this task. The main challenge of this problem is how to aggregate the complementary information from RGB modality and depth modality. However, conventional deep models heavily rely on CNN feature extractors, and the long-range contextual dependencies are usually ignored. In this work, we propose Dual Swin-Transformer based Mutual Interactive Network. We adopt Swin-Transformer as the feature extractor for both RGB and depth modality to model the lo…
Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）
Weakly supervised object detection (WSOD) focuses on training object detector with only image-level annotations, and is challenging due to the gap between the supervision and the objective. Most of existing approaches model WSOD as a multiple instance learning (MIL) problem. However, we observe that the result of MIL based detector is unstable, i.e., the most confident bounding boxes change significantly when using different initializations. We quantitatively demonstrate the instability by introducing a metric to measure it, and empirically analyze the reason of instability. Although the insta…
SenseTime Group Limited（商汤科技集团有限公司）；The Chinese University of HongKong（香港中文大学）
Although person re-identification (ReID) has achieved significant improvement recently by enforcing part alignment, it is still a challenging task when it comes to distinguishing visually similar identities or identifying the occluded person. In these scenarios, magnifying details in each part features and selectively fusing them together may provide a feasible solution. In this work, we propose MagnifierNet, a triple-branch network which accurately mines details from whole to parts. Firstly, the holistic salient features are encoded by a global branch. Secondly, to enhance detailed representa…
DQFormer: Towards Unified LiDAR Panoptic Segmentation with Decoupled Queries
Institute of Cyber-Systems and Control, Zhejiang University（浙江大学控制科学与工程学院 Cyber-Systems 研究所）；Huawei Technologies Co., Ltd.（华为技术有限公司）；Institute of Industrial Technology Research, Zhejiang University（浙江大学工业技术研究院）；Institute of Intelligent and Software Technology, Hangzhou Dianzi University（杭州电子科技大学智能与软件技术研究所）
We introduce a simple yet effective fusion method of LiDAR and RGB data to segment LiDAR point clouds. Utilizing the dense native range representation of a LiDAR sensor and the setup calibration, we establish point correspondences between the two input modalities. Subsequently, we are able to warp and fuse the features from one domain into the other. Therefore, we can jointly exploit information from both data sources within one single network. To show the merit of our method, we extend SqueezeSeg, a point cloud segmentation network, with an RGB feature branch and fuse it into the original str…
Multispectral State-Space Feature Fusion: Bridging Shared and Cross-Parametric Interactions for Object Detection
School of Electrical and Information Engineering, Jiangsu University, Zhenjiang, 212013, China（江苏大学电气与信息工程学院）；Department of Computer Science and Engineering, University of North Texas, Denton, TX 76207, USA（德克萨斯大学北卡罗来纳分校计算机科学与工程系）；School of Computer Science and Engineering, Jiangsu University of Science and Technology, Zhenjiang, 212003, China（江苏科技大学计算机科学与工程学院）；School of Automation, Southeast University, Nanjing, 210096, China（东南大学自动化学院）；Bodhi Intelligence Lab, Department of Artificial Intelligence, Westlake University, Hangzhou, Zhejiang 310030, China（西湖大学人工智能研究院）
In actual industrial production, the assessment of the steel plate welding effect is an important task, and the segmentation of the weld section is the basis of the assessment. This paper proposes an industrial weld segmentation network based on a deep learning semantic segmentation algorithm fused with heatmap detail guidance and Image Matting to solve the automatic segmentation problem of weld regions. In the existing semantic segmentation networks, the boundary information can be preserved by fusing the features of both high-level and low-level layers. However, this method can lead to insuf…
Shandong University（山东大学）；Institute of Tsinghua-Berkeley Shenzhen, Tsinghua Shenzhen International Graduate School（清华大学深圳国际研究生院清华-伯克利深圳学院）；Hangzhou Dianzi University（杭州电子科技大学）；Shenzhen ZNV Technology Co., Ltd（深圳中兴网信科技有限公司）；Shenzhen Graduate School of Harbin Institute of Technology（哈尔滨工业大学深圳研究生院）；Institute of Biopharmaceutical and Health Engineering, Tsinghua Shenzhen International Graduate School（清华大学深圳国际研究生院生物医药与健康工程研究院）
Deep learning techniques have shown great potential in medical image processing, particularly through accurate and reliable image segmentation on magnetic resonance imaging (MRI) scans or computed tomography (CT) scans, which allow the localization and diagnosis of lesions. However, training these segmentation models requires a large number of manually annotated pixel-level labels, which are time-consuming and labor-intensive, in contrast to image-level labels that are easier to obtain. It is imperative to resolve this problem through weakly-supervised semantic segmentation models using image-…
Towards Semi-supervised Dual-modal Semantic Segmentation
School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；Center for Excellence in Brain Science and Intelligence Technology, Chinese Academy of Sciences（中国科学院脑科学与智能技术卓越创新中心）；JD logistics（京东物流）
State Key Laboratory of Electromechanical Integrated Manufacturing of High-Performance Electronic Equipments（高性能电子设备机电一体化制造国家重点实验室）；Center for Complex Systems（复杂系统中心）；School of Mechano-Electronic Engineering（机械电子工程学院）；Xidian University（西安电子科技大学）
ContrastAlign: Toward Robust BEV Feature Alignment via Contrastive Learning for Multi-Modal 3D Object Detection
School of Computer Science & Technology, Beijing Key Laboratory of Traffic Data Mining and Embodied Intelligence, Beijing Jiaotong University（计算机科学与技术学院，北京交通大数据挖掘与具身智能重点实验室，北京交通大学）；Horizon Robotics；Nanyang Technological University（南洋理工大学）；University of Macau（澳门大学）；School of Information Science and Engineering, Yanshan University（信息科学与工程学院，燕山大学）；School of Computer Science and Technology, Harbin Institute of Technology（计算机科学与技术学院，哈尔滨理工大学）；School of Information Technology and Electrical Engineering, The University of Queensland（信息技术与电气工程学院，昆士兰大学）
TABNet: A Triplet Augmentation Self-Recovery Framework with Boundary-Aware Pseudo-Labels for Medical Image Segmentation
School of Information Science and Technology, Northwest University（信息科学与技术学院，西北大学）；Institute of Biomedical Engineering, Department of Engineering Science, University of Oxford（生物医学工程研究所，工程科学系，牛津大学）
Domain shift has always been one of the primary issues in video object segmentation (VOS), for which models suffer from degeneration when tested on unfamiliar datasets. Recently, many online methods have emerged to narrow the performance gap between training data (source domain) and test data (target domain) by fine-tuning on annotations of test data which are usually in shortage. In this paper, we propose a novel method to tackle domain shift by first introducing adversarial domain adaptation to the VOS task, with supervised training on the source domain and unsupervised training on the targe…
MV-MOS: Multi-View Feature Fusion for 3D Moving Object Segmentation
Research Institute of Trustworthy Autonomous Systems（可信自主系统研究院）；Southern University of Science and Technology（南方科技大学）；School of Electronic and Information Engineering, South China Normal University（华南师范大学电子与信息工程学院）；College of Intelligence Science and Technology, National University of Defense Technology（国防科技大学智能科学学院）
The encoding of the target in object tracking moves from the coarse bounding-box to fine-grained segmentation map recently. Revisiting de facto real-time approaches that are capable of predicting mask during tracking, we observed that they usually fork a light branch from the backbone network for segmentation. Although efficient, directly fusing backbone features without considering the negative influence of background clutter tends to introduce false-negative predictions, lagging the segmentation accuracy. To mitigate this problem, we propose an attention retrieval network (ARN) to perform so…
Deep learning has thrived by training on large-scale datasets. However, in robotics applications sample efficiency is critical. We propose a novel adaptive masked proxies method that constructs the final segmentation layer weights from few labelled samples. It utilizes multi-resolution average pooling on base embeddings masked with the label to act as a positive proxy for the new class, while fusing it with the previously learned class signatures. Our method is evaluated on PASCAL-$5^i$ dataset and outperforms the state-of-the-art in the few-shot semantic segmentation. Unlike previous methods,…
Rethinking Attention Gated with Hybrid Dual Pyramid Transformer-CNN for Generalized Segmentation in Medical Imaging
Junia（朱尼亚学院）；Centrale Lille（里尔中央理工学院）；University of the Basque Country UPV/EHU（巴斯克大学 UPV/EHU）；Université Polytechnique Hauts-de-France（上法兰西理工大学）；Université de Lille（里尔大学）；Ho Chi Minh City Open University（胡志明市开放大学）
DAGLFNet: Deep Feature Attention Guided Global and Local Feature Fusion for Pseudo-Image Point Cloud Segmentation
College of Computer Science, Chengdu University of Information Technology（成都信息科技大学计算机学院）；College of Computer Science, Sichuan University（四川大学计算机学院）；Publications Department, Optica Publishing Group（Optica出版社出版部）；Department of Electronic Journals, Optica Publishing Group（Optica出版社电子期刊部）
Bridging Knowledge Gap Between Image Inpainting and Large-Area Visible Watermark Removal
School of Artificial Intelligence, Xidian University（西安电子科技大学人工智能学院）；School of Data Science, The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳）数据科学学院）；Research Institute of Sun Yat-sen University in Shenzhen（中山大学深圳研究院）；Afirstsoft
