English
Related papers

Related papers: Unlocking Constraints: Source-Free Occlusion-Aware…

200 papers

The Segmentation Anything Model (SAM) requires labor-intensive data labeling. We present Unsupervised SAM (UnSAM) for promptable and automatic whole-image segmentation that does not require human annotations. UnSAM utilizes a…

Computer Vision and Pattern Recognition · Computer Science 2024-07-01 XuDong Wang , Jingfeng Yang , Trevor Darrell

To help address the occlusion problem in panoptic segmentation and image understanding, this paper proposes a new large-scale dataset named COCO-OLAC (COCO Occlusion Labels for All Computer Vision Tasks), which is derived from the COCO…

Computer Vision and Pattern Recognition · Computer Science 2025-01-14 Wenbo Wei , Jun Wang , Abhir Bhalerao

Domain adaptation tackles the challenge of generalizing knowledge acquired from a source domain to a target domain with different data distributions. Traditional domain adaptation methods presume that the classes in the source and target…

Computer Vision and Pattern Recognition · Computer Science 2023-03-22 Xinghong Liu , Yi Zhou , Tao Zhou , Jie Qin , Shengcai Liao

In this work, we introduce panoramic panoptic segmentation as the most holistic scene understanding both in terms of field of view and image level understanding for standard camera based input. A complete surrounding understanding provides…

Computer Vision and Pattern Recognition · Computer Science 2021-05-31 Alexander Jaus , Kailun Yang , Rainer Stiefelhagen

Deep learning-based segmentation methods have been widely employed for automatic glaucoma diagnosis and prognosis. In practice, fundus images obtained by different fundus cameras vary significantly in terms of illumination and intensity.…

Computer Vision and Pattern Recognition · Computer Science 2022-10-11 Qianbi Yu , Dongnan Liu , Chaoyi Zhang , Xinwen Zhang , Weidong Cai

Source-free object detection adapts a detector pre-trained on a source domain to an unlabeled target domain without requiring access to labeled source data. While this setting is practical as it eliminates the need for the source dataset…

Computer Vision and Pattern Recognition · Computer Science 2025-07-24 Keon-Hee Park , Seun-An Choe , Gyeong-Moon Park

Panoptic segmentation methods assign a known class to each pixel given in input. Even for state-of-the-art approaches, this inevitably enforces decisions that systematically lead to wrong predictions for objects outside the training…

Computer Vision and Pattern Recognition · Computer Science 2024-01-23 Stefano Gasperini , Alvaro Marcos-Ramiro , Michael Schmidt , Nassir Navab , Benjamin Busam , Federico Tombari

Recent advances in object-centric representation learning have shown that slot attention-based methods can effectively decompose visual scenes into object slot representations without supervision. However, existing approaches typically…

Computer Vision and Pattern Recognition · Computer Science 2025-12-11 Huankun Sheng , Ming Li , Yixiang Wei , Yeying Fan , Yu-Hui Wen , Tieliang Gong , Yong-Jin Liu

Camouflaged object segmentation presents unique challenges compared to traditional segmentation tasks, primarily due to the high similarity in patterns and colors between camouflaged objects and their backgrounds. Effective solutions to…

Computer Vision and Pattern Recognition · Computer Science 2025-07-22 Wenqi Guo , Mohamed Shehata , Shan Du

Unseen Object Instance Segmentation (UOIS) is crucial for autonomous robots operating in unstructured environments. Previous approaches require full supervision on large-scale tabletop datasets for effective pretraining. In this paper, we…

Robotics · Computer Science 2024-09-25 Rui Cao , Chuanxin Song , Biqi Yang , Jiangliu Wang , Pheng-Ann Heng , Yun-Hui Liu

Vision-language models (VLMs) have gained widespread attention for their strong zero-shot capabilities across numerous downstream tasks. However, these models assume that each test image's class label is drawn from a predefined label set…

Computer Vision and Pattern Recognition · Computer Science 2026-01-30 Yongguang Li , Jindong Li , Qi Wang , Qianli Xing , Runliang Niu , Shengsheng Wang , Menglin Yang

Semantic segmentation is fundamental to vision systems requiring pixel-level scene understanding, yet deploying it on resource-constrained devices demands efficient architectures. Although existing methods achieve real-time inference…

Computer Vision and Pattern Recognition · Computer Science 2025-08-13 Shi-Chen Zhang , Yunheng Li , Yu-Huan Wu , Qibin Hou , Ming-Ming Cheng

In open-world semi-supervised learning, a machine learning model is tasked with uncovering novel categories from unlabeled data while maintaining performance on seen categories from labeled data. The central challenge is the substantial…

Machine Learning · Computer Science 2024-04-18 Bo Ye , Kai Gan , Tong Wei , Min-Ling Zhang

The Segment Anything Model (SAM) family has become a widely adopted vision foundation model, but its ability to control segmentation granularity remains limited. Users often need to refine results manually - by adding more prompts or…

Computer Vision and Pattern Recognition · Computer Science 2025-11-18 Junwei Yu , Trevor Darrell , XuDong Wang

Semi-supervised semantic segmentation learns a model for classifying pixels into specific classes using a few labeled samples and numerous unlabeled images. The recent leading approach is consistency regularization by selftraining with…

Computer Vision and Pattern Recognition · Computer Science 2023-03-22 Jingi Ju , Hyeoncheol Noh , Yooseung Wang , Minseok Seo , Dong-Geol Choi

Semantically interpreting the traffic scene is crucial for autonomous transportation and robotics systems. However, state-of-the-art semantic segmentation pipelines are dominantly designed to work with pinhole cameras and train with narrow…

Computer Vision and Pattern Recognition · Computer Science 2020-02-10 Kailun Yang , Xinxin Hu , Hao Chen , Kaite Xiang , Kaiwei Wang , Rainer Stiefelhagen

Incompletely-Supervised Concealed Object Segmentation (ISCOS) involves segmenting objects that seamlessly blend into their surrounding environments, utilizing incompletely annotated data, such as weak and semi-annotations, for model…

Computer Vision and Pattern Recognition · Computer Science 2025-06-17 Chunming He , Kai Li , Yachao Zhang , Ziyun Yang , Youwei Pang , Longxiang Tang , Chengyu Fang , Yulun Zhang , Linghe Kong , Xiu Li , Sina Farsiu

In this paper, we address panoramic semantic segmentation which is under-explored due to two critical challenges: (1) image distortions and object deformations on panoramas; (2) lack of semantic annotations in the 360{\deg} imagery. To…

Computer Vision and Pattern Recognition · Computer Science 2024-06-03 Jiaming Zhang , Kailun Yang , Hao Shi , Simon Reiß , Kunyu Peng , Chaoxiang Ma , Haodong Fu , Philip H. S. Torr , Kaiwei Wang , Rainer Stiefelhagen

Amodal segmentation is a challenging task that aims to predict the complete geometric shape of objects, including their occluded regions. Although existing methods primarily focus on amodal segmentation within the training domain, these…

Computer Vision and Pattern Recognition · Computer Science 2026-04-23 Bo Zhang , Zhuotao Tian , Xin Tao , Songlin Tang , Jun Yu , Wenjie Pei

This paper focuses on source-free domain adaptation for object detection in computer vision. This task is challenging and of great practical interest, due to the cost of obtaining annotated data sets for every new domain. Recent research…

Computer Vision and Pattern Recognition · Computer Science 2024-07-11 Yan Hao , Florent Forest , Olga Fink