中文
相关论文

相关论文: An Alternative to WSSS? An Empirical Study of the …

200 篇论文

Weakly supervised semantic segmentation (WSSS) aims to bypass the need for laborious pixel-level annotation by using only image-level annotation. Most existing methods rely on Class Activation Maps (CAM) to derive pixel-level pseudo-labels…

计算机视觉与模式识别 · 计算机科学 2023-11-07 Tianle Chen , Zheda Mai , Ruiwen Li , Wei-lun Chao

Semantic segmentation is a core computer vision problem, but the high costs of data annotation have hindered its wide application. Weakly-Supervised Semantic Segmentation (WSSS) offers a cost-efficient workaround to extensive labeling in…

计算机视觉与模式识别 · 计算机科学 2024-05-13 Elham Ravanbakhsh , Cheng Niu , Yongqing Liang , J. Ramanujam , Xin Li

Weakly supervised semantic segmentation (WSSS) trains dense pixel-level segmentation models from partial or coarse annotations such as bounding boxes, scribbles, or image-level tags. While recent work leverages foundation models such as the…

计算机视觉与模式识别 · 计算机科学 2026-05-14 Stefano Colamonaco , Andrei-Bogdan Florea , Jaron Maene

Weakly supervised visual recognition using inexact supervision is a critical yet challenging learning problem. It significantly reduces human labeling costs and traditionally relies on multi-instance learning and pseudo-labeling. This paper…

计算机视觉与模式识别 · 计算机科学 2024-08-20 Lianghui Zhu , Junwei Zhou , Yan Liu , Xin Hao , Wenyu Liu , Xinggang Wang

Weakly supervised semantic segmentation with weak labels is a long-lived ill-posed problem. Mainstream methods mainly focus on improving the quality of pseudo labels. In this report, we attempt to explore the potential of 'prompt to masks'…

计算机视觉与模式识别 · 计算机科学 2023-05-03 Peng-Tao Jiang , Yuqi Yang

Semantic segmentation requires dense pixel-level annotations, which are costly and time-consuming to acquire. To address this, we present SeSAM, a framework that uses a foundational segmentation model, i.e. Segment Anything Model (SAM),…

计算机视觉与模式识别 · 计算机科学 2026-04-14 Anurag Das , Anna Kukleva , Xinting Hu , Yuki M. Asano , Bernt Schiele

This work proposes a novel approach beyond supervised learning for effective pathological image analysis, addressing the challenge of limited robust labeled data. Pathological diagnosis of diseases like cancer has conventionally relied on…

计算机视觉与模式识别 · 计算机科学 2024-10-23 Joonhyeon Song , Seohwan Yun , Seongho Yoon , Joohyeok Kim , Sangmin Lee

The rapid development of deep learning has driven significant progress in image semantic segmentation - a fundamental task in computer vision. Semantic segmentation algorithms often depend on the availability of pixel-level labels (i.e.,…

计算机视觉与模式识别 · 计算机科学 2024-12-03 Zhaozheng Chen , Qianru Sun

This work aims to leverage pre-trained foundation models, such as contrastive language-image pre-training (CLIP) and segment anything model (SAM), to address weakly supervised semantic segmentation (WSSS) using image-level labels. To this…

计算机视觉与模式识别 · 计算机科学 2023-12-12 Xiaobo Yang , Xiaojin Gong

Image-level weakly-supervised semantic segmentation (WSSS) reduces the usually vast data annotation cost by surrogate segmentation masks during training. The typical approach involves training an image classification network using global…

计算机视觉与模式识别 · 计算机科学 2024-06-10 Arvi Jonnarth , Yushan Zhang , Michael Felsberg

The Segment Anything Model (SAM) is a foundational model for image segmentation tasks, known for its strong generalization across diverse applications. However, its impressive performance comes with significant computational and resource…

计算机视觉与模式识别 · 计算机科学 2026-04-15 Xiaorui Sun , Jun Liu , Heng Tao Shen , Xiaofeng Zhu , Ping Hu

Segmenting and recognizing diverse object parts is crucial in computer vision and robotics. Despite significant progress in object segmentation, part-level segmentation remains underexplored due to complex boundaries and scarce annotated…

计算机视觉与模式识别 · 计算机科学 2024-07-16 Xinjian Wu , Ruisong Zhang , Jie Qin , Shijie Ma , Cheng-Lin Liu

Semi-supervised instance segmentation poses challenges due to limited labeled data, causing difficulties in accurately localizing distinct object instances. Current teacher-student frameworks still suffer from performance constraints due to…

计算机视觉与模式识别 · 计算机科学 2025-04-08 Heeji Yoon , Heeseong Shin , Eunbeen Hong , Hyunwook Choi , Hansang Cho , Daun Jeong , Seungryong Kim

Weakly Supervised Semantic Segmentation (WSSS) is a challenging task aiming to learn the segmentation labels from class-level labels. In the literature, exploiting the information obtained from Class Activation Maps (CAMs) is widely used…

计算机视觉与模式识别 · 计算机科学 2022-11-24 Cenk Bircanoglu , Nafiz Arica

We propose a method to efficiently equip the Segment Anything Model (SAM) with the ability to generate regional captions. SAM presents strong generalizability to segment anything while is short for semantic understanding. By introducing a…

计算机视觉与模式识别 · 计算机科学 2024-03-27 Xiaoke Huang , Jianfeng Wang , Yansong Tang , Zheng Zhang , Han Hu , Jiwen Lu , Lijuan Wang , Zicheng Liu

Weakly supervised semantic segmentation (WSSS) aims to produce pixel-wise class predictions with only image-level labels for training. To this end, previous methods adopt the common pipeline: they generate pseudo masks from class activation…

计算机视觉与模式识别 · 计算机科学 2022-08-09 Sungpil Kho , Pilhyeon Lee , Wonyoung Lee , Minsong Ki , Hyeran Byun

Most weakly supervised semantic segmentation (WSSS) methods follow the pipeline that generates pseudo-masks initially and trains the segmentation model with the pseudo-masks in fully supervised manner after. However, we find some matters…

计算机视觉与模式识别 · 计算机科学 2021-09-08 Yi Li , Zhanghui Kuang , Liyang Liu , Yimin Chen , Wayne Zhang

Weakly-supervised semantic segmentation (WSSS) performs pixel-wise classification given only image-level labels for training. Despite the difficulty of this task, the research community has achieved promising results over the last five…

计算机视觉与模式识别 · 计算机科学 2023-09-26 Cheolhyun Mun , Sanghuk Lee , Youngjung Uh , Junsuk Choe , Hyeran Byun

Weakly-Supervised Concealed Object Segmentation (WSCOS) aims to segment objects well blended with surrounding environments using sparsely-annotated data for model training. It remains a challenging task since (1) it is hard to distinguish…

计算机视觉与模式识别 · 计算机科学 2023-05-19 Chunming He , Kai Li , Yachao Zhang , Guoxia Xu , Longxiang Tang , Yulun Zhang , Zhenhua Guo , Xiu Li

Weakly-supervised semantic segmentation (WSSS) is introduced to narrow the gap for semantic segmentation performance from pixel-level supervision to image-level supervision. Most advanced approaches are based on class activation maps (CAMs)…

计算机视觉与模式识别 · 计算机科学 2021-09-24 Sanghyun Jo , In-Jae Yu
‹ 上一页 1 2 3 10 下一页 ›