中文
相关论文

相关论文: Removing supervision in semantic segmentation with…

200 篇论文

Semantic segmentation has been continuously investigated in the last ten years, and majority of the established technologies are based on supervised models. In recent years, image-level weakly supervised semantic segmentation (WSSS),…

计算机视觉与模式识别 · 计算机科学 2021-08-04 Xiangrong Zhang , Zelin Peng , Peng Zhu , Tianyang Zhang , Chen Li , Huiyu Zhou , Licheng Jiao

Semantic segmentation is one of the most challenging tasks in computer vision. However, in many applications, a frequent obstacle is the lack of labeled images, due to the high cost of pixel-level labeling. In this scenario, it makes sense…

计算机视觉与模式识别 · 计算机科学 2023-02-21 Adrian Peláez-Vegas , Pablo Mesejo , Julián Luengo

Semantic image segmentation is a principal problem in computer vision, where the aim is to correctly classify each individual pixel of an image into a semantic label. Its widespread use in many areas, including medical imaging and…

计算机视觉与模式识别 · 计算机科学 2016-08-16 Vladimir Nekrasov , Janghoon Ju , Jaesik Choi

Semi-supervised semantic segmentation relieves the reliance on large-scale labeled data by leveraging unlabeled data. Recent semi-supervised semantic segmentation approaches mainly resort to pseudo-labeling methods to exploit unlabeled…

计算机视觉与模式识别 · 计算机科学 2024-04-11 Hui Xiao , Yuting Hong , Li Dong , Diqun Yan , Jiayan Zhuang , Junjie Xiong , Dongtai Liang , Chengbin Peng

We present ReCo, a contrastive learning framework designed at a regional level to assist learning in semantic segmentation. ReCo performs semi-supervised or supervised pixel-level contrastive learning on a sparse set of hard negative…

计算机视觉与模式识别 · 计算机科学 2022-02-01 Shikun Liu , Shuaifeng Zhi , Edward Johns , Andrew J. Davison

Most of the recent Deep Semantic Segmentation algorithms suffer from large generalization errors, even when powerful hierarchical representation models based on convolutional neural networks have been employed. This could be attributed to…

计算机视觉与模式识别 · 计算机科学 2019-10-01 Javed Iqbal , Mohsen Ali

Despite recent improvements using fully convolutional networks, in general, the segmentation produced by most state-of-the-art semantic segmentation methods does not show satisfactory adherence to the object boundaries. We propose a method…

计算机视觉与模式识别 · 计算机科学 2018-02-23 Philipe A. Dias , Henry Medeiros

Recently, semantic segmentation models trained with image-level text supervision have shown promising results in challenging open-world scenarios. However, these models still face difficulties in learning fine-grained semantic alignment at…

计算机视觉与模式识别 · 计算机科学 2024-03-14 Kaixin Cai , Pengzhen Ren , Yi Zhu , Hang Xu , Jianzhuang Liu , Changlin Li , Guangrun Wang , Xiaodan Liang

We consider the task of learning a classifier for semantic segmentation using weak supervision in the form of image labels which specify the object classes present in the image. Our method uses deep convolutional neural networks (CNNs) and…

计算机视觉与模式识别 · 计算机科学 2017-11-07 Qinbin Hou , Puneet Kumar Dokania , Daniela Massiceti , Yunchao Wei , Ming-Ming Cheng , Philip Torr

In fine-grained road scene understanding, semantic segmentation plays a crucial role in enabling vehicles to perceive and comprehend their surroundings. By assigning a specific class label to each pixel in an image, it allows for precise…

计算机视觉与模式识别 · 计算机科学 2026-01-27 Yuting Hong , Yongkang Wu , Hui Xiao , Huazheng Hao , Xiaojie Qiu , Baochen Yao , Chengbin Peng

Unsupervised semantic segmentation requires assigning a label to every pixel without any human annotations. Despite recent advances in self-supervised representation learning for individual images, unsupervised semantic segmentation with…

计算机视觉与模式识别 · 计算机科学 2022-07-27 Wenbin He , William Surmeier , Arvind Kumar Shekar , Liang Gou , Liu Ren

Unsupervised domain adaptation for point cloud semantic segmentation has attracted great attention due to its effectiveness in learning with unlabeled data. Most of existing methods use global-level feature alignment to transfer the…

计算机视觉与模式识别 · 计算机科学 2022-08-10 Yikai Bian , Le Hui , Jianjun Qian , Jin Xie

We propose a method for semi-supervised semantic segmentation using an adversarial network. While most existing discriminators are trained to classify input images as real or fake on the image level, we design a discriminator in a fully…

计算机视觉与模式识别 · 计算机科学 2018-07-26 Wei-Chih Hung , Yi-Hsuan Tsai , Yan-Ting Liou , Yen-Yu Lin , Ming-Hsuan Yang

Unsupervised image segmentation aims at grouping different semantic patterns in an image without the use of human annotation. Similarly, image clustering searches for groupings of images based on their semantic content without supervision.…

计算机视觉与模式识别 · 计算机科学 2024-01-18 Isaac Wasserman , Jeova Farias Sales Rocha Neto

Thanks to the impressive progress of large-scale vision-language pretraining, recent recognition models can classify arbitrary objects in a zero-shot and open-set manner, with a surprisingly high accuracy. However, translating this success…

计算机视觉与模式识别 · 计算机科学 2023-04-18 Xinyu Liu , Beiwen Tian , Zhen Wang , Rui Wang , Kehua Sheng , Bo Zhang , Hao Zhao , Guyue Zhou

Medical ultrasound imaging is ubiquitous, but manual analysis struggles to keep pace. Automated segmentation can help but requires large labeled datasets, which are scarce. Semi-supervised learning leveraging both unlabeled and limited…

图像与视频处理 · 电气工程与系统科学 2025-03-19 Yaxiong Chen , Yujie Wang , Zixuan Zheng , Jingliang Hu , Yilei Shi , Shengwu Xiong , Xiao Xiang Zhu , Lichao Mou

Unsupervised panoptic segmentation aims to partition an image into semantically meaningful regions and distinct object instances without training on manually annotated data. In contrast to prior work on unsupervised panoptic scene…

计算机视觉与模式识别 · 计算机科学 2025-11-12 Oliver Hahn , Christoph Reich , Nikita Araslanov , Daniel Cremers , Christian Rupprecht , Stefan Roth

This paper studies semi-supervised learning of semantic segmentation, which assumes that only a small portion of training images are labeled and the others remain unlabeled. The unlabeled images are usually assigned pseudo labels to be used…

计算机视觉与模式识别 · 计算机科学 2022-06-02 Donghyeon Kwon , Suha Kwak

This paper proposes a novel weakly-supervised semantic segmentation method using image-level label only. The class-specific activation maps from the well-trained classifiers are used as cues to train a segmentation network. The well-known…

计算机视觉与模式识别 · 计算机科学 2019-06-17 Ting Sun , Lei Tai , Zhihan Gao , Ming Liu , Dit-Yan Yeung

Reliable classification and detection of certain medical conditions, in images, with state-of-the-art semantic segmentation networks, require vast amounts of pixel-wise annotation. However, the public availability of such datasets is…

计算机视觉与模式识别 · 计算机科学 2023-03-17 Erik Ostrowski , Bharath Srinivas Prabakaran , Muhammad Shafique