中文
相关论文

相关论文: RegionCL: Can Simple Region Swapping Contribute to…

200 篇论文

Self-supervised learning has been widely used to obtain transferrable representations from unlabeled images. Especially, recent contrastive learning methods have shown impressive performances on downstream image classification tasks. While…

计算机视觉与模式识别 · 计算机科学 2021-04-29 Byungseok Roh , Wuhyun Shin , Ildoo Kim , Sungwoong Kim

Contrastive learning (CL) approaches have gained great recognition as a very successful subset of self-supervised learning (SSL) methods. SSL enables learning from unlabeled data, a crucial step in the advancement of deep learning,…

计算机视觉与模式识别 · 计算机科学 2025-04-29 Mohamed Hassan , Mohammad Wasil , Sebastian Houben

Contrastive learning (CL) methods effectively learn data representations in a self-supervision manner, where the encoder contrasts each positive sample over multiple negative samples via a one-vs-many softmax cross-entropy loss. By…

Detectingandsegmentingobjectswithinwholeslideimagesis essential in computational pathology workflow. Self-supervised learning (SSL) is appealing to such annotation-heavy tasks. Despite the extensive benchmarks in natural images for dense…

计算机视觉与模式识别 · 计算机科学 2022-07-15 Jiawei Yang , Hanbo Chen , Yuan Liang , Junzhou Huang , Lei He , Jianhua Yao

Contrastive self-supervised learning has outperformed supervised pretraining on many downstream tasks like segmentation and object detection. However, current methods are still primarily applied to curated datasets like ImageNet. In this…

计算机视觉与模式识别 · 计算机科学 2021-12-15 Wouter Van Gansbeke , Simon Vandenhende , Stamatios Georgoulis , Luc Van Gool

In Computer Vision, self-supervised contrastive learning enforces similar representations between different views of the same image. The pre-training is most often performed on image classification datasets, like ImageNet, where images…

计算机视觉与模式识别 · 计算机科学 2023-10-31 Benjamin Missaoui , Chongbin Yuan

Contrastive learning (CL) is a popular technique for self-supervised learning (SSL) of visual representations. It uses pairs of augmentations of unlabeled training examples to define a classification task for pretext learning of a deep…

计算机视觉与模式识别 · 计算机科学 2020-10-26 Chih-Hui Ho , Nuno Vasconcelos

Contrastive language-image pretraining (CLIP) using image-text pairs has achieved impressive results on image classification in both zero-shot and transfer learning settings. However, we show that directly applying such models to recognize…

计算机视觉与模式识别 · 计算机科学 2021-12-17 Yiwu Zhong , Jianwei Yang , Pengchuan Zhang , Chunyuan Li , Noel Codella , Liunian Harold Li , Luowei Zhou , Xiyang Dai , Lu Yuan , Yin Li , Jianfeng Gao

Contrastive Learning (CL) enhances the training of sequential recommendation (SR) models through informative self-supervision signals. Existing methods often rely on data augmentation strategies to create positive samples and promote…

信息检索 · 计算机科学 2026-04-06 Zhikai Wang , Yanyan Shen , Zexi Zhang , Li He , Yichun Li , Hao Gu , Yinghua Zhang

Contrastive self-supervised learning (SSL) learns an embedding space that maps similar data pairs closer and dissimilar data pairs farther apart. Despite its success, one issue has been overlooked: the fairness aspect of representations…

Contrastive Learning (CL), a leading paradigm in Self-Supervised Learning (SSL), typically relies on pairs of data views generated through augmentation. While multiple augmentations per instance (more than two) improve generalization in…

Contrastive learning (CL) aims to learn useful representation without relying on expert annotations in the context of medical image segmentation. Existing approaches mainly contrast a single positive vector (i.e., an augmentation of the…

计算机视觉与模式识别 · 计算机科学 2022-03-08 Chenyu You , Ruihan Zhao , Lawrence Staib , James S. Duncan

Deep models have been widely and successfully used in image manipulation detection, which aims to classify tampered images and localize tampered regions. Most existing methods mainly focus on extracting global features from tampered images,…

计算机视觉与模式识别 · 计算机科学 2023-02-23 Yuyuan Zeng , Bowen Zhao , Shanzhao Qiu , Tao Dai , Shu-Tao Xia

In this work, we present Multi-Level Contrastive Learning for Dense Prediction Task (MCL), an efficient self-supervised method for learning region-level feature representation for dense prediction tasks. Our method is motivated by the three…

计算机视觉与模式识别 · 计算机科学 2023-04-05 Qiushan Guo , Yizhou Yu , Yi Jiang , Jiannan Wu , Zehuan Yuan , Ping Luo

We tackle open-world semantic segmentation, which aims at learning to segment arbitrary visual concepts in images, by using only image-text pairs without dense annotations. Existing open-world segmentation methods have shown impressive…

计算机视觉与模式识别 · 计算机科学 2023-03-28 Junbum Cha , Jonghwan Mun , Byungseok Roh

Semi-supervised learning (SSL), which aims at leveraging a few labeled images and a large number of unlabeled images for network training, is beneficial for relieving the burden of data annotation in medical image segmentation. According to…

图像与视频处理 · 电气工程与系统科学 2022-02-15 Xinkai Zhao , Chaowei Fang , De-Jun Fan , Xutao Lin , Feng Gao , Guanbin Li

We present a self-supervised learning (SSL) method suitable for semi-global tasks such as object detection and semantic segmentation. We enforce local consistency between self-learned features, representing corresponding image locations of…

计算机视觉与模式识别 · 计算机科学 2022-12-09 Ashraful Islam , Ben Lundell , Harpreet Sawhney , Sudipta Sinha , Peter Morales , Richard J. Radke

We propose an augmentation policy for Contrastive Self-Supervised Learning (SSL) in the form of an already established Salient Image Segmentation technique entitled Global Contrast based Salient Region Detection. This detection technique,…

计算机视觉与模式识别 · 计算机科学 2022-11-01 Veysel Kocaman , Ofer M. Shir , Thomas Bäck , Ahmed Nabil Belbachir

Self-supervised learning (SSL) approaches have achieved great success when the amount of labeled data is limited. Within SSL, models learn robust feature representations by solving pretext tasks. One such pretext task is contrastive…

计算机视觉与模式识别 · 计算机科学 2024-02-28 Jamshid Hassanpour , Vinkle Srivastav , Didier Mutter , Nicolas Padoy

Medical image segmentation is a critical yet challenging task, primarily due to the difficulty of obtaining extensive datasets of high-quality, expert-annotated images. Contrastive learning presents a potential but still problematic…

计算机视觉与模式识别 · 计算机科学 2025-04-22 Shuang Zeng , Lei Zhu , Xinliang Zhang , Hangzhou He , Yanye Lu
‹ 上一页 1 2 3 10 下一页 ›