中文
相关论文

相关论文: Exploring Negatives in Contrastive Learning for Un…

200 篇论文

In image-to-image translation, each patch in the output should reflect the content of the corresponding patch in the input, independent of domain. We propose a straightforward method for doing so -- maximizing mutual information between the…

计算机视觉与模式识别 · 计算机科学 2020-08-21 Taesung Park , Alexei A. Efros , Richard Zhang , Jun-Yan Zhu

Image-to-image translation models transfer images from input domain to output domain in an endeavor to retain the original content of the image. Contrastive Unpaired Translation is one of the existing methods for solving such problems.…

计算机视觉与模式识别 · 计算机科学 2021-09-28 Bernard Spiegl

Unsupervised image-to-image translation tasks aim to find a mapping between a source domain X and a target domain Y from unpaired training data. Contrastive learning for Unpaired image-to-image Translation (CUT) yields state-of-the-art…

计算机视觉与模式识别 · 计算机科学 2021-04-19 Junlin Han , Mehrdad Shoeiby , Lars Petersson , Mohammad Ali Armin

As one of the most effective self-supervised representation learning methods, contrastive learning (CL) relies on multiple negative pairs to contrast against each positive pair. In the standard practice of contrastive learning, data…

机器学习 · 计算机科学 2024-01-18 Lu Wang , Chao Du , Pu Zhao , Chuan Luo , Zhangchi Zhu , Bo Qiao , Wei Zhang , Qingwei Lin , Saravan Rajmohan , Dongmei Zhang , Qi Zhang

Unsupervised learning has recently made exceptional progress because of the development of more effective contrastive learning methods. However, CNNs are prone to depend on low-level features that humans deem non-semantic. This dependency…

计算机视觉与模式识别 · 计算机科学 2022-01-04 Songwei Ge , Shlok Mishra , Haohan Wang , Chun-Liang Li , David Jacobs

While the wisdom of training an image dehazing model on synthetic hazy data can alleviate the difficulty of collecting real-world hazy/clean image pairs, it brings the well-known domain shift problem. From a different yet new perspective,…

计算机视觉与模式识别 · 计算机科学 2022-05-05 Yongzhen Wang , Xuefeng Yan , Fu Lee Wang , Haoran Xie , Wenhan Yang , Mingqiang Wei , Jing Qin

Image-to-image translation aims to learn a mapping between different groups of visually distinguishable images. While recent methods have shown impressive ability to change even intricate appearance of images, they still rely on domain…

计算机视觉与模式识别 · 计算机科学 2021-05-10 Hanbit Lee , Jinseok Seol , Sang-goo Lee

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…

Visual contrastive learning aims to learn representations by contrasting similar (positive) and dissimilar (negative) pairs of data samples. The design of these pairs significantly impacts representation quality, training efficiency, and…

计算机视觉与模式识别 · 计算机科学 2025-02-13 Shasvat Desai , Debasmita Ghose , Deep Chakraborty

Recently, contrastive learning-based image translation methods have been proposed, which contrasts different spatial locations to enhance the spatial correspondence. However, the methods often ignore the diverse semantic relation within the…

计算机视觉与模式识别 · 计算机科学 2022-03-04 Chanyong Jung , Gihyun Kwon , Jong Chul Ye

Contrastive learning, which aims at minimizing the distance between positive pairs while maximizing that of negative ones, has been widely and successfully applied in unsupervised feature learning, where the design of positive and negative…

计算机视觉与模式识别 · 计算机科学 2021-08-09 Rui Zhu , Bingchen Zhao , Jingen Liu , Zhenglong Sun , Chang Wen Chen

Unpaired image-to-image translation involves learning mappings between source domain and target domain in the absence of aligned or corresponding samples. Score based diffusion models have demonstrated state-of-the-art performance in…

计算机视觉与模式识别 · 计算机科学 2025-10-07 Venkata Narendra Kotyada , Revanth Eranki , Nagesh Bhattu Sristy

Self-supervised representation learning has made significant leaps fueled by progress in contrastive learning, which seeks to learn transformations that embed positive input pairs nearby, while pushing negative pairs far apart. While…

计算机视觉与模式识别 · 计算机科学 2022-01-04 Tri Huynh , Simon Kornblith , Matthew R. Walter , Michael Maire , Maryam Khademi

Ensuring the realism of computer-generated synthetic images is crucial to deep neural network (DNN) training. Due to different semantic distributions between synthetic and real-world captured datasets, there exists semantic mismatch between…

计算机视觉与模式识别 · 计算机科学 2023-04-27 Ganning Zhao , Tingwei Shen , Suya You , C. -C. Jay Kuo

Recently, patch-wise contrastive learning is drawing attention for the image translation by exploring the semantic correspondence between the input and output images. To further explore the patch-wise topology for high-level semantic…

计算机视觉与模式识别 · 计算机科学 2024-02-21 Chanyong Jung , Gihyun Kwon , Jong Chul Ye

Image captioning, a popular topic in computer vision, has achieved substantial progress in recent years. However, the distinctiveness of natural descriptions is often overlooked in previous work. It is closely related to the quality of…

计算机视觉与模式识别 · 计算机科学 2017-10-10 Bo Dai , Dahua Lin

Contrastive pretraining can substantially increase model generalisation and downstream performance. However, the quality of the learned representations is highly dependent on the data augmentation strategy applied to generate positive…

计算机视觉与模式识别 · 计算机科学 2025-06-17 Mélanie Roschewitz , Fabio De Sousa Ribeiro , Tian Xia , Galvin Khara , Ben Glocker

Recently, unsupervised image-to-image translation methods based on contrastive learning have achieved state-of-the-art results in many tasks. However, in the previous works, the negatives are sampled from the input image itself, which…

计算机视觉与模式识别 · 计算机科学 2023-07-06 Chen Zhao , Wei-Ling Cai , Zheng Yuan , Cheng-Wei Hu

Learning discriminative image representations plays a vital role in long-tailed image classification because it can ease the classifier learning in imbalanced cases. Given the promising performance contrastive learning has shown recently in…

计算机视觉与模式识别 · 计算机科学 2021-03-29 Peng Wang , Kai Han , Xiu-Shen Wei , Lei Zhang , Lei Wang

Self-supervised learning is a machine learning approach that generates implicit labels by learning underlined patterns and extracting discriminative features from unlabeled data without manual labelling. Contrastive learning introduces the…

计算机视觉与模式识别 · 计算机科学 2025-10-13 Asifullah Khan , Laiba Asmatullah , Anza Malik , Shahzaib Khan , Hamna Asif
‹ 上一页 1 2 3 10 下一页 ›