Results 1 to 10 of about 15,854,673 (328)
Parametric Contrastive Learning [PDF]
2021 IEEE/CVF International Conference on Computer Vision (ICCV), 2021 In this paper, we propose Parametric Contrastive Learning (PaCo) to tackle long-tailed recognition. Based on theoretical analysis, we observe supervised contrastive loss tends to bias on high-frequency classes and thus increases the difficulty of ...
Jiequan Cui +4 more
semanticscholar +5 more sources
Contrastive Representation Learning: A Framework and Review
IEEE Access, 2020 Contrastive Learning has recently received interest due to its success in self-supervised representation learning in the computer vision domain. However, the origins of Contrastive Learning date as far back as the 1990s and its development has spanned ...
Phuc H. Le-Khac +2 more
doaj +3 more sources
Contrastive Learning with Stronger Augmentations
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022 12 pages, 6 ...
Guo-Jun Qi, Xiao Wang
exaly +6 more sources
SimCSE: Simple Contrastive Learning of Sentence Embeddings [PDF]
Conference on Empirical Methods in Natural Language Processing, 2021 This paper presents SimCSE, a simple contrastive learning framework that greatly advances the state-of-the-art sentence embeddings. We first describe an unsupervised approach, which takes an input sentence and predicts itself in a contrastive objective ...
Tianyu Gao, Xingcheng Yao, Danqi Chen
semanticscholar +1 more source
MedCLIP: Contrastive Learning from Unpaired Medical Images and Text [PDF]
Conference on Empirical Methods in Natural Language Processing, 2022 Existing vision-text contrastive learning like CLIP aims to match the paired image and caption embeddings while pushing others apart, which improves representation transferability and supports zero-shot prediction.
Zifeng Wang +3 more
semanticscholar +1 more source
Are Graph Augmentations Necessary?: Simple Graph Contrastive Learning for Recommendation [PDF]
Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, 2021 Contrastive learning (CL) recently has spurred a fruitful line of research in the field of recommendation, since its ability to extract self-supervised signals from the raw data is well-aligned with recommender systems' needs for tackling the data ...
Junliang Yu +5 more
semanticscholar +1 more source
Improving Graph Collaborative Filtering with Neighborhood-enriched Contrastive Learning [PDF]
The Web Conference, 2022 Recently, graph collaborative filtering methods have been proposed as an effective recommendation approach, which can capture users’ preference over items by modeling the user-item interaction graphs.
Zihan Lin +3 more
semanticscholar +1 more source
Contrastive Learning for Compact Single Image Dehazing [PDF]
Computer Vision and Pattern Recognition, 2021 Single image dehazing is a challenging ill-posed problem due to the severe information degeneration. However, existing deep learning based dehazing methods only adopt clear images as positive samples to guide the training of dehazing network while ...
Haiyan Wu +7 more
semanticscholar +1 more source
Contrastive Learning for Representation Degeneration Problem in Sequential Recommendation [PDF]
Web Search and Data Mining, 2021 Recent advancements of sequential deep learning models such as Transformer and BERT have significantly facilitated the sequential recommendation. However, according to our study, the distribution of item embeddings generated by these models tends to ...
Ruihong Qiu +3 more
semanticscholar +1 more source
Graph Contrastive Learning with Adaptive Augmentation [PDF]
The Web Conference, 2020 Recently, contrastive learning (CL) has emerged as a successful method for unsupervised graph representation learning. Most graph CL methods first perform stochastic augmentation on the input graph to obtain two graph views and maximize the agreement of ...
Yanqiao Zhu +5 more
semanticscholar +1 more source