Results 31 to 40 of about 115,093 (312)

Contrastive Learning with Stronger Augmentations

IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022
12 pages, 6 ...
Xiao Wang, Guo-Jun Qi
openaire   +3 more sources

Contrasting Contrastive Self-Supervised Representation Learning Pipelines [PDF]

2021 IEEE/CVF International Conference on Computer Vision (ICCV), 2021
In the past few years, we have witnessed remarkable breakthroughs in self-supervised representation learning. Despite the success and adoption of representations learned through this paradigm, much is yet to be understood about how different training methods and datasets influence performance on downstream tasks.
Kotar, Klemen, Ilharco, Gabriel, Schmidt, Ludwig, Ehsani, Kiana, Mottaghi, Roozbeh   +4 more
openaire   +2 more sources

Debiased Contrastive Learning

, 2020
A prominent technique for self-supervised representation learning has been to contrast semantically similar and dissimilar pairs of samples. Without access to labels, dissimilar (negative) points are typically taken to be randomly sampled datapoints, implicitly accepting that these points may, in reality, actually have the same label.
Chuang, Ching-Yao, Robinson, Joshua, Yen-Chen, Lin, Torralba, Antonio, Jegelka, Stefanie   +4 more
openaire   +2 more sources

Robust age estimation model using group‐aware contrastive learning

IET Image Processing, 2022
Although great efforts have been devoted to developing lightweight models for age estimation in recent works, the robustness is still unsatisfactory in unconstrained environments.
Xiaoqiang Li, Chengyu Guo, Yifan Wu, Congcong Zhu, Jide Li   +4 more
doaj   +1 more source

Generalized Parametric Contrastive Learning

IEEE Transactions on Pattern Analysis and Machine Intelligence
TPAMI 2023.
Jiequan Cui, Zhisheng Zhong, Zhuotao Tian, Shu Liu, Bei Yu, Jiaya Jia   +5 more
openaire   +3 more sources

Consistent contrast aids concept learning [PDF]

Memory & Cognition, 2001
We suggest that coherence among concepts and correspondence between concepts and the world are important in concept learning. We identify one aspect of coherence, consistent contrast, and investigate its role in supervised concept learning. Concepts that contrast consistently carry information about the same attributes across the concepts within a ...
D, Billman, D, Dávila
openaire   +2 more sources

Improving Graph Collaborative Filtering from the Perspective of User–Item Interaction Directly Using Contrastive Learning

Mathematics
Graph contrastive learning has demonstrated significant superiority for collaborative filtering. These methods typically use augmentation technology to generate contrastive views, and then train graph neural networks with contrastive learning as an ...
Jifeng Dong, Yu Zhou, Shufeng Hao, Ding Feng, Haixia Zheng, Zhenhuan Xu   +5 more
doaj   +1 more source

Prototypical Contrastive Learning of Unsupervised Representations

, 2021
This paper presents Prototypical Contrastive Learning (PCL), an unsupervised representation learning method that addresses the fundamental limitations of instance-wise contrastive learning.
Hoi, Steven C. H., Li, Junnan, Xiong, Caiming, Zhou, Pan   +3 more
core  

Hodge-Aware Contrastive Learning

ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
4 pages, 2 ...
Möllers, A., Immer, A., Fortuin, V., Isufi, E.   +3 more
openaire   +3 more sources

CC-GNN: A Clustering Contrastive Learning Network for Graph Semi-Supervised Learning

IEEE Access
In graph modeling, scarcity of labeled data is a challenging issue. To address this issue, state-of-the-art graph models learn the representation of graph data via contrastive learning.
Peng Qin, Weifu Chen, Min Zhang, Defang Li, Guocan Feng   +4 more
doaj   +1 more source