Z Wang, Y Wang, Z Wu, J Lu… - Proceedings of the IEEE …, 2021 - openaccess.thecvf.com
In this paper, we propose an instance similarity learning (ISL) method for unsupervised feature representation. Conventional methods assign close instance pairs in the feature …
Cluster discrimination is an effective pretext task for unsupervised representation learning, which often consists of two phases: clustering and discrimination. Clustering is to assign …
Self-supervised learning algorithms based on instance discrimination train encoders to be invariant to pre-defined transformations of the same instance. While most methods treat …
Self-supervised learning based on instance discrimination has shown remarkable progress. In particular, contrastive learning, which regards each image as well as its augmentations as …
Unsupervised visual representation learning has gained much attention from the computer vision community because of the recent achievement of contrastive learning. Most of the …
A Devillers, M Lefort - International Conference on Learning …, 2023 - hal.science
Recent self-supervised visual representation methods are closing the gap with supervised learning performance. Most of these successful methods rely on maximizing the similarity …
P Chen, S Liu, J Jia - … of the IEEE/CVF conference on …, 2021 - openaccess.thecvf.com
Unsupervised representation learning with contrastive learning achieves great success recently. However, these methods have to duplicate each training batch to construct …
Y Cao, Z Xie, B Liu, Y Lin… - Advances in neural …, 2020 - proceedings.neurips.cc
This paper presents parametric instance classification (PIC) for unsupervised visual feature learning. Unlike the state-of-the-art approaches which do instance discrimination in a dual …
M Alkhalefi, G Leontidis, M Zhong - arXiv preprint arXiv:2306.16122, 2023 - arxiv.org
Self-supervised learning algorithms based on instance discrimination effectively prevent representation collapse and produce promising results in representation learning. However …