paper-with-me

홈 › Papers

Batch Curation for Unsupervised Contrastive Representation Learning

2021-08-19 · Michael C. Welle, Petra Poklukar, Danica Kragic

The state-of-the-art unsupervised contrastive visual representation learning methods that have emerged recently (SimCLR, MoCo, SwAV) all make use of data augmentations in order to construct a pretext task of instant discrimination consisting of similar and dissimilar pairs of images. Similar pairs are constructed by randomly extracting patches from the same image and applying several other transformations such as color jittering or blurring, while transformed patches from different image instances in a given batch are regarded as dissimilar pairs. We argue that this approach can result similar pairs that are \textit{semantically} dissimilar. In this work, we address this problem by introducing a \textit{batch curation} scheme that selects batches during the training process that are more inline with the underlying contrastive objective. We provide insights into what constitutes beneficial similar and dissimilar pairs as well as validate \textit{batch curation} on CIFAR10 by integrating it in the SimCLR model.

📄 PDF Abstract BibTeX arXiv:2108.08643

Code (0)

등록된 구현이 없습니다.

Tasks

Representation Learning

Methods 이 논문이 사용한 방법론

Bitcoin Customer Service Number +1-833-534-1729 설명 없음
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Residual Connection 설명 없음
1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Average Pooling 설명 없음
Bottleneck Residual Block A Bottleneck Residual Block is a variant of the residual block that utilises 1x1 convolutions to create a bottleneck. The…
Global Average Pooling Global Average Pooling is a pooling operation designed to replace fully connected layers in classical CNNs. The idea is to generate one feature map for each corresponding…

Similar Papers 제목 키워드 기반

Data curation via joint example selection further accelerates multimodal learning

2024-06-25 · Talfan Evans, Nikhil Parthasarathy, Hamza Merzic, Olivier J. Henaff

Data curation is an essential component of large-scale pretraining. In this work, we demonstrate that jointly selecting batches of data is more effective for learning than selecting examples independently. Multimodal con…

Contrastive Learning

Jigsaw Clustering for Unsupervised Visual Representation Learning

2021-04-01 · CVPR 2021 1 · Pengguang Chen, Shu Liu, Jiaya Jia

Unsupervised representation learning with contrastive learning achieved great success. This line of methods duplicate each training batch to construct contrastive pairs, making each training batch and its augmented versi…

ClusteringContrastive LearningRepresentation Learning

The Bad Batches: Enhancing Self-Supervised Learning in Image Classification Through Representative Batch Curation

2024-03-28 · Ozgu Goksu, Nicolas Pugeault

The pursuit of learning robust representations without human supervision is a longstanding challenge. The recent advancements in self-supervised contrastive learning approaches have demonstrated high performance across v…

Contrastive Learningimage-classificationImage ClassificationRepresentation Learning+1

Less can be more in contrastive learning

2020-10-19 · NeurIPS Workshop ICBINB 2020 12 · Jovana Mitrovic, Brian McWilliams, Melanie Rey

Unsupervised representation learning provides an attractive alternative to its supervised counterpart because of the abundance of unlabelled data. Contrastive learning has recently emerged as one of the most successful…

Contrastive LearningRepresentation Learning

IPCL: Iterative Pseudo-Supervised Contrastive Learning to Improve Self-Supervised Feature Representation

2024-03-18 · IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2024 3 · Sonal Kumar; Anirudh Phukan, Arijit Sur

Self-supervised learning with a contrastive batch approach has become a powerful tool for representation learning in computer vision. The performance of downstream tasks is proportional to the quality of visual features …

Contrastive LearningData Augmentationimage-classificationImage Classification+5