paper-with-me

홈 › Papers

On the Efficacy of Small Self-Supervised Contrastive Models without Distillation Signals

2021-07-30 · Haizhou Shi, Youcai Zhang, Siliang Tang, Wenjie Zhu, Yaqian Li, Yandong Guo, Yueting Zhuang

It is a consensus that small models perform quite poorly under the paradigm of self-supervised contrastive learning. Existing methods usually adopt a large off-the-shelf model to transfer knowledge to the small one via distillation. Despite their effectiveness, distillation-based methods may not be suitable for some resource-restricted scenarios due to the huge computational expenses of deploying a large model. In this paper, we study the issue of training self-supervised small models without distillation signals. We first evaluate the representation spaces of the small models and make two non-negligible observations: (i) the small models can complete the pretext task without overfitting despite their limited capacity and (ii) they universally suffer the problem of over clustering. Then we verify multiple assumptions that are considered to alleviate the over-clustering phenomenon. Finally, we combine the validated techniques and improve the baseline performances of five small architectures with considerable margins, which indicates that training small self-supervised contrastive models is feasible even without distillation signals. The code is available at \textit{https://github.com/WOWNICE/ssl-small}.

📄 PDF Abstract BibTeX arXiv:2107.14762

Code (0)

등록된 구현이 없습니다.

Tasks

ClusteringContrastive LearningKnowledge Distillation

Similar Papers 제목 키워드 기반

Scribble-supervised Cell Segmentation Using Multiscale Contrastive Regularization

2023-06-25 · Hyun-Jic Oh, Kanggeun Lee, Won-Ki Jeong

Current state-of-the-art supervised deep learning-based segmentation approaches have demonstrated superior performance in medical image segmentation tasks. However, such supervised approaches require fully annotated pixe…

Cell SegmentationImage SegmentationMedical Image SegmentationSegmentation+2

Exploring Representation Learning for Small-Footprint Keyword Spotting

2023-03-20 · Fan Cui, Liyong Guo, Quandong Wang, Peng Gao 외

In this paper, we investigate representation learning for low-resource keyword spotting (KWS). The main challenges of KWS are limited labeled data and limited available device resources. To address those challenges, we e…

Contrastive LearningKeyword SpottingRepresentation LearningSmall-Footprint Keyword Spotting

Rethinking Self-Supervised Learning: Small is Beautiful

2021-03-25 · Yun-Hao Cao, Jianxin Wu

Self-supervised learning (SSL), in particular contrastive learning, has made great progress in recent years. However, a common theme in these methods is that they inherit the learning paradigm from the supervised deep le…

Contrastive LearningSelf-Supervised Learning

Efficient Self-Supervision using Patch-based Contrastive Learning for Histopathology Image Segmentation

2022-08-23 · Nicklas Boserup, Raghavendra Selvan

Learning discriminative representations of unlabelled data is a challenging task. Contrastive self-supervised learning provides a framework to learn meaningful representations using learned notions of similarity measures…

Contrastive LearningImage SegmentationSelf-Supervised LearningSemantic Segmentation

ContraCluster: Learning to Classify without Labels by Contrastive Self-Supervision and Prototype-Based Semi-Supervision

2023-04-19 · Seongho Joe, Byoungjip Kim, Hoyoung Kang, Kyoungwon Park 외

The recent advances in representation learning inspire us to take on the challenging problem of unsupervised image classification tasks in a principled way. We propose ContraCluster, an unsupervised image classification …

Contrastive Learningimage-classificationImage ClassificationRepresentation Learning+2