paper-with-me

홈 › Papers

Constructive Assimilation: Boosting Contrastive Learning Performance through View Generation Strategies

2023-04-02 · Ligong Han, Seungwook Han, Shivchander Sudalairaj, Charlotte Loh, Rumen Dangovski, Fei Deng, Pulkit Agrawal, Dimitris Metaxas, Leonid Karlinsky, Tsui-Wei Weng, Akash Srivastava

Transformations based on domain expertise (expert transformations), such as random-resized-crop and color-jitter, have proven critical to the success of contrastive learning techniques such as SimCLR. Recently, several attempts have been made to replace such domain-specific, human-designed transformations with generated views that are learned. However for imagery data, so far none of these view-generation methods has been able to outperform expert transformations. In this work, we tackle a different question: instead of replacing expert transformations with generated views, can we constructively assimilate generated views with expert transformations? We answer this question in the affirmative and propose a view generation method and a simple, effective assimilation method that together improve the state-of-the-art by up to ~3.6% on three different datasets. Importantly, we conduct a detailed empirical study that systematically analyzes a range of view generation and assimilation methods and provides a holistic picture of the efficacy of learned views in contrastive representation learning.

📄 PDF Abstract BibTeX arXiv:2304.00601

Code (0)

등록된 구현이 없습니다.

Tasks

Contrastive LearningRepresentation Learning

Methods 이 논문이 사용한 방법론

None 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,…
Residual Connection 설명 없음
Average Pooling 설명 없음
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…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
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

CoRe-ECG: Advancing Self-Supervised Representation Learning for 12-Lead ECG via Contrastive and Reconstructive Synergy

2026-04-13 · Zehao Qin, Xiaojian Lin, Ping Zhang, Hongliang Wu 외 arxiv

Accurate interpretation of electrocardiogram (ECG) remains challenging due to the scarcity of labeled data and the high cost of expert annotation. Self-supervised learning (SSL) offers a promising solution by enabling mo…

Self-Supervised LearningRepresentation LearningContrastive Learning

RePre: Improving Self-Supervised Vision Transformer with Reconstructive Pre-training

2022-01-18 · Luya Wang, Feng Liang, Yangguang Li, Honggang Zhang 외

Recently, self-supervised vision transformers have attracted unprecedented attention for their impressive representation learning ability. However, the dominant method, contrastive learning, mainly relies on an instance …

Contrastive LearningDecoderRepresentation Learning

Understanding Masked Autoencoders From a Local Contrastive Perspective

2023-10-03 · Xiaoyu Yue, Lei Bai, Meng Wei, Jiangmiao Pang 외

Masked AutoEncoder (MAE) has revolutionized the field of self-supervised learning with its simple yet effective masking and reconstruction strategies. However, despite achieving state-of-the-art performance across variou…

Contrastive LearningData AugmentationDecoderSelf-Supervised Learning

Ensemble-based kernel learning for a class of data assimilation problems with imperfect forward simulators

2019-01-30 · Xiaodong Luo

Simulator imperfection, often known as model error, is ubiquitous in practical data assimilation problems. Despite the enormous efforts dedicated to addressing this problem, properly handling simulator imperfection in da…

BIG-bench Machine Learning

How to Boost Any Loss Function

2024-07-02 · Richard Nock, Yishay Mansour

Boosting is a highly successful ML-born optimization setting in which one is required to computationally efficiently learn arbitrarily good models based on the access to a weak learner oracle, providing classifiers perfo…