English
Related papers

Related papers: CIPER: Combining Invariant and Equivariant Represe…

200 papers

When robots learn reward functions using high capacity models that take raw state directly as input, they need to both learn a representation for what matters in the task -- the task ``features" -- as well as how to combine these features…

Robotics · Computer Science 2023-03-20 Andreea Bobu , Yi Liu , Rohin Shah , Daniel S. Brown , Anca D. Dragan

Contrastive Learning (CL) has emerged as a powerful method for training feature extraction models using unlabeled data. Recent studies suggest that incorporating a linear projection head post-backbone significantly enhances model…

Machine Learning · Computer Science 2024-10-08 Huanran Li , Daniel Pimentel-Alarcón

Contrastive learning has become a key component of self-supervised learning approaches for computer vision. By learning to embed two augmented versions of the same image close to each other and to push the embeddings of different images…

Computer Vision and Pattern Recognition · Computer Science 2020-12-07 Yannis Kalantidis , Mert Bulent Sariyildiz , Noe Pion , Philippe Weinzaepfel , Diane Larlus

In the field of continual learning, models are designed to learn tasks one after the other. While most research has centered on supervised continual learning, there is a growing interest in unsupervised continual learning, which makes use…

Machine Learning · Computer Science 2024-07-18 Daniel Marczak , Sebastian Cygert , Tomasz Trzciński , Bartłomiej Twardowski

Contrastive learning has led to substantial improvements in the quality of learned embedding representations for tasks such as image classification. However, a key drawback of existing contrastive augmentation methods is that they may lead…

Computer Vision and Pattern Recognition · Computer Science 2022-04-19 Zhibo Zhang , Jongseong Jang , Chiheb Trabelsi , Ruiwen Li , Scott Sanner , Yeonjeong Jeong , Dongsub Shim

The success of deep learning is usually accompanied by the growth in neural network depth. However, the traditional training method only supervises the neural network at its last layer and propagates the supervision layer-by-layer, which…

Computer Vision and Pattern Recognition · Computer Science 2022-07-13 Linfeng Zhang , Xin Chen , Junbo Zhang , Runpei Dong , Kaisheng Ma

Contrastive learning is a well-established paradigm in representation learning. The standard framework of contrastive learning minimizes the distance between "similar" instances and maximizes the distance between dissimilar ones in the…

Machine Learning · Computer Science 2025-02-06 Naghmeh Ghanooni , Barbod Pajoum , Harshit Rawal , Sophie Fellenz , Vo Nguyen Le Duy , Marius Kloft

Self-supervised learning (SSL) has become prevalent for learning representations in computer vision. Notably, SSL exploits contrastive learning to encourage visual representations to be invariant under various image transformations. The…

Computer Vision and Pattern Recognition · Computer Science 2022-10-25 Swati Jindal , Roberto Manduchi

Contrastive learning has been proven beneficial for self-supervised skeleton-based action recognition. Most contrastive learning methods utilize carefully designed augmentations to generate different movement patterns of skeletons for the…

Computer Vision and Pattern Recognition · Computer Science 2023-07-13 Jiahang Zhang , Lilang Lin , Jiaying Liu

Self-supervised learning has been widely used to obtain transferrable representations from unlabeled images. Especially, recent contrastive learning methods have shown impressive performances on downstream image classification tasks. While…

Computer Vision and Pattern Recognition · Computer Science 2021-04-29 Byungseok Roh , Wuhyun Shin , Ildoo Kim , Sungwoong Kim

Tremendous progress has been made in visual representation learning, notably with the recent success of self-supervised contrastive learning methods. Supervised contrastive learning has also been shown to outperform its cross-entropy…

Computer Vision and Pattern Recognition · Computer Science 2021-08-17 Ashraful Islam , Chun-Fu Chen , Rameswar Panda , Leonid Karlinsky , Richard Radke , Rogerio Feris

Despite the success of a number of recent techniques for visual self-supervised deep learning, there has been limited investigation into the representations that are ultimately learned. By leveraging recent advances in the comparison of…

Computer Vision and Pattern Recognition · Computer Science 2021-12-06 Tom George Grigg , Dan Busbridge , Jason Ramapuram , Russ Webb

The standard approach to contrastive learning is to maximize the agreement between different views of the data. The views are ordered in pairs, such that they are either positive, encoding different views of the same object, or negative,…

Computer Vision and Pattern Recognition · Computer Science 2023-02-21 Artem Moskalev , Ivan Sosnovik , Volker Fischer , Arnold Smeulders

Self-supervision is one of the hallmarks of representation learning in the increasingly popular suite of foundation models including large language models such as BERT and GPT-3, but it has not been pursued in the context of multivariate…

Machine Learning · Computer Science 2024-02-05 Xiao Shou , Dharmashankar Subramanian , Debarun Bhattacharjya , Tian Gao , Kristin P. Bennet

Self-supervised visual representation methods are closing the gap with supervised learning performance. These methods rely on maximizing the similarity between embeddings of related synthetic inputs created through data augmentations. This…

Machine Learning · Computer Science 2023-06-09 Alexandre Devillers , Mathieu Lefort

This paper investigates unsupervised representation learning for facial expression analysis. We think Unsupervised Facial Expression Representation (UFER) deserves exploration and has the potential to address some key challenges in facial…

Computer Vision and Pattern Recognition · Computer Science 2023-03-17 Fanglei Xue , Yifan Sun , Yi Yang

Latent representations are used extensively for downstream tasks, such as visualization, interpolation or feature extraction of deep learning models. Invariant and equivariant neural networks are powerful and well-established models for…

Machine Learning · Computer Science 2025-01-16 Andreas Abildtrup Hansen , Anna Calissano , Aasa Feragen

Asymmetric appearance between positive pair effectively reduces the risk of representation degradation in contrastive learning. However, there are still a mass of appearance similarities between positive pair constructed by the existing…

Computer Vision and Pattern Recognition · Computer Science 2023-06-06 Chengchao Shen , Jianzhong Chen , Shu Wang , Hulin Kuang , Jin Liu , Jianxin Wang

Previous contrastive learning methods for sentence representations often focus on insensitive transformations to produce positive pairs, but neglect the role of sensitive transformations that are harmful to semantic representations.…

Computation and Language · Computer Science 2023-03-10 Jie Liu , Yixuan Liu , Xue Han , Chao Deng , Junlan Feng

Recently contrastive learning has shown significant progress in learning visual representations from unlabeled data. The core idea is training the backbone to be invariant to different augmentations of an instance. While most methods only…

Computer Vision and Pattern Recognition · Computer Science 2021-11-05 Xiaoyang Guo , Tianhao Zhao , Yutian Lin , Bo Du