Related papers: Self-Labeling Refinement for Robust Representation…

Self-supervised learning (SSL) has demonstrated its effectiveness in learning representations through comparison methods that align with human intuition. However, mainstream SSL methods heavily rely on high body datasets with single label,…

Neural networks trained on standard image classification data sets are shown to be less resistant to data set bias. It is necessary to comprehend the behavior objective function that might correspond to superior performance for data with…

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…

Models initialized from self-supervised pretraining may suffer from poor alignment with downstream tasks, reducing the extent to which subsequent fine-tuning can adapt pretrained features toward downstream objectives. To mitigate this, we…

Recent binary representation learning models usually require sophisticated binary optimization, similarity measure or even generative models as auxiliaries. However, one may wonder whether these non-trivial components are needed to…

Self-supervised Learning (SSL) aims to learn transferable feature representations for downstream applications without relying on labeled data. The Barlow Twins algorithm, renowned for its widespread adoption and straightforward…

Session-based recommendation, which aims to predict the next item of users' interest as per an existing sequence interaction of items, has attracted growing applications of Contrastive Learning (CL) with improved user and item…

The vision-language navigation (VLN) task requires an agent to reach a target with the guidance of natural language instruction. Previous works learn to navigate step-by-step following an instruction. However, these works may fail to…

Self-supervised learning (SSL) has recently achieved tremendous empirical advancements in learning image representation. However, our understanding of the principle behind learning such a representation is still limited. This work shows…

Despite the empirical successes of self-supervised learning (SSL) methods, it is unclear what characteristics of their representations lead to high downstream accuracies. In this work, we characterize properties that SSL representations…

We present Variational Self-Supervised Learning (VSSL), a novel framework that combines variational inference with self-supervised learning to enable efficient, decoder-free representation learning. Unlike traditional VAEs that rely on…

Recent progress in self-supervised (SSL) visual representation learning has led to the development of several different proposed frameworks that rely on augmentations of images but use different loss functions. However, there are few…

Self-supervised learning provides a promising path towards eliminating the need for costly label information in representation learning on graphs. However, to achieve state-of-the-art performance, methods often need large numbers of…

Sentence Representation Learning (SRL) is a crucial task in Natural Language Processing (NLP), where contrastive Self-Supervised Learning (SSL) is currently a mainstream approach. However, the reasons behind its remarkable effectiveness…

Contrastive learning is a powerful technique to learn representations that are semantically distinctive and geometrically invariant. While most of the earlier approaches have demonstrated its effectiveness on single-modality learning tasks…

This paper presents a new way to identify additional positive pairs for BYOL, a state-of-the-art (SOTA) self-supervised learning framework, to improve its representation learning ability. Unlike conventional BYOL which relies on only one…

Self-Supervised Learning (SSL) surmises that inputs and pairwise positive relationships are enough to learn meaningful representations. Although SSL has recently reached a milestone: outperforming supervised methods in many modalities\dots…

This paper presents SPeCiaL: a method for unsupervised pretraining of representations tailored for continual learning. Our approach devises a meta-learning objective that differentiates through a sequential learning process. Specifically,…

This work combines Convolutional Neural Networks (CNNs), clustering via Self-Organizing Maps (SOMs) and Hebbian Learning to propose the building blocks of Convolutional Self-Organizing Neural Networks (CSNNs), which learn representations in…

The fundamental goal of self-supervised learning (SSL) is to produce useful representations of data without access to any labels for classifying the data. Modern methods in SSL, which form representations based on known or constructed…