相关论文: Understanding Contrastive Representation Learning …

Contrastive learning has achieved remarkable success in representation learning via self-supervision in unsupervised settings. However, effectively adapting contrastive learning to supervised learning tasks remains as a challenge in…

This work studies the relationship between Contrastive Learning and Domain Adaptation from a theoretical perspective. The two standard contrastive losses, NT-Xent loss (Self-supervised) and Supervised Contrastive loss, are related to the…

Learning discriminative image representations plays a vital role in long-tailed image classification because it can ease the classifier learning in imbalanced cases. Given the promising performance contrastive learning has shown recently in…

How can you sample good negative examples for contrastive learning? We argue that, as with metric learning, contrastive learning of representations benefits from hard negative samples (i.e., points that are difficult to distinguish from an…

Multimodal contrastive learning (MCL) aims to embed data from different modalities in a shared embedding space. However, empirical evidence shows that representations from different modalities occupy completely separate regions of embedding…

Many Click-Through Rate (CTR) prediction works focused on designing advanced architectures to model complex feature interactions but neglected the importance of feature representation learning, e.g., adopting a plain embedding layer for…

Adversarial attacks exploit the vulnerabilities of convolutional neural networks by introducing imperceptible perturbations that lead to misclassifications, exposing weaknesses in feature representations and decision boundaries. This paper…

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,…

We investigate the role of projection heads, also known as projectors, within the encoder-projector framework (e.g., SimCLR) used in contrastive learning. We aim to demystify the observed phenomenon where representations learned before…

Contrastive learning is a major studied topic in metric learning. However, sampling effective contrastive pairs remains a challenge due to factors such as limited batch size, imbalanced data distribution, and the risk of overfitting. In…

Contrastive learning has recently demonstrated superior performance to supervised learning, despite requiring no training labels. We explore how contrastive learning can be applied to hundreds of thousands of unlabeled Mars terrain images,…

Classical machine learners are designed only to tackle one task without capability of adopting new emerging tasks or classes whereas such capacity is more practical and human-like in the real world. To address this shortcoming, continual…

Unsupervised learning has made substantial progress over the last few years, especially by means of contrastive self-supervised learning. The dominating dataset for benchmarking self-supervised learning has been ImageNet, for which recent…

Contrastive Learning (CL) has shown promising performance in collaborative filtering. The key idea is to generate augmentation-invariant embeddings by maximizing the Mutual Information between different augmented views of the same instance.…

In Self-Supervised Learning (SSL), various pretext tasks are designed for learning feature representations through contrastive loss. However, previous studies have shown that this loss is less tolerant to semantically similar samples due to…

Self-supervised contrastive learning is a powerful tool to learn visual representation without labels. Prior work has primarily focused on evaluating the recognition accuracy of various pre-training algorithms, but has overlooked other…

We study offline meta-reinforcement learning, a practical reinforcement learning paradigm that learns from offline data to adapt to new tasks. The distribution of offline data is determined jointly by the behavior policy and the task.…

Unsupervised object-centric learning from videos is a promising approach to extract structured representations from large, unlabeled collections of videos. To support downstream tasks like autonomous control, these representations must be…

Contrastive, self-supervised learning of object representations recently emerged as an attractive alternative to reconstruction-based training. Prior approaches focus on contrasting individual object representations (slots) against one…

Learning node-level representations of heterophilic graphs is crucial for various applications, including fraudster detection and protein function prediction. In such graphs, nodes share structural similarity identified by the equivalence…