Related papers: Understanding Dimensional Collapse in Contrastive …
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…
Recent works in self-supervised learning have advanced the state-of-the-art by relying on the contrastive learning paradigm, which learns representations by pushing positive pairs, or similar examples from the same class, closer together…
Labeling data is often very time consuming and expensive, leaving us with a majority of unlabeled data. Self-supervised representation learning methods such as SimCLR (Chen et al., 2020) or BYOL (Grill et al., 2020) have been very…
Recently, dense contrastive learning has shown superior performance on dense prediction tasks compared to instance-level contrastive learning. Despite its supremacy, the properties of dense contrastive representations have not yet been…
Self-Supervised Learning (SSL) is a paradigm that leverages unlabeled data for model training. Empirical studies show that SSL can achieve promising performance in distribution shift scenarios, where the downstream and training…
Contrastive self-supervised learning has become a prominent technique in representation learning. The main step in these methods is to contrast semantically similar and dissimilar pairs of samples. However, in the domain of Natural Language…
To improve performance in visual feature representation from photos or videos for practical applications, we generally require large-scale human-annotated labeled data while training deep neural networks. However, the cost of gathering and…
In recent years, a variety of contrastive learning based unsupervised visual representation learning methods have been designed and achieved great success in many visual tasks. Generally, these methods can be roughly classified into four…
In self-supervised representation learning, Siamese networks are a natural architecture for learning transformation-invariance by bringing representations of positive pairs closer together. But it is prone to collapse into a degenerate…
Contrastive self-supervised learning (CSL) with a prototypical regularization has been introduced in learning meaningful representations for downstream tasks that require strong semantic information. However, to optimize CSL with a loss…
Contrastive learning has shown promising potential in self-supervised spatio-temporal representation learning. Most works naively sample different clips to construct positive and negative pairs. However, we observe that this formulation…
Self-supervised skeleton-based action recognition enjoys a rapid growth along with the development of contrastive learning. The existing methods rely on imposing invariance to augmentations of 3D skeleton within a single data stream, which…
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…
In recent years, self-supervised learning (SSL) has emerged as a promising approach for extracting valuable representations from unlabeled data. One successful SSL method is contrastive learning, which aims to bring positive examples closer…
Self-supervised learning (SSL) has recently achieved great success in mining the user-item interactions for collaborative filtering. As a major paradigm, contrastive learning (CL) based SSL helps address data sparsity in Web platforms by…
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…
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…
Most Neural Networks (NNs) for classification are trained using Cross-Entropy as a loss function. This approach requires the model to have an explicit classification layer. However, there exist alternative approaches, such as Contrastive…
Multimodal Contrastive Learning (MCL) advances in aligning different modalities and generating multimodal representations in a joint space. By leveraging contrastive learning across diverse modalities, large-scale multimodal data enhances…
In reinforcement learning (RL), it is easier to solve a task if given a good representation. While deep RL should automatically acquire such good representations, prior work often finds that learning representations in an end-to-end fashion…