Related papers: Intriguing Properties of Contrastive Losses

Self-supervised instance discrimination is an effective contrastive pretext task to learn feature representations and address limited medical image annotations. The idea is to make features of transformed versions of the same images similar…

Representation learning methods utilizing the InfoNCE loss have demonstrated considerable capacity in reducing human annotation effort by training invariant neural feature extractors. Although different variants of the training objective…

We propose a self-supervised approach for learning representations of objects from monocular videos and demonstrate it is particularly useful in situated settings such as robotics. The main contributions of this paper are: 1) a…

Contrastive Learning (CL) has been successfully applied to classification and other downstream tasks related to concrete concepts, such as objects contained in the ImageNet dataset. No attempts seem to have been made so far in applying this…

Detecting anomalies is one fundamental aspect of a safety-critical software system, however, it remains a long-standing problem. Numerous branches of works have been proposed to alleviate the complication and have demonstrated their…

Ensembles of Convolutional neural networks have shown remarkable results in learning discriminative semantic features for image classification tasks. Though, the models in the ensemble often concentrate on similar regions in images. This…

Neural network based speech recognition systems suffer from performance degradation due to accented speech, especially unfamiliar accents. In this paper, we study the supervised contrastive learning framework for accented speech…

In this paper we present a world model, which learns causal features using the invariance principle. In particular, we use contrastive unsupervised learning to learn the invariant causal features, which enforces invariance across…

Distribution shifts are problems where the distribution of data changes between training and testing, which can significantly degrade the performance of a model deployed in the real world. Recent studies suggest that one reason for the…

We propose a novel contrastive learning framework to effectively address the challenges of data heterogeneity in federated learning. We first analyze the inconsistency of gradient updates across clients during local training and establish…

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…

Dense correspondence across semantically related images has been extensively studied, but still faces two challenges: 1) large variations in appearance, scale and pose exist even for objects from the same category, and 2) labeling…

Contrastive representation learning (CRL) underpins many modern foundation models. Despite recent theoretical progress, existing analyses suffer from several key limitations: (i) the statistical consistency of CRL remains poorly understood;…

Contrastive learning operates on a simple yet effective principle: Embeddings of positive pairs are pulled together, while those of negative pairs are pushed apart. In this paper, we propose a unified framework for understanding contrastive…

Deep neural networks (DNNs) have achieved remarkable success in computer vision tasks such as image classification, segmentation, and object detection. However, they are vulnerable to adversarial attacks, which can cause incorrect…

Visual domain gaps often impact object detection performance. Image-to-image translation can mitigate this effect, where contrastive approaches enable learning of the image-to-image mapping under unsupervised regimes. However, existing…

Video summarization aims to select the most informative subset of frames in a video to facilitate efficient video browsing. Unsupervised methods usually rely on heuristic training objectives such as diversity and representativeness.…

As a seminal tool in self-supervised representation learning, contrastive learning has gained unprecedented attention in recent years. In essence, contrastive learning aims to leverage pairs of positive and negative samples for…

Contrastive representation learning, which aims to learnthe shared information between different views of unlabeled data by maximizing the mutual information between them, has shown its powerful competence in self-supervised learning for…

Contrastive loss and triplet loss are widely used objectives in deep metric learning, yet their effects on representation quality remain insufficiently understood. We present a theoretical and empirical comparison of these losses, focusing…