Related papers: EBMs vs. CL: Exploring Self-Supervised Visual Pret…

Recently, contrastive self-supervised learning, where the proximity of representations is determined based on the identities of samples, has made remarkable progress in unsupervised representation learning. SimSiam is a well-known example…

Pre-training a recognition model with contrastive learning on a large dataset of unlabeled data has shown great potential to boost the performance of a downstream task, e.g., image classification. However, in domains such as medical…

Multi-view clustering (MVC) has had significant implications in cross-modal representation learning and data-driven decision-making in recent years. It accomplishes this by leveraging the consistency and complementary information among…

Representation learning approaches typically rely on images of objects captured from a single perspective that are transformed using affine transformations. Additionally, self-supervised learning, a successful paradigm of representation…

Semi-supervised learning acts as an effective way to leverage massive unlabeled data. In this paper, we propose a novel training strategy, termed as Semi-supervised Contrastive Learning (SsCL), which combines the well-known contrastive loss…

State-of-the-art computer vision models are mostly trained with supervised learning using human-labeled images, which limits their scalability due to the expensive annotation cost. While self-supervised representation learning has achieved…

Learning from previously collected data via behavioral cloning or offline reinforcement learning (RL) is a powerful recipe for scaling generalist agents by avoiding the need for expensive online learning. Despite strong generalization in…

This work proposes a hybrid unsupervised and supervised learning method to pre-train models applied in Earth observation downstream tasks when only a handful of labels denoting very general semantic concepts are available. We combine a…

Self-supervised learning has produced impressive results in multimedia domains of audio, vision and speech. This paradigm is equally, if not more, relevant for the domain of biosignals, owing to the scarcity of labelled data in such…

Contrastive learning is among the most successful methods for visual representation learning, and its performance can be further improved by jointly performing clustering on the learned representations. However, existing methods for joint…

Contrastive language-image Pre-training (CLIP) [13] can leverage large datasets of unlabeled Image-Text pairs, which have demonstrated impressive performance in various downstream tasks. Given that annotating medical data is time-consuming…

Contrastive pretraining on image-text pairs from the web is one of the most popular large-scale pretraining strategies for vision backbones, especially in the context of large multimodal models. At the same time, image captioning on this…

Most Visual Question Answering (VQA) models suffer from the language prior problem, which is caused by inherent data biases. Specifically, VQA models tend to answer questions (e.g., what color is the banana?) based on the high-frequency…

Despite its success in self-supervised learning, contrastive learning is less studied in the supervised setting. In this work, we first use a set of pilot experiments to show that in the supervised setting, the cross-entropy loss objective…

As digital medical imaging becomes more prevalent and archives increase in size, representation learning exposes an interesting opportunity for enhanced medical decision support systems. On the other hand, medical imaging data is often…

Learning visual representations of medical images (e.g., X-rays) is core to medical image understanding but its progress has been held back by the scarcity of human annotations. Existing work commonly relies on fine-tuning weights…

Learning effective visual representations without human supervision is a long-standing problem in computer vision. Recent advances in self-supervised learning algorithms have utilized contrastive learning, with methods such as SimCLR, which…

Pre-trained Vision Language Models (VLMs) have demonstrated notable progress in various zero-shot tasks, such as classification and retrieval. Despite their performance, because improving performance on new tasks requires task-specific…

Disease diagnosis from medical images via supervised learning is usually dependent on tedious, error-prone, and costly image labeling by medical experts. Alternatively, semi-supervised learning and self-supervised learning offer…

Variable names are critical for conveying intended program behavior. Machine learning-based program analysis methods use variable name representations for a wide range of tasks, such as suggesting new variable names and bug detection.…