Related papers: Learning Better Contrastive View from Radiologist'…

Radiology reports are crucial for planning treatment strategies and facilitating effective doctor-patient communication. However, the manual creation of these reports places a significant burden on radiologists. While automatic radiology…

Artificial intelligence aids in brain tumor detection via MRI scans, enhancing the accuracy and reducing the workload of medical professionals. However, in scenarios with extremely limited medical images, traditional deep learning…

Well-annotated medical datasets enable deep neural networks (DNNs) to gain strong power in extracting lesion-related features. Building such large and well-designed medical datasets is costly due to the need for high-level expertise. Model…

Learning self-supervised representations using reconstruction or contrastive losses improves performance and sample complexity of image-based and multimodal reinforcement learning (RL). Here, different self-supervised loss functions have…

What role do augmentations play in contrastive learning? Recent work suggests that good augmentations are label-preserving with respect to a specific downstream task. We complicate this picture by showing that label-destroying augmentations…

Vast quantities of person-generated health data (wearables) are collected but the process of annotating to feed to machine learning models is impractical. This paper discusses ways in which self-supervised approaches that use contrastive…

Contrastive Learning (CL), a leading paradigm in Self-Supervised Learning (SSL), typically relies on pairs of data views generated through augmentation. While multiple augmentations per instance (more than two) improve generalization in…

This paper presents SimCLR: a simple framework for contrastive learning of visual representations. We simplify recently proposed contrastive self-supervised learning algorithms without requiring specialized architectures or a memory bank.…

Recent advances in supervised deep learning methods are enabling remote measurements of photoplethysmography-based physiological signals using facial videos. The performance of these supervised methods, however, are dependent on the…

High annotation costs are a substantial bottleneck in applying modern deep learning architectures to clinically relevant medical use cases, substantiating the need for novel algorithms to learn from unlabeled data. In this work, we propose…

Contrastive self-supervised learning has shown impressive results in learning visual representations from unlabeled images by enforcing invariance against different data augmentations. However, the learned representations are often…

Contrastive learning -- a modern approach to extract useful representations from unlabeled data by training models to distinguish similar samples from dissimilar ones -- has driven significant progress in foundation models. In this work, we…

Counterfactually Augmented Data (CAD) involves creating new data samples by applying minimal yet sufficient modifications to flip the label of existing data samples to other classes. Training with CAD enhances model robustness against…

Self-supervised representation learning is an emerging research topic for its powerful capacity in learning with unlabeled data. As a mainstream self-supervised learning method, augmentation-based contrastive learning has achieved great…

Deep anomaly detection methods learn representations that separate between normal and anomalous images. Although self-supervised representation learning is commonly used, small dataset sizes limit its effectiveness. It was previously shown…

This paper targets at improving the generalizability of hypergraph neural networks in the low-label regime, through applying the contrastive learning approach from images/graphs (we refer to it as HyperGCL). We focus on the following…

While contrastive learning is proven to be an effective training strategy in computer vision, Natural Language Processing (NLP) is only recently adopting it as a self-supervised alternative to Masked Language Modeling (MLM) for improving…

Medical image registration is a fundamental task in medical image analysis, enabling the alignment of images from different modalities or time points. However, intensity inconsistencies and nonlinear tissue deformations pose significant…

Contrastive learning methods train visual encoders by comparing views from one instance to others. Typically, the views created from one instance are set as positive, while views from other instances are negative. This binary instance…

Recent works in Generative Adversarial Networks (GANs) are actively revisiting various data augmentation techniques as an effective way to prevent discriminator overfitting. It is still unclear, however, that which augmentations could…