An empirical study of graph contrastive learning
Graph Contrastive Learning (GCL) establishes a new paradigm for learning graph
representations without human annotations. Although remarkable progress has been …
representations without human annotations. Although remarkable progress has been …
Is a caption worth a thousand images? a controlled study for representation learning
The development of CLIP [Radford et al., 2021] has sparked a debate on whether language
supervision can result in vision models with more transferable representations than …
supervision can result in vision models with more transferable representations than …
Contrasting contrastive self-supervised representation learning pipelines
In the past few years, we have witnessed remarkable breakthroughs in self-supervised
representation learning. Despite the success and adoption of representations learned …
representation learning. Despite the success and adoption of representations learned …
Is self-supervised learning more robust than supervised learning?
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 …
labels. Prior work has primarily focused on evaluating the recognition accuracy of various …
Beyond supervised vs. unsupervised: Representative benchmarking and analysis of image representation learning
M Gwilliam, A Shrivastava - … of the IEEE/CVF Conference on …, 2022 - openaccess.thecvf.com
By leveraging contrastive learning, clustering, and other pretext tasks, unsupervised
methods for learning image representations have reached impressive results on standard …
methods for learning image representations have reached impressive results on standard …
Learning representations with contrastive self-supervised learning for histopathology applications
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 …
means of contrastive self-supervised learning. The dominating dataset for benchmarking self …
Contrastive Learning Relies More on Spatial Inductive Bias Than Supervised Learning: An Empirical Study
Though self-supervised contrastive learning (CL) has shown its potential to achieve state-of-
the-art accuracy without any supervision, its behavior still remains under investigated by …
the-art accuracy without any supervision, its behavior still remains under investigated by …
An empirical analysis for zero-shot multi-label classification on covid-19 ct scans and uncurated reports
The pandemic resulted in vast repositories of unstructured data, including radiology reports,
due to increased medical examinations. Previous research on automated diagnosis of …
due to increased medical examinations. Previous research on automated diagnosis of …
Enhancing 2D Representation Learning with a 3D Prior
Learning robust and effective representations of visual data is a fundamental task in
computer vision. Traditionally this is achieved by training models with expensive to obtain …
computer vision. Traditionally this is achieved by training models with expensive to obtain …
Feature dropout: Revisiting the role of augmentations in contrastive learning
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 …
augmentations are label-preserving with respect to a specific downstream task. We …