In this paper, we present a comprehensive review of the imbalance problems in object
detection. To analyze the problems in a systematic manner, we introduce a problem-based …

Despite the success of large vision and language models (VLMs) in many downstream
applications, it is unclear how well they encode compositional information. Here, we create …

Contrastive learning has become a key component of self-supervised learning approaches
for computer vision. By learning to embed two augmented versions of the same image close …

Abstract We introduce Bootstrap Your Own Latent (BYOL), a new approach to self-
supervised image representation learning. BYOL relies on two neural networks, referred to …

Understanding verbs is crucial to modelling how people and objects interact with each other
and the environment through space and time. Recently, state-of-the-art video-language …

Deep metric learning papers from the past four years have consistently claimed great
advances in accuracy, often more than doubling the performance of decade-old methods. In …

A family of loss functions built on pair-based computation have been proposed in the
literature which provide a myriad of solutions for deep metric learning. In this pa-per, we …

Existing metric learning losses can be categorized into two classes: pair-based and proxy-
based losses. The former class can leverage fine-grained semantic relations between data …

Meta-learning has been proposed as a framework to address the challenging few-shot
learning setting. The key idea is to leverage a large number of similar few-shot tasks in order …

This paper studies the unsupervised embedding learning problem, which requires an
effective similarity measurement between samples in low-dimensional embedding space …