CVAug 12, 2022

Contrastive Learning for Object Detection

arXiv:2208.06412v14 citationsh-index: 4
Originality Synthesis-oriented
AI Analysis

This addresses the problem of learning better feature embeddings in computer vision, but appears incremental as it builds on existing supervised contrastive approaches.

The paper tackles the challenge of improving supervised contrastive learning for object detection by ranking classes based on similarity to study the impact of human bias on learned representations, but no concrete results or numbers are reported.

Contrastive learning is commonly used as a method of self-supervised learning with the "anchor" and "positive" being two random augmentations of a given input image, and the "negative" is the set of all other images. However, the requirement of large batch sizes and memory banks has made it difficult and slow to train. This has motivated the rise of Supervised Contrasative approaches that overcome these problems by using annotated data. We look to further improve supervised contrastive learning by ranking classes based on their similarity, and observe the impact of human bias (in the form of ranking) on the learned representations. We feel this is an important question to address, as learning good feature embeddings has been a long sought after problem in computer vision.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes