Dense Contrastive Learning

Introduced by Wang et al. in Dense Contrastive Learning for Self-Supervised Visual Pre-Training

Dense Contrastive Learning is a self-supervised learning method for dense prediction tasks. It implements self-supervised learning by optimizing a pairwise contrastive (dis)similarity loss at the pixel level between two views of input images. Contrasting with regular contrastive loss, the contrastive loss is computed between the single feature vectors outputted by the global projection head, at the level of global feature, while the dense contrastive loss is computed between the dense feature vectors outputted by the dense projection head, at the level of local feature.

Source: Dense Contrastive Learning for Self-Supervised Visual Pre-Training

Read Paper See Code

Papers

Paper	Code	Results	Date	Stars

Tasks

Task	Papers	Share
Image Classification	2	12.50%
Self-Supervised Learning	2	12.50%
Semantic Segmentation	2	12.50%
Optical Flow Estimation	1	6.25%
PICO	1	6.25%
Image Segmentation	1	6.25%
Image Retrieval	1	6.25%
Multi-label zero-shot learning	1	6.25%
Multimodal Deep Learning	1	6.25%

Usage Over Time

This feature is experimental; we are continuously improving our matching algorithm.

Components

Component	Type	Add Remove
🤖 No Components Found	You can add them if they exist; e.g. Mask R-CNN uses RoIAlign

Categories

Add Remove

Self-Supervised Learning