Dense Siamese Network

by   Wenwei Zhang, et al.

This paper presents Dense Siamese Network (DenseSiam), a simple unsupervised learning framework for dense prediction tasks. It learns visual representations by maximizing the similarity between two views of one image with two types of consistency, i.e., pixel consistency and region consistency. Concretely, DenseSiam first maximizes the pixel level spatial consistency according to the exact location correspondence in the overlapped area. It also extracts a batch of region embeddings that correspond to some sub-regions in the overlapped area to be contrasted for region consistency. In contrast to previous methods that require negative pixel pairs, momentum encoders, or heuristic masks, DenseSiam benefits from the simple Siamese network and optimizes the consistency of different granularities. It also proves that the simple location correspondence and interacted region embeddings are effective enough to learn the similarity. We apply DenseSiam on ImageNet and obtain competitive improvements on various downstream tasks. We also show that only with some extra task-specific losses, the simple framework can directly conduct dense prediction tasks. On an existing unsupervised semantic segmentation benchmark, it surpasses state-of-the-art segmentation methods by 2.1 mIoU with 28


page 1

page 2

page 3

page 4


Unsupervised Learning of Dense Visual Representations

Contrastive self-supervised learning has emerged as a promising approach...

Propagate Yourself: Exploring Pixel-Level Consistency for Unsupervised Visual Representation Learning

Contrastive learning methods for unsupervised visual representation lear...

Learning Multi-level Region Consistency with Dense Multi-label Networks for Semantic Segmentation

Semantic image segmentation is a fundamental task in image understanding...

MPASNET: Motion Prior-Aware Siamese Network for Unsupervised Deep Crowd Segmentation in Video Scenes

Crowd segmentation is a fundamental task serving as the basis of crowded...

Exploring Simple Siamese Representation Learning

Siamese networks have become a common structure in various recent models...

In-N-Out Generative Learning for Dense Unsupervised Video Segmentation

In this paper, we focus on the unsupervised Video Object Segmentation (V...

Please sign up or login with your details

Forgot password? Click here to reset