Multi-scale Matching Networks for Semantic Correspondence

07/31/2021
by   Dongyang Zhao, et al.
2

Deep features have been proven powerful in building accurate dense semantic correspondences in various previous works. However, the multi-scale and pyramidal hierarchy of convolutional neural networks has not been well studied to learn discriminative pixel-level features for semantic correspondence. In this paper, we propose a multi-scale matching network that is sensitive to tiny semantic differences between neighboring pixels. We follow the coarse-to-fine matching strategy and build a top-down feature and matching enhancement scheme that is coupled with the multi-scale hierarchy of deep convolutional neural networks. During feature enhancement, intra-scale enhancement fuses same-resolution feature maps from multiple layers together via local self-attention and cross-scale enhancement hallucinates higher-resolution feature maps along the top-down hierarchy. Besides, we learn complementary matching details at different scales thus the overall matching score is refined by features of different semantic levels gradually. Our multi-scale matching network can be trained end-to-end easily with few additional learnable parameters. Experimental results demonstrate that the proposed method achieves state-of-the-art performance on three popular benchmarks with high computational efficiency.

READ FULL TEXT

page 1

page 3

page 5

page 8

page 13

page 14

page 15

page 16

research
06/16/2020

Dual-Resolution Correspondence Networks

We tackle the problem of establishing dense pixel-wise correspondences b...
research
11/17/2016

AutoScaler: Scale-Attention Networks for Visual Correspondence

Finding visual correspondence between local features is key to many comp...
research
05/31/2021

ACNet: Mask-Aware Attention with Dynamic Context Enhancement for Robust Acne Detection

Computer-aided diagnosis has recently received attention for its advanta...
research
08/06/2023

Multi-scale Alternated Attention Transformer for Generalized Stereo Matching

Recent stereo matching networks achieves dramatic performance by introdu...
research
03/26/2020

Correspondence Networks with Adaptive Neighbourhood Consensus

In this paper, we tackle the task of establishing dense visual correspon...
research
06/09/2020

Single Image Deraining via Scale-space Invariant Attention Neural Network

Image enhancement from degradation of rainy artifacts plays a critical r...
research
10/17/2022

Anisotropic Multi-Scale Graph Convolutional Network for Dense Shape Correspondence

This paper studies 3D dense shape correspondence, a key shape analysis a...

Please sign up or login with your details

Forgot password? Click here to reset