Correspondence Networks with Adaptive Neighbourhood Consensus

03/26/2020
by   Shuda Li, et al.
0

In this paper, we tackle the task of establishing dense visual correspondences between images containing objects of the same category. This is a challenging task due to large intra-class variations and a lack of dense pixel level annotations. We propose a convolutional neural network architecture, called adaptive neighbourhood consensus network (ANC-Net), that can be trained end-to-end with sparse key-point annotations, to handle this challenge. At the core of ANC-Net is our proposed non-isotropic 4D convolution kernel, which forms the building block for the adaptive neighbourhood consensus module for robust matching. We also introduce a simple and efficient multi-scale self-similarity module in ANC-Net to make the learned feature robust to intra-class variations. Furthermore, we propose a novel orthogonal loss that can enforce the one-to-one matching constraint. We thoroughly evaluate the effectiveness of our method on various benchmarks, where it substantially outperforms state-of-the-art methods.

READ FULL TEXT

page 2

page 8

research
10/24/2018

Neighbourhood Consensus Networks

We address the problem of finding reliable dense correspondences between...
research
12/19/2017

End-to-end weakly-supervised semantic alignment

We tackle the task of semantic alignment where the goal is to compute de...
research
03/31/2021

Convolutional Hough Matching Networks

Despite advances in feature representation, leveraging geometric relatio...
research
07/31/2021

Multi-scale Matching Networks for Semantic Correspondence

Deep features have been proven powerful in building accurate dense seman...
research
08/06/2023

Local Consensus Enhanced Siamese Network with Reciprocal Loss for Two-view Correspondence Learning

Recent studies of two-view correspondence learning usually establish an ...
research
09/03/2020

Tasks Integrated Networks: Joint Detection and Retrieval for Image Search

The traditional object retrieval task aims to learn a discriminative fea...
research
09/11/2021

Convolutional Hough Matching Networks for Robust and Efficient Visual Correspondence

Despite advances in feature representation, leveraging geometric relatio...

Please sign up or login with your details

Forgot password? Click here to reset