TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK	REMOVE
Semantic correspondence	PF-PASCAL	ANCNet	PCK	88.7	# 11
Semantic correspondence	SPair-71k	ANCNet	PCK	30.1	# 17

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/correspondence-networks-with-adaptive/semantic-correspondence-on-pf-pascal)](https://paperswithcode.com/sota/semantic-correspondence-on-pf-pascal?p=correspondence-networks-with-adaptive)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/correspondence-networks-with-adaptive/semantic-correspondence-on-spair-71k)](https://paperswithcode.com/sota/semantic-correspondence-on-spair-71k?p=correspondence-networks-with-adaptive)`

Correspondence Networks with Adaptive Neighbourhood Consensus

CVPR 2020 · Shuda Li, Kai Han, Theo W. Costain, Henry Howard-Jenkins, Victor Prisacariu ·

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.