Correspondence Networks with Adaptive Neighbourhood Consensus
This work solves the problem of robust dense matching for computer vision applications, but it appears incremental as it builds on existing network architectures with specific modules.
The paper tackles dense visual correspondence between images of the same object category, addressing challenges like intra-class variations and lack of dense annotations, and reports that their method substantially outperforms state-of-the-art methods on various benchmarks.
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.