Graph Matching with Bi-level Noisy Correspondence
This addresses a common issue in graph matching for computer vision applications, but it is incremental as it builds on existing contrastive learning and noisy correspondence handling techniques.
The paper tackles the problem of Bi-level Noisy Correspondence in graph matching, which involves node-level and edge-level mismatches due to annotation errors and viewpoint differences, and proposes a method called Contrastive Matching with Momentum Distillation that achieves robustness, as shown by extensive experiments outperforming 12 baselines on three real-world datasets.
In this paper, we study a novel and widely existing problem in graph matching (GM), namely, Bi-level Noisy Correspondence (BNC), which refers to node-level noisy correspondence (NNC) and edge-level noisy correspondence (ENC). In brief, on the one hand, due to the poor recognizability and viewpoint differences between images, it is inevitable to inaccurately annotate some keypoints with offset and confusion, leading to the mismatch between two associated nodes, i.e., NNC. On the other hand, the noisy node-to-node correspondence will further contaminate the edge-to-edge correspondence, thus leading to ENC. For the BNC challenge, we propose a novel method termed Contrastive Matching with Momentum Distillation. Specifically, the proposed method is with a robust quadratic contrastive loss which enjoys the following merits: i) better exploring the node-to-node and edge-to-edge correlations through a GM customized quadratic contrastive learning paradigm; ii) adaptively penalizing the noisy assignments based on the confidence estimated by the momentum teacher. Extensive experiments on three real-world datasets show the robustness of our model compared with 12 competitive baselines. The code is available at https://github.com/XLearning-SCU/2023-ICCV-COMMON.