Joint Learning of Feature Extraction and Cost Aggregation for Semantic Correspondence

TL;DR

This paper introduces a joint learning framework for feature extraction and cost aggregation in semantic correspondence, improving performance by leveraging pseudo labels and a confidence-aware contrastive loss.

Contribution

It proposes a novel joint learning approach with a boosting strategy and confidence-aware loss, addressing limitations of previous independent methods.

Findings

Achieved competitive results on standard semantic correspondence benchmarks.

Demonstrated effectiveness of joint learning over separate modules.

Validated the robustness of the confidence-aware contrastive loss.

Abstract

Establishing dense correspondences across semantically similar images is one of the challenging tasks due to the significant intra-class variations and background clutters. To solve these problems, numerous methods have been proposed, focused on learning feature extractor or cost aggregation independently, which yields sub-optimal performance. In this paper, we propose a novel framework for jointly learning feature extraction and cost aggregation for semantic correspondence. By exploiting the pseudo labels from each module, the networks consisting of feature extraction and cost aggregation modules are simultaneously learned in a boosting fashion. Moreover, to ignore unreliable pseudo labels, we present a confidence-aware contrastive loss function for learning the networks in a weakly-supervised manner. We demonstrate our competitive results on standard benchmarks for semantic correspondence.