RIPE: Reinforcement Learning on Unlabeled Image Pairs for Robust Keypoint Extraction
This addresses the need for robust keypoint extraction in computer vision with reduced data dependency, though it is incremental as it builds on existing weakly-supervised methods.
The paper tackles the problem of training keypoint extractors with minimal supervision by introducing RIPE, a reinforcement learning framework that uses only binary labels on image pairs, achieving competitive performance on standard benchmarks.
We introduce RIPE, an innovative reinforcement learning-based framework for weakly-supervised training of a keypoint extractor that excels in both detection and description tasks. In contrast to conventional training regimes that depend heavily on artificial transformations, pre-generated models, or 3D data, RIPE requires only a binary label indicating whether paired images represent the same scene. This minimal supervision significantly expands the pool of training data, enabling the creation of a highly generalized and robust keypoint extractor. RIPE utilizes the encoder's intermediate layers for the description of the keypoints with a hyper-column approach to integrate information from different scales. Additionally, we propose an auxiliary loss to enhance the discriminative capability of the learned descriptors. Comprehensive evaluations on standard benchmarks demonstrate that RIPE simplifies data preparation while achieving competitive performance compared to state-of-the-art techniques, marking a significant advancement in robust keypoint extraction and description. To support further research, we have made our code publicly available at https://github.com/fraunhoferhhi/RIPE.