An Improved Learning Framework for Covariant Local Feature Detection
This work addresses the challenge of detecting stable and novel features in computer vision, which is incremental by building on prior learning formulations with covariant constraints.
The paper tackles the problem of learning covariant local feature detection, where existing methods either produce unstable features or rely on pre-determined handcrafted features, limiting novelty. The proposed method incorporates covariant constraints as triplets and an affine covariant constraint, achieving state-of-the-art repeatability scores on datasets like Vgg-Affine, EF, and Webcam.
Learning feature detection has been largely an unexplored area when compared to handcrafted feature detection. Recent learning formulations use the covariant constraint in their loss function to learn covariant detectors. However, just learning from covariant constraint can lead to detection of unstable features. To impart further, stability detectors are trained to extract pre-determined features obtained by hand-crafted detectors. However, in the process they lose the ability to detect novel features. In an attempt to overcome the above limitations, we propose an improved scheme by incorporating covariant constraints in form of triplets with addition to an affine covariant constraint. We show that using these additional constraints one can learn to detect novel and stable features without using pre-determined features for training. Extensive experiments show our model achieves state-of-the-art performance in repeatability score on the well known datasets such as Vgg-Affine, EF, and Webcam.