SDGMNet: Statistic-based Dynamic Gradient Modulation for Local Descriptor Learning
This work addresses a domain-specific problem in computer vision for researchers and practitioners working on local descriptor learning, offering incremental improvements over existing gradient modulation methods.
The paper tackled the problem of static gradient modulation strategies in triplet loss for local descriptor learning by proposing SDGMNet, a dynamic gradient modulation method based on statistical characteristics, which achieved state-of-the-art results on standard benchmarks for patch verification, matching, and retrieval tasks.
Modifications on triplet loss that rescale the back-propagated gradients of special pairs have made significant progress on local descriptor learning. However, current gradient modulation strategies are mainly static so that they would suffer from changes of training phases or datasets. In this paper, we propose a dynamic gradient modulation, named SDGMNet, to improve triplet loss for local descriptor learning. The core of our method is formulating modulation functions with statistical characteristics which are estimated dynamically. Firstly, we perform deep analysis on back propagation of general triplet-based loss and introduce included angle for distance measure. On this basis, auto-focus modulation is employed to moderate the impact of statistically uncommon individual pairs in stochastic gradient descent optimization; probabilistic margin cuts off the gradients of proportional Siamese pairs that are believed to reach the optimum; power adjustment balances the total weights of negative pairs and positive pairs. Extensive experiments demonstrate that our novel descriptor surpasses previous state-of-the-arts on standard benchmarks including patch verification, matching and retrieval tasks.