Multimodal-Aware Weakly Supervised Metric Learning with Self-weighting Triplet Loss
This work provides an incremental improvement for researchers and practitioners working on weakly supervised metric learning, especially in scenarios with multimodal data distributions.
This paper addresses the challenge of learning distance metrics from weakly supervised data, particularly when datasets exhibit multimodal distributions. The authors propose MDaML, a method that partitions data into clusters, allocates local cluster centers and weights, and uses a weighted triplet loss to enhance local separability. They cast the metric learning problem as an unconstrained optimization on the SPD manifold, solving it efficiently with Riemannian Conjugate Gradient Descent.
In recent years, we have witnessed a surge of interests in learning a suitable distance metric from weakly supervised data. Most existing methods aim to pull all the similar samples closer while push the dissimilar ones as far as possible. However, when some classes of the dataset exhibit multimodal distribution, these goals conflict and thus can hardly be concurrently satisfied. Additionally, to ensure a valid metric, many methods require a repeated eigenvalue decomposition process, which is expensive and numerically unstable. Therefore, how to learn an appropriate distance metric from weakly supervised data remains an open but challenging problem. To address this issue, in this paper, we propose a novel weakly supervised metric learning algorithm, named MultimoDal Aware weakly supervised Metric Learning (MDaML). MDaML partitions the data space into several clusters and allocates the local cluster centers and weight for each sample. Then, combining it with the weighted triplet loss can further enhance the local separability, which encourages the local dissimilar samples to keep a large distance from the local similar samples. Meanwhile, MDaML casts the metric learning problem into an unconstrained optimization on the SPD manifold, which can be efficiently solved by Riemannian Conjugate Gradient Descent (RCGD). Extensive experiments conducted on 13 datasets validate the superiority of the proposed MDaML.