Rethinking preventing class-collapsing in metric learning with margin-based losses
This addresses a specific issue in metric learning for fine-grained image retrieval, offering an incremental improvement over existing methods.
The paper tackles the problem of class collapse in metric learning with margin-based losses, where diverse intra-class samples collapse to a single point, and proposes a simple modification using nearest same-class sampling to preserve sub-clusters, resulting in improved performance on fine-grained image retrieval datasets.
Metric learning seeks perceptual embeddings where visually similar instances are close and dissimilar instances are apart, but learned representations can be sub-optimal when the distribution of intra-class samples is diverse and distinct sub-clusters are present. Although theoretically with optimal assumptions, margin-based losses such as the triplet loss and margin loss have a diverse family of solutions. We theoretically prove and empirically show that under reasonable noise assumptions, margin-based losses tend to project all samples of a class with various modes onto a single point in the embedding space, resulting in a class collapse that usually renders the space ill-sorted for classification or retrieval. To address this problem, we propose a simple modification to the embedding losses such that each sample selects its nearest same-class counterpart in a batch as the positive element in the tuple. This allows for the presence of multiple sub-clusters within each class. The adaptation can be integrated into a wide range of metric learning losses. The proposed sampling method demonstrates clear benefits on various fine-grained image retrieval datasets over a variety of existing losses; qualitative retrieval results show that samples with similar visual patterns are indeed closer in the embedding space.