MIC: Mining Interclass Characteristics for Improved Metric Learning
This work addresses variability in image retrieval for computer vision applications, offering a novel approach to improve accuracy by disentangling cross-class characteristics.
The paper tackles the problem of metric learning for image retrieval by explicitly modeling latent visual characteristics shared across object classes, rather than treating them as noise, and achieves significant improvements over state-of-the-art methods on five standard benchmarks.
Metric learning seeks to embed images of objects suchthat class-defined relations are captured by the embeddingspace. However, variability in images is not just due to different depicted object classes, but also depends on other latent characteristics such as viewpoint or illumination. In addition to these structured properties, random noise further obstructs the visual relations of interest. The common approach to metric learning is to enforce a representation that is invariant under all factors but the ones of interest. In contrast, we propose to explicitly learn the latent characteristics that are shared by and go across object classes. We can then directly explain away structured visual variability, rather than assuming it to be unknown random noise. We propose a novel surrogate task to learn visual characteristics shared across classes with a separate encoder. This encoder is trained jointly with the encoder for class information by reducing their mutual information. On five standard image retrieval benchmarks the approach significantly improves upon the state-of-the-art.