Top-DB-Net: Top DropBlock for Activation Enhancement in Person Re-Identification

TL;DR

Top-DB-Net introduces a novel Top DropBlock technique that enhances person re-identification by focusing on the most relevant regions and encoding low informative areas for improved discriminability, outperforming existing methods.

Contribution

The paper proposes Top-DB-Net, a multi-stream architecture utilizing Top DropBlock to improve focus on task-relevant regions in person re-identification tasks.

Findings

Outperforms state-of-the-art methods on three challenging datasets.

Produces activation maps focusing on reliable, discriminative parts of images.

Effectively encodes low informative regions to enhance discriminability.

Abstract

Person Re-Identification is a challenging task that aims to retrieve all instances of a query image across a system of non-overlapping cameras. Due to the various extreme changes of view, it is common that local regions that could be used to match people are suppressed, which leads to a scenario where approaches have to evaluate the similarity of images based on less informative regions. In this work, we introduce the Top-DB-Net, a method based on Top DropBlock that pushes the network to learn to focus on the scene foreground, with special emphasis on the most task-relevant regions and, at the same time, encodes low informative regions to provide high discriminability. The Top-DB-Net is composed of three streams: (i) a global stream encodes rich image information from a backbone, (ii) the Top DropBlock stream encourages the backbone to encode low informative regions with high discriminative features, and (iii) a regularization stream helps to deal with the noise created by the dropping process of the second stream, when testing the first two streams are used. Vast experiments on three challenging datasets show the capabilities of our approach against state-of-the-art methods. Qualitative results demonstrate that our method exhibits better activation maps focusing on reliable parts of the input images.