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

arXiv: https://arxiv.org/abs/2010.05435 · HTML: https://mlsanity.com/paper/2010.05435/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Oct 2020.

## Built on by (most cited first, 14 of 14)

- [Large-Scale Spatio-Temporal Person Re-identification: Algorithms and Benchmark](https://mlsanity.com/paper/2105.15076/) (2021)
- [Lightweight Multi-Branch Network for Person Re-Identification](https://mlsanity.com/paper/2101.10774/) (2021)
- [Graph Neural Networks for Cross-Camera Data Association](https://mlsanity.com/paper/2201.06311/) (2022)
- [Benchmarks for Corruption Invariant Person Re-identification](https://mlsanity.com/paper/2111.00880/) (2021)
- [Relation Preserving Triplet Mining for Stabilising the Triplet Loss in Re-identification Systems](https://mlsanity.com/paper/2110.07933/) (2021)
- [The Self-Optimal-Transport Feature Transform](https://mlsanity.com/paper/2204.03065/) (2022)
- [CLIP-ReIdent: Contrastive Training for Player Re-Identification](https://mlsanity.com/paper/2303.11855/) (2023)
- [Masked Attribute Description Embedding for Cloth-Changing Person Re-identification](https://mlsanity.com/paper/2401.05646/) (2024)
- [Disentangled Representations for Short-Term and Long-Term Person Re-Identification](https://mlsanity.com/paper/2409.05277/) (2024)
- [Combining human parsing with analytical feature extraction and ranking schemes for high-generalization person reidentification](https://mlsanity.com/paper/2207.14243/) (2022)
- [Enhancing Long-Term Person Re-Identification Using Global, Local Body Part, and Head Streams](https://mlsanity.com/paper/2403.02892/) (2024)
- [The Balanced-Pairwise-Affinities Feature Transform](https://mlsanity.com/paper/2407.01467/) (2024)
- [TSDW: A Tri-Stream Dynamic Weight Network for Cloth-Changing Person Re-Identification](https://mlsanity.com/paper/2503.00477/) (2025)
- [A review of Recent Techniques for Person Re-Identification](https://mlsanity.com/paper/2509.22690/) (2025)

## Abstract (arXiv)

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.