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

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

12 Oct 2020arXiv:2010.05435archive 2025-07-28

Rodolfo Quispe, Helio Pedrini

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.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2010.05435")

Code

Syntology Ran 0 of 15 code samples harvested from 1 repository linked to this paper; 15 have no recorded run.

By repository: official repository: 15 samples from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

RQuispeC/top-dropblock officialmentioned in papermentioned on GitHubpytorchMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

15 samples harvested; 0 ran; 0 honoured the contract we drafted; 15 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

15unverified

Licence: 0 of the 15 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from RQuispeC/top-dropblock. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

densenet121 RQuispeC/top-dropblock/torchreid/models/densenet.py official repository unverified MIT (permissive) · 6473856732e614c2 · report
densenet169 RQuispeC/top-dropblock/torchreid/models/densenet.py official repository unverified MIT (permissive) · e271cdd444e9c43d · report
densenet201 RQuispeC/top-dropblock/torchreid/models/densenet.py official repository unverified MIT (permissive) · 14ea88b72b8a45f3 · report
imagedata_kwargs RQuispeC/top-dropblock/default_config.py official repository unverified MIT (permissive) · 561c35d94c883194 · report
inceptionresnetv2 RQuispeC/top-dropblock/torchreid/models/inceptionresnetv2.py official repository unverified MIT (permissive) · 968ff7bf292adbec · report
inceptionresnetv2 RQuispeC/top-dropblock/torchreid/models/inceptionresnetv2.py official repository unverified MIT (permissive) · 0c2afba5ccb6bcc2 · report
inceptionv4 RQuispeC/top-dropblock/torchreid/models/inceptionv4.py official repository unverified MIT (permissive) · 2bcd3828691ac1d1 · report
mlfn RQuispeC/top-dropblock/torchreid/models/mlfn.py official repository unverified MIT (permissive) · b52023dd659c7a90 · report
mobilenetv2_x1_0 RQuispeC/top-dropblock/torchreid/models/mobilenetv2.py official repository unverified MIT (permissive) · 85b4bac4b8d2c9e4 · report
mobilenetv2_x1_4 RQuispeC/top-dropblock/torchreid/models/mobilenetv2.py official repository unverified MIT (permissive) · 92bf5ac4db6e8f28 · report
optimizer_kwargs RQuispeC/top-dropblock/default_config.py official repository unverified MIT (permissive) · d3e1b4b879ea0786 · report
top_bdnet_botdropfeat_doubot RQuispeC/top-dropblock/torchreid/models/bdnet.py official repository unverified MIT (permissive) · 745b2ecb6d17d120 · report
top_bdnet_doubot RQuispeC/top-dropblock/torchreid/models/bdnet.py official repository unverified MIT (permissive) · b423187d3a670707 · report
top_bdnet_neck_botdropfeat_doubot RQuispeC/top-dropblock/torchreid/models/bdnet.py official repository unverified MIT (permissive) · d3e058c65c930753 · report
videodata_kwargs RQuispeC/top-dropblock/default_config.py official repository unverified MIT (permissive) · 0951e0d511f67f90 · report

Tasks

Person Re-Identification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Person Re-Identification CUHK03 detected Top-DB-Net + RK MAP 86.9 #1 of 19 Archive leaderboard report
Person Re-Identification CUHK03 detected Top-DB-Net + RK Rank-1 85.7 #1 of 19 Archive leaderboard report
Person Re-Identification CUHK03 detected Top-DB-Net MAP 74.2 #8 of 19 Archive leaderboard report
Person Re-Identification CUHK03 detected Top-DB-Net Rank-1 77.3 #8 of 19 Archive leaderboard report
Person Re-Identification CUHK03 labeled Top-DB-Net + RK MAP 88.5 #2 of 21 Archive leaderboard report
Person Re-Identification CUHK03 labeled Top-DB-Net + RK Rank-1 86.7 #2 of 21 Archive leaderboard report
Person Re-Identification CUHK03 labeled Top-DB-Net MAP 75.4 #11 of 21 Archive leaderboard report
Person Re-Identification CUHK03 labeled Top-DB-Net Rank-1 79.4 #11 of 21 Archive leaderboard report
Person Re-Identification DukeMTMC-reID Top-DB-Net + RK Rank-1 90.9 #16 of 94 Archive leaderboard report
Person Re-Identification DukeMTMC-reID Top-DB-Net + RK mAP 88.6 #16 of 94 Archive leaderboard report
Person Re-Identification DukeMTMC-reID Top-DB-Net Rank-1 87.5 #62 of 94 Archive leaderboard report
Person Re-Identification DukeMTMC-reID Top-DB-Net mAP 73.5 #62 of 94 Archive leaderboard report
Person Re-Identification Market-1501 Top-DB-Net + RK Rank-1 95.5 #53 of 135 Archive leaderboard report
Person Re-Identification Market-1501 Top-DB-Net + RK mAP 94.1 #53 of 135 Archive leaderboard report
Person Re-Identification Market-1501 Top-DB-Net Rank-1 94.9 #72 of 135 Archive leaderboard report
Person Re-Identification Market-1501 Top-DB-Net mAP 85.8 #72 of 135 Archive leaderboard report
Person Re-Identification Market-1501-C TDB Rank-1 28.56 #18 of 22 Archive leaderboard report
Person Re-Identification Market-1501-C TDB mAP 8.90 #18 of 22 Archive leaderboard report
Person Re-Identification Market-1501-C TDB mINP 0.20 #18 of 22 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

DropBlock

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections