Papers › LightTrack: Finding Lightweight Neural Networks for Object Tracking via One-Shot...

LightTrack: Finding Lightweight Neural Networks for Object Tracking via One-Shot Architecture Search

29 Apr 2021CVPR 2021 1arXiv:2104.14545archive 2025-07-28

Bin Yan, Houwen Peng, Kan Wu, Dong Wang, Jianlong Fu, Huchuan Lu

Object tracking has achieved significant progress over the past few years. However, state-of-the-art trackers become increasingly heavy and expensive, which limits their deployments in resource-constrained applications. In this work, we present LightTrack, which uses neural architecture search (NAS) to design more lightweight and efficient object trackers. Comprehensive experiments show that our LightTrack is effective. It can find trackers that achieve superior performance compared to handcrafted SOTA trackers, such as SiamRPN++ and Ocean, while using much fewer model Flops and parameters. Moreover, when deployed on resource-constrained mobile chipsets, the discovered trackers run much faster. For example, on Snapdragon 845 Adreno GPU, LightTrack runs 12× faster than Ocean, while using 13× fewer parameters and 38× fewer Flops. Such improvements might narrow the gap between academic models and industrial deployments in object tracking task. LightTrack is released at https://github.com/researchmm/LightTrack.

PaperPDFConference PDFCodeCode 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="2104.14545")

Code

Syntology Ran 7 of 7 code samples harvested from 1 repository linked to this paper; 0 have no recorded run. Of those that ran: 2 ran · honoured contract; 1 ran · our draft was wrong; 2 ran · fixture could not drive it; 2 ran with no contract checked.

By repository: official repository: 7 samples from 1 repository, 7 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

researchmm/LightTrack officialmentioned in papermentioned on GitHubpytorch 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

7 samples harvested; 7 ran; 2 honoured the contract we drafted; 0 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.

2ran · honoured contract
1ran · our draft was wrong
2ran · fixture could not drive it
2ran

Licence: 0 of the 7 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 researchmm/LightTrack. “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.

Config researchmm/LightTrack/lib/tracker/lighttrack.py official repository ran MIT (permissive) · a36dcbde2714611a · report
Lighttrack researchmm/LightTrack/lib/tracker/lighttrack.py official repository ran MIT (permissive) · bf42cff83b1cbcf3 · report
get_subwindow_tracking researchmm/LightTrack/lib/tracker/lighttrack.py official repository ran · fixture could not drive it fingerprinted MIT (permissive) · a5063c71c5931d27 · report
im_to_torch researchmm/LightTrack/lib/tracker/lighttrack.py official repository ran · fixture could not drive it fingerprinted MIT (permissive) · 25c9237afd263361 · report
load_yaml researchmm/LightTrack/lib/tracker/lighttrack.py official repository ran · our draft was wrong MIT (permissive) · 4b0995306a51fa38 · report
python2round researchmm/LightTrack/lib/tracker/lighttrack.py official repository ran · honoured contract fingerprinted MIT (permissive) · 80095723929304cb · report
to_torch researchmm/LightTrack/lib/tracker/lighttrack.py official repository ran · honoured contract MIT (permissive) · 516e33dfd5c4f7df · report

Tasks

Neural Architecture SearchObjectObject TrackingVideo Object Tracking

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Video Object Tracking NT-VOT211 LightTrack AUC 32.85 #27 of 43 Archive leaderboard report
Video Object Tracking NT-VOT211 LightTrack Precision 43.65 #27 of 43 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.

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