Papers › TransNAS-Bench-101: Improving Transferability and Generalizability of Cross-Task...

TransNAS-Bench-101: Improving Transferability and Generalizability of Cross-Task Neural Architecture Search

25 May 2021CVPR 2021 1arXiv:2105.11871archive 2025-07-28

Yawen Duan, Xin Chen, Hang Xu, Zewei Chen, Xiaodan Liang, Tong Zhang, Zhenguo Li

Recent breakthroughs of Neural Architecture Search (NAS) extend the field's research scope towards a broader range of vision tasks and more diversified search spaces. While existing NAS methods mostly design architectures on a single task, algorithms that look beyond single-task search are surging to pursue a more efficient and universal solution across various tasks. Many of them leverage transfer learning and seek to preserve, reuse, and refine network design knowledge to achieve higher efficiency in future tasks. However, the enormous computational cost and experiment complexity of cross-task NAS are imposing barriers for valuable research in this direction. Existing NAS benchmarks all focus on one type of vision task, i.e., classification. In this work, we propose TransNAS-Bench-101, a benchmark dataset containing network performance across seven tasks, covering classification, regression, pixel-level prediction, and self-supervised tasks. This diversity provides opportunities to transfer NAS methods among tasks and allows for more complex transfer schemes to evolve. We explore two fundamentally different types of search space: cell-level search space and macro-level search space. With 7,352 backbones evaluated on seven tasks, 51,464 trained models with detailed training information are provided. With TransNAS-Bench-101, we hope to encourage the advent of exceptional NAS algorithms that raise cross-task search efficiency and generalizability to the next level. Our dataset file will be available at Mindspore, VEGA.

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="2105.11871")

Code

Syntology Ran 0 of 9 code samples harvested from 1 repository linked to this paper; 9 have no recorded run.

By repository: community (archive-listed): 9 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.

Edge-AI-Acceleration-Lab/RBFleX-NAS mentioned on GitHubpytorch report
kmdanielduan/TransNASBench mentioned on GitHubpytorchMIT report
tomomasayamasaki/RBFleX-NAS mentioned on GitHubpytorch report
yawen-d/transnasbench mentioned 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

9 samples harvested; 0 ran; 0 honoured the contract we drafted; 9 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.

9unverified

Licence: 0 of the 9 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 kmdanielduan/TransNASBench. “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.

classification kmdanielduan/TransNASBench/lib/procedures/task_vis.py community (archive-listed) unverified MIT (permissive) · e6683d2088f920e6 · report
get_confusion_matrix kmdanielduan/TransNASBench/lib/models/utils.py community (archive-listed) unverified MIT (permissive) · 5842dd066c74c704 · report
get_flops kmdanielduan/TransNASBench/lib/models/model_info.py community (archive-listed) unverified MIT (permissive) · da484d75b643a432 · report
get_inference_time kmdanielduan/TransNASBench/lib/models/model_info.py community (archive-listed) unverified MIT (permissive) · 8629889d5612c287 · report
get_params kmdanielduan/TransNASBench/lib/models/model_info.py community (archive-listed) unverified MIT (permissive) · a8ddf8c8aed9b1bc · report
get_topk_acc kmdanielduan/TransNASBench/lib/models/utils.py community (archive-listed) unverified MIT (permissive) · a3a03882516092f5 · report
merge_list kmdanielduan/TransNASBench/lib/models/utils.py community (archive-listed) unverified MIT (permissive) · f1eae5bb66aa2d1b · report
set_img_color kmdanielduan/TransNASBench/lib/procedures/task_vis.py community (archive-listed) unverified MIT (permissive) · a3fc3801fa7b9bb4 · report
tensor2np_img kmdanielduan/TransNASBench/lib/procedures/task_vis.py community (archive-listed) unverified MIT (permissive) · 2ee061ffaae87c15 · report

Tasks

Neural Architecture SearchTransfer Learning

Datasets

Introduced by this paper, per the archive.

TransNAS-Bench-101

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

VEGA

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