Papers › Less is More: Focus Attention for Efficient DETR

Less is More: Focus Attention for Efficient DETR

24 Jul 2023ICCV 2023 1arXiv:2307.12612archive 2025-07-28

Dehua Zheng, Wenhui Dong, Hailin Hu, Xinghao Chen, Yunhe Wang

DETR-like models have significantly boosted the performance of detectors and even outperformed classical convolutional models. However, all tokens are treated equally without discrimination brings a redundant computational burden in the traditional encoder structure. The recent sparsification strategies exploit a subset of informative tokens to reduce attention complexity maintaining performance through the sparse encoder. But these methods tend to rely on unreliable model statistics. Moreover, simply reducing the token population hinders the detection performance to a large extent, limiting the application of these sparse models. We propose Focus-DETR, which focuses attention on more informative tokens for a better trade-off between computation efficiency and model accuracy. Specifically, we reconstruct the encoder with dual attention, which includes a token scoring mechanism that considers both localization and category semantic information of the objects from multi-scale feature maps. We efficiently abandon the background queries and enhance the semantic interaction of the fine-grained object queries based on the scores. Compared with the state-of-the-art sparse DETR-like detectors under the same setting, our Focus-DETR gets comparable complexity while achieving 50.4AP (+2.2) on COCO. The code is available at https://github.com/huawei-noah/noah-research/tree/master/Focus-DETR and https://gitee.com/mindspore/models/tree/master/research/cv/Focus-DETR.

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="2307.12612")

Code

Syntology Ran 0 of 12 code samples harvested from 1 repository linked to this paper; 12 have no recorded run.

By repository: community (archive-listed): 12 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.

huawei-noah/noah-research officialmentioned in paperpytorch report
linxid/Focus-DETR mentioned on GitHubmindsporeApache-2.0 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

12 samples harvested; 0 ran; 0 honoured the contract we drafted; 12 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.

12unverified

Licence: 0 of the 12 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 linxid/Focus-DETR. “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.

area_box_grad linxid/Focus-DETR/models/focus_detr/grad_ops.py community (archive-listed) unverified Apache-2.0 (permissive) · 439ca3d20ddd3507 · report
box_cxcywh_to_xyxy linxid/Focus-DETR/models/focus_detr/box_ops.py community (archive-listed) unverified Apache-2.0 (permissive) · 074307e51146fa09 · report
box_xyxy_to_cxcywh linxid/Focus-DETR/models/focus_detr/box_ops.py community (archive-listed) unverified Apache-2.0 (permissive) · dbb0d0f90ff599c4 · report
box_xyxy_to_xywh linxid/Focus-DETR/models/focus_detr/box_ops.py community (archive-listed) unverified Apache-2.0 (permissive) · c7dc3cdd056cc5f7 · report
crop linxid/Focus-DETR/models/focus_detr/transforms.py community (archive-listed) unverified Apache-2.0 (permissive) · 3a961927a8349cc0 · report
dres_dwh linxid/Focus-DETR/models/focus_detr/grad_ops.py community (archive-listed) unverified Apache-2.0 (permissive) · f111786e2550d75b · report
grad_xywh_to_cxcy linxid/Focus-DETR/models/focus_detr/grad_ops.py community (archive-listed) unverified Apache-2.0 (permissive) · b825001fb2f9656b · report
hflip linxid/Focus-DETR/models/focus_detr/transforms.py community (archive-listed) unverified Apache-2.0 (permissive) · 3489d75749a692fb · report
merge linxid/Focus-DETR/models/focus_detr/coco_eval.py community (archive-listed) unverified Apache-2.0 (permissive) · 13cebdd9482d0683 · report
pad_image_to_max_size linxid/Focus-DETR/models/focus_detr/dataset.py community (archive-listed) unverified Apache-2.0 (permissive) · 5a86d23535474849 · report
prepare_data linxid/Focus-DETR/models/focus_detr/dataset.py community (archive-listed) unverified Apache-2.0 (permissive) · b7a71f5fa31b5a46 · report
resize linxid/Focus-DETR/models/focus_detr/transforms.py community (archive-listed) unverified Apache-2.0 (permissive) · fbb85c3da476c722 · report

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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