Papers › Salience DETR: Enhancing Detection Transformer with Hierarchical Salience Filtering Refinement

Salience DETR: Enhancing Detection Transformer with Hierarchical Salience Filtering Refinement

24 Mar 2024CVPR 2024 1arXiv:2403.16131archive 2025-07-28

Xiuquan Hou, Meiqin Liu, Senlin Zhang, Ping Wei, Badong Chen

DETR-like methods have significantly increased detection performance in an end-to-end manner. The mainstream two-stage frameworks of them perform dense self-attention and select a fraction of queries for sparse cross-attention, which is proven effective for improving performance but also introduces a heavy computational burden and high dependence on stable query selection. This paper demonstrates that suboptimal two-stage selection strategies result in scale bias and redundancy due to the mismatch between selected queries and objects in two-stage initialization. To address these issues, we propose hierarchical salience filtering refinement, which performs transformer encoding only on filtered discriminative queries, for a better trade-off between computational efficiency and precision. The filtering process overcomes scale bias through a novel scale-independent salience supervision. To compensate for the semantic misalignment among queries, we introduce elaborate query refinement modules for stable two-stage initialization. Based on above improvements, the proposed Salience DETR achieves significant improvements of +4.0% AP, +0.2% AP, +4.4% AP on three challenging task-specific detection datasets, as well as 49.2% AP on COCO 2017 with less FLOPs. The code is available at https://github.com/xiuqhou/Salience-DETR.

PaperPDFConference PDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 23 code samples harvested from 3 repositories linked to this paper: 11 ran (of which 6 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 0 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 12 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 13 samples from 1 repository, 6 ran (3 with no instrument failure; 3 where Syntology's instrument failed); community (archive-listed): 10 samples from 2 repositories, 5 ran (5 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

xiuqhou/Salience-DETR officialmentioned in papermentioned on GitHubpytorchSyntology: 13 samples, 6 ran (3 instrument-failed) · 7 unverified report
xiuqhou/relation-detr mentioned on GitHubpytorchSyntology: 5 samples, 4 ran (0 instrument-failed) · 1 unverified report
xunull/read-Salience-DETR mentioned on GitHubpytorchSyntology: 5 samples, 1 ran (0 instrument-failed) · 4 unverified 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

23 samples harvested: 11 ran (of which 6 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 0 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 12 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · honoured contract
3ran · our draft was wrong
6ran
12unverified

Licence: 0 of the 23 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 3 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. For 1 sample that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

xiuqhou/Salience-DETR official repository 13 samples, 6 ran (3 instrument-failed) · 7 unverified
EvalResize models/detectors/salience_detr.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 88c02c4fc776a779 · report fixture: returned EvalResize · level recorded 2026-09-22
GenerateDNQueries models/detectors/salience_detr.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 5d857e337ecf6a8a · report fixture: returned GenerateDNQueries · level recorded 2026-09-22
decode_labels models/detectors/salience_detr.py ran · our draft was wrong Apache-2.0 (permissive) · 0b3cdeb3b0b05c06 · report fixture: signature ints:tuple/1/int · returned list · level recorded 2026-09-22
encode_labels in 6 papers models/detectors/salience_detr.py ran · honoured contract Apache-2.0 (permissive) · d088164a46bf049d · report fixture: signature labels:tuple/1/str · returned list · level recorded 2026-09-22
image_list_from_tensors models/detectors/salience_detr.py ran · our draft was wrong Apache-2.0 (permissive) · d4dcad186c11cc6e · report fixture: signature images:list/1/Tensor, size_divisible:int/0/int, fill_value:int/0/int · returned ImageList · level recorded 2026-09-22
inverse_sigmoid in 80 papers
census: 9 implementations from 14 papers, 5 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 2, kind float, dtype float32
models/detectors/salience_detr.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 24d843af1035723e · report fixture: signature x:Tensor/2/float, eps:float/0/float · returned Tensor · level recorded 2026-09-22
BaseDetector in 8 papers models/detectors/salience_detr.py unverified Apache-2.0 (permissive) · b6ec17c5de8153f5 · report
DETRDetector models/detectors/salience_detr.py unverified Apache-2.0 (permissive) · 8d8d14c400dc9048 · report
DNDETRDetector models/detectors/salience_detr.py unverified Apache-2.0 (permissive) · e08e50fcf0e7c2e7 · report
GenerateCDNQueries models/detectors/salience_detr.py unverified Apache-2.0 (permissive) · 8806364b547cbe2c · report
InterpolationMode models/detectors/salience_detr.py unverified Apache-2.0 (permissive) · 3b967208a4a214e1 · report
SalienceDETR models/detectors/salience_detr.py unverified Apache-2.0 (permissive) · 5127f19798539444 · report
_onnx_batch_images models/detectors/salience_detr.py unverified Apache-2.0 (permissive) · 974577b98ac3356d · report
xiuqhou/relation-detr community (archive-listed) 5 samples, 4 ran (0 instrument-failed) · 1 unverified
DETRBaseTransformer models/bricks/relation_transformer.py ran Apache-2.0 (permissive) · e54def49272a77fb · report fixture: returned DETRBaseTransformer · level recorded 2026-09-22
MLP in 375 papers models/bricks/relation_transformer.py ran Apache-2.0 (permissive) · 26df4273ae94b72a · report fixture: returned MLP · level recorded 2026-09-22
MultiLevelTransformer models/bricks/relation_transformer.py ran Apache-2.0 (permissive) · f4b996d811277585 · report fixture: returned MultiLevelTransformer · level recorded 2026-09-22
TwostageTransformer models/bricks/relation_transformer.py ran Apache-2.0 (permissive) · 8d39466be24010f8 · report fixture: returned TwostageTransformer · level recorded 2026-09-22
RelationTransformer models/bricks/relation_transformer.py unverified Apache-2.0 (permissive) · 4b9d0e934f46f9fd · report
xunull/read-Salience-DETR community (archive-listed) 5 samples, 1 ran (0 instrument-failed) · 4 unverified
encode_labels in 6 papers models/detectors/salience_detr.py ran · honoured contract Apache-2.0 (permissive) · 4350a1d28ee65b0a · report fixture: signature labels:tuple/1/str · returned list · level recorded 2026-09-22
BaseDetector in 8 papers models/detectors/salience_detr.py unverified Apache-2.0 (permissive) · b9d6e114bdfb48b5 · report
DETRDetector models/detectors/salience_detr.py unverified Apache-2.0 (permissive) · b452573f88203f9d · report
DNDETRDetector models/detectors/salience_detr.py unverified Apache-2.0 (permissive) · 4b6a428989977191 · report
SalienceDETR models/detectors/salience_detr.py unverified Apache-2.0 (permissive) · 7325ee0427e649c0 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.

3 assemblies on this paper: 3 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

3 sibling assemblies for Salience DETR (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for Salience DETR (graph method: Salience DETR). 15 bricks; individually on a fixture: 8 ran (of which 2 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified. The assembly has not been run end-to-end.

one of 3 siblings

  1. SalienceDETR entry · level 0 · unverified · 5127f19798539444
  2. DNDETRDetector helper · level 0 · unverified · e08e50fcf0e7c2e7
  3. GenerateCDNQueries helper · level 0 · unverified · 8806364b547cbe2c
  4. DETRDetector helper · level 0 · unverified · 8d8d14c400dc9048
  5. get_world_size helper · level 1 · ran · c9d133b7656f2129
  6. is_dist_avail_and_initialized helper · level 1 · ran · 5f205488cb7b9004
  7. GenerateDNQueries helper · level 1 · ran · 5d857e337ecf6a8a
  8. inverse_sigmoid helper · level 1 · ran · our draft was wrong · 24d843af1035723e
  9. BaseDetector helper · level 0 · unverified · b6ec17c5de8153f5
  10. EvalResize helper · level 1 · ran · 88c02c4fc776a779
  11. decode_labels helper · level 1 · ran · our draft was wrong · 0b3cdeb3b0b05c06
  12. encode_labels helper · level 1 · ran · honoured contract · d088164a46bf049d
  13. image_list_from_tensors helper · level 1 · ran · our draft was wrong · d4dcad186c11cc6e
  14. InterpolationMode helper · level 0 · unverified · 3b967208a4a214e1
  15. _onnx_batch_images helper · level 0 · unverified · 974577b98ac3356d

harvested Assembly for Salience DETR (graph method: Salience DETR). 5 bricks; individually on a fixture: 4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 4 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 3 siblings

  1. RelationTransformer entry · level 0 · unverified · 4b9d0e934f46f9fd
  2. MLP helper · level 1 · ran · 26df4273ae94b72a
  3. TwostageTransformer helper · level 1 · ran · 8d39466be24010f8
  4. MultiLevelTransformer helper · level 1 · ran · f4b996d811277585
  5. DETRBaseTransformer helper · level 1 · ran · e54def49272a77fb

harvested Assembly for Salience DETR (graph method: Salience DETR). 15 bricks; individually on a fixture: 8 ran (of which 2 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified. The assembly has not been run end-to-end.

one of 3 siblings

  1. SalienceDETR entry · level 0 · unverified · 7325ee0427e649c0
  2. DNDETRDetector helper · level 0 · unverified · 4b6a428989977191
  3. GenerateCDNQueries helper · level 0 · unverified · 8806364b547cbe2c
  4. DETRDetector helper · level 0 · unverified · b452573f88203f9d
  5. get_world_size helper · level 1 · ran · c9d133b7656f2129
  6. is_dist_avail_and_initialized helper · level 1 · ran · 5f205488cb7b9004
  7. GenerateDNQueries helper · level 1 · ran · 5d857e337ecf6a8a
  8. inverse_sigmoid helper · level 1 · ran · our draft was wrong · 24d843af1035723e
  9. BaseDetector helper · level 0 · unverified · b9d6e114bdfb48b5
  10. EvalResize helper · level 1 · ran · 88c02c4fc776a779
  11. decode_labels helper · level 1 · ran · our draft was wrong · 0b3cdeb3b0b05c06
  12. encode_labels helper · level 1 · ran · honoured contract · 4350a1d28ee65b0a
  13. image_list_from_tensors helper · level 1 · ran · our draft was wrong · d4dcad186c11cc6e
  14. InterpolationMode helper · level 0 · unverified · 3b967208a4a214e1
  15. _onnx_batch_images helper · level 0 · unverified · 974577b98ac3356d

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2403.16131") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

2D Object DetectionComputational EfficiencyDense Object DetectionObject Detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Object Detection COCO 2017 val Salience-DETR (Focal-L 1x) AP 57.3 #6 of 33 Archive leaderboard report
Object Detection COCO 2017 val Salience-DETR (Focal-L 1x) AP50 75.5 #6 of 33 Archive leaderboard report
Object Detection COCO 2017 val Salience-DETR (Focal-L 1x) AP75 62.3 #6 of 33 Archive leaderboard report
Object Detection COCO 2017 val Salience-DETR (Focal-L 1x) APL 74.5 #6 of 33 Archive leaderboard report
Object Detection COCO 2017 val Salience-DETR (Focal-L 1x) APM 61.8 #6 of 33 Archive leaderboard report
Object Detection COCO 2017 val Salience-DETR (Focal-L 1x) APS 40.9 #6 of 33 Archive leaderboard report
Object Detection COCO 2017 val Salience-DETR (Focal-L 1x) Param. 220M #6 of 33 Archive leaderboard report
Object Detection COCO 2017 val Salience-DETR (Swin-L 1x) AP 56.5 #8 of 33 Archive leaderboard report
Object Detection COCO 2017 val Salience-DETR (Swin-L 1x) AP50 75.0 #8 of 33 Archive leaderboard report
Object Detection COCO 2017 val Salience-DETR (Swin-L 1x) AP75 61.5 #8 of 33 Archive leaderboard report
Object Detection COCO 2017 val Salience-DETR (Swin-L 1x) APL 72.8 #8 of 33 Archive leaderboard report
Object Detection COCO 2017 val Salience-DETR (Swin-L 1x) APM 61.2 #8 of 33 Archive leaderboard report
Object Detection COCO 2017 val Salience-DETR (Swin-L 1x) APS 40.2 #8 of 33 Archive leaderboard report
Object Detection COCO 2017 val Salience-DETR (Swin-L 1x) Param. 210M #8 of 33 Archive leaderboard report
Object Detection COCO 2017 val Salience-DETR (ResNet50 1x) AP 50.0 #16 of 33 Archive leaderboard report
Object Detection COCO 2017 val Salience-DETR (ResNet50 1x) AP50 67.7 #16 of 33 Archive leaderboard report
Object Detection COCO 2017 val Salience-DETR (ResNet50 1x) AP75 54.2 #16 of 33 Archive leaderboard report
Object Detection COCO 2017 val Salience-DETR (ResNet50 1x) APL 64.4 #16 of 33 Archive leaderboard report
Object Detection COCO 2017 val Salience-DETR (ResNet50 1x) APM 54.4 #16 of 33 Archive leaderboard report
Object Detection COCO 2017 val Salience-DETR (ResNet50 1x) APS 33.3 #16 of 33 Archive leaderboard report
Object Detection COCO 2017 val Salience-DETR (ResNet50 1x) Param. 56M #16 of 33 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

Absolute Position EncodingsAdamAttentionBPEConvolutionDense ConnectionsDetrDropoutFeedforward NetworkLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

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