SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · Chen_Recurrent_Glimpse-Based_Decoder_for_Detection_With_Transformer_CVPR_2022_paper · CVPR · 2022

Recurrent Glimpse-based Decoder for Detection with Transformer

Dacheng Tao, Jing Zhang, Zhe Chen

Open in the Atlas

Code that ran

5 of 7 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 1 violated it and 0 have no contract verdict; 3 failures of our instrument; 2 no recorded run), measured 2026-11-22; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/Chen_Recurrent_Glimpse-Based_Decoder_for_Detection_With_Transformer_CVPR_2022_paper.json · badge: /api/ran/Chen_Recurrent_Glimpse-Based_Decoder_for_Detection_With_Transformer_CVPR_2022_paper.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
zhechen/Deformable-DETR-REGO canonical (classifier label)
classifier basis: census
5 ran · 2 no recorded run
FunctionStatusWhere it lives
convert_to_xywh Ran
ran, honoured the contract we drafted
zhechen/Deformable-DETR-REGO/datasets/coco_eval.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from yuhangzang/contextdet, is pointer only (licence: NOASSERTION) · get_code("f31a58bf6457ced5")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, zhechen/Deformable-DETR-REGO, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

dice_loss Ran
ran, violated the contract we drafted
zhechen/Deformable-DETR-REGO/models/segmentation.py
pointer only (licence: Apache-2.0) · get_code("ac8fe530cdad4d8c")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, zhechen/Deformable-DETR-REGO, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

evaluate Ran
ran; our contract draft was wrong, not the code
zhechen/Deformable-DETR-REGO/datasets/coco_eval.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from yuhangzang/contextdet, is pointer only (licence: NOASSERTION) · get_code("fe0ddcc2d420c9a0")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, zhechen/Deformable-DETR-REGO, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

measure_average_inference_time Ran
ran; our contract draft was wrong, not the code
zhechen/Deformable-DETR-REGO/benchmark.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from CAMMA-public/OR_anonymization, is pointer only (licence: NOASSERTION) · get_code("3e5d34f155e97585")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, zhechen/Deformable-DETR-REGO, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

sigmoid_focal_loss Ran
ran; our contract draft was wrong, not the code
zhechen/Deformable-DETR-REGO/models/segmentation.py
pointer only (licence: Apache-2.0) · get_code("5c0711aada67957e")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, zhechen/Deformable-DETR-REGO, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

build_glimpse_transformer Not yet run
unverified (harvested, no recorded run)
zhechen/Deformable-DETR-REGO/models/transformer.py
pointer only (licence: Apache-2.0) · get_code("401163776066b2b6")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, zhechen/Deformable-DETR-REGO, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

build_transformer Not yet run
unverified (harvested, no recorded run)
zhechen/Deformable-DETR-REGO/models/transformer.py
pointer only (licence: Apache-2.0) · get_code("e4cf3178d4a1e4c0")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, zhechen/Deformable-DETR-REGO, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 6 are also present in other papers whose code we hold (6 with at least one paper dated earlier, 0 the same month, 6 later) and 1 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
sigmoid_focal_loss 56 other papers
11 dated earlier, 34 later, 11 same year, order not determinable · 1 only as an assembly brick
2005.12872 (2020-05)
End-to-End Object Detection with Transformers
2010.04159 (2020-10)
Deformable DETR: Deformable Transformers for End-to-End Object Detection
2103.11731 (2021-03)
Meta-DETR: Image-Level Few-Shot Object Detection with Inter-Class Correlation Exploitation
and 53 more not named here
dice_loss 40 other papers
9 dated earlier, 21 later, 10 same year, order not determinable · 1 only as an assembly brick
2005.12872 (2020-05)
End-to-End Object Detection with Transformers
2010.04159 (2020-10)
Deformable DETR: Deformable Transformers for End-to-End Object Detection
2103.12115 (2021-03)
End-to-End Trainable Multi-Instance Pose Estimation with Transformers
and 37 more not named here
build_transformer 32 other papers
12 dated earlier, 18 later, 2 same year, order not determinable
2005.12872 (2020-05)
End-to-End Object Detection with Transformers
2103.12115 (2021-03)
End-to-End Trainable Multi-Instance Pose Estimation with Transformers
2104.04369 (2021-04)
Video-aided Unsupervised Grammar Induction
and 29 more not named here
convert_to_xywh 24 other papers
8 dated earlier, 12 later, 4 same year, order not determinable
1512.02325 (2015-12)
SSD: Single Shot MultiBox Detector
2010.04159 (2020-10)
Deformable DETR: Deformable Transformers for End-to-End Object Detection
2103.11731 (2021-03)
Meta-DETR: Image-Level Few-Shot Object Detection with Inter-Class Correlation Exploitation
and 21 more not named here
evaluate 23 other papers
8 dated earlier, 12 later, 3 same year, order not determinable
1512.02325 (2015-12)
SSD: Single Shot MultiBox Detector
2010.04159 (2020-10)
Deformable DETR: Deformable Transformers for End-to-End Object Detection
2103.11731 (2021-03)
Meta-DETR: Image-Level Few-Shot Object Detection with Inter-Class Correlation Exploitation
and 20 more not named here
measure_average_inference_time 10 other papers
2 dated earlier, 4 later, 4 same year, order not determinable
2010.04159 (2020-10)
Deformable DETR: Deformable Transformers for End-to-End Object Detection
2106.04550 (2021-06)
DETReg: Unsupervised Pretraining with Region Priors for Object Detection
ijcai2022_0136 (2022 (year only))
AQT: Adversarial Query Transformers for Domain Adaptive Object Detection
and 7 more not named here

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Although detection with Transformer (DETR) is increasingly popular, its global attention modeling requires an extremely long training period to optimize and achieve promising detection performance. Alternative to existing studies that mainly develop advanced feature or embedding designs to tackle the training issue, we point out that the Region-of-Interest (RoI) based detection refinement can easily help mitigate the difficulty of training for DETR methods. Based on this, we introduce a novel REcurrent Glimpse-based decOder (REGO) in this paper. In particular, the REGO employs a multi-stage recurrent processing structure to help the attention of DETR gradually focus on foreground objects more accurately. In each processing stage, visual features are extracted as glimpse features from RoIs with enlarged bounding box areas of detection results from the previous stage. Then, a glimpse-based decoder is introduced to provide refined detection results based on both the glimpse features and the attention modeling outputs of the previous stage. In practice, REGO can be easily embedded in representative DETR variants while maintaining their fully end-to-end training and inference pipelines. In particular, REGO helps Deformable DETR achieve 44.8 AP on the MSCOCO dataset with only 36 training epochs, compared with the first DETR and the Deformable DETR that require 500 and 50 epochs to achieve comparable performance, respectively. Experiments also show that REGO consistently boosts the performance of different DETR detectors by up to 7% relative gain at the same setting of 50 training epochs. Code is available via https://github.com/zhechen/Deformable-DETR-REGO. Stage 1 Stage 2 DETR Recurrent Glimpsebased Decoder Glimpsebased Decoder Stage 3 Poor Detection with Shorter Training Robust Detection with Shorter Training Glimpsebased Decoder Glimpsebased Decoder

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("Chen_Recurrent_Glimpse-Based_Decoder_for_Detection_With_Transformer_CVPR_2022_paper")
get_code_for_paper("Chen_Recurrent_Glimpse-Based_Decoder_for_Detection_With_Transformer_CVPR_2022_paper")
have("Chen_Recurrent_Glimpse-Based_Decoder_for_Detection_With_Transformer_CVPR_2022_paper")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/Chen_Recurrent_Glimpse-Based_Decoder_for_Detection_With_Transformer_CVPR_2022_paper.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/Chen_Recurrent_Glimpse-Based_Decoder_for_Detection_With_Transformer_CVPR_2022_paper.svg)](https://syntology.ai/paper/Chen_Recurrent_Glimpse-Based_Decoder_for_Detection_With_Transformer_CVPR_2022_paper)

Connect an agent — have() is free.