Papers › Domain Adaptive Faster R-CNN for Object Detection in the Wild

Domain Adaptive Faster R-CNN for Object Detection in the Wild

8 Mar 2018CVPR 2018 6arXiv:1803.03243archive 2025-07-28

Yuhua Chen, Wen Li, Christos Sakaridis, Dengxin Dai, Luc van Gool

Object detection typically assumes that training and test data are drawn from an identical distribution, which, however, does not always hold in practice. Such a distribution mismatch will lead to a significant performance drop. In this work, we aim to improve the cross-domain robustness of object detection. We tackle the domain shift on two levels: 1) the image-level shift, such as image style, illumination, etc, and 2) the instance-level shift, such as object appearance, size, etc. We build our approach based on the recent state-of-the-art Faster R-CNN model, and design two domain adaptation components, on image level and instance level, to reduce the domain discrepancy. The two domain adaptation components are based on H-divergence theory, and are implemented by learning a domain classifier in adversarial training manner. The domain classifiers on different levels are further reinforced with a consistency regularization to learn a domain-invariant region proposal network (RPN) in the Faster R-CNN model. We evaluate our newly proposed approach using multiple datasets including Cityscapes, KITTI, SIM10K, etc. The results demonstrate the effectiveness of our proposed approach for robust object detection in various domain shift scenarios.

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="1803.03243")

Code

Syntology Ran 1 of 8 code samples harvested from 5 repositories linked to this paper; 7 have no recorded run. Of those that ran: 1 ran · our draft was wrong.

By repository: community (archive-listed): 8 samples from 5 repositories, 1 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

yuhuayc/da-faster-rcnn officialmentioned on GitHubpytorchNOASSERTION report
harsh-99/SCL mentioned on GitHubpytorch report
jinlong17/da-detect mentioned on GitHubpytorchMIT report
krumo/Detectron-DA-Faster-RCNN mentioned on GitHubpytorchApache-2.0 report
krumo/Domain-Adaptive-Faster-RCNN-PyTorch mentioned on GitHubpytorchMIT report
shreyasrajesh/DA-Object-Detection mentioned 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

8 samples harvested; 1 ran; 0 honoured the contract we drafted; 7 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.

1ran · our draft was wrong
7unverified

Licence: 4 of the 8 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 5 repositories linked to this paper, official or community; each sample names its own and says which. “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.

consistency_reg harsh-99/SCL/trainval_net_dfrcnn.py community (archive-listed) ran · our draft was wrong fingerprinted no licence file found · pointer only · cad124aa0ae8aaea · report
add_VGG16_conv5_body krumo/Detectron-DA-Faster-RCNN/detectron/modeling/VGG16.py community (archive-listed) unverified Apache-2.0 (permissive) · 867590b1664a9388 · report
add_VGG_CNN_M_1024_conv5_body krumo/Detectron-DA-Faster-RCNN/detectron/modeling/VGG_CNN_M_1024.py community (archive-listed) unverified Apache-2.0 (permissive) · a7195f42969e79d3 · report
build_roi_box_head shreyasrajesh/DA-Object-Detection/maskrcnn_benchmark/modeling/roi_heads/box_head/box_head.py community (archive-listed) unverified MIT (permissive) · e3f26cc60ad5f628 · report
consistency_loss krumo/Domain-Adaptive-Faster-RCNN-PyTorch/maskrcnn_benchmark/layers/consistency_loss.py community (archive-listed) unverified MIT recorded; this copy not marked cleared · pointer only · 447d0d4c7a2722a4 · report
consistency_regularization_loss GiovanniPasq/DA-Faster-RCNN/DA-Faster-RCNN/da_modules/consistency_regularization_loss.py community (archive-listed) unverified MIT (permissive) · f947eb7467dce42e · report
interpolate krumo/Domain-Adaptive-Faster-RCNN-PyTorch/maskrcnn_benchmark/layers/misc.py community (archive-listed) unverified MIT recorded; this copy not marked cleared · pointer only · 2902bf4410253ff7 · report
sigmoid_focal_loss_cpu krumo/Domain-Adaptive-Faster-RCNN-PyTorch/maskrcnn_benchmark/layers/sigmoid_focal_loss.py community (archive-listed) unverified MIT recorded; this copy not marked cleared · pointer only · 426fd02a2beaf826 · report

Tasks

Domain AdaptationObjectObject DetectionRegion ProposalRobust Object DetectionUnsupervised Domain Adaptationobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image-to-Image Translation Cityscapes-to-Foggy Cityscapes FRCNN in the wild mAP 27.6 #6 of 6 Archive leaderboard report
Unsupervised Domain Adaptation Cityscapes to Foggy Cityscapes DA-Faster mAP@0.5 26.1 #22 of 22 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

ConvolutionFaster R-CNNRPNRoIPoolSoftmax

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