</> Code with Papers by Syntology

Papers › Align and Distill: Unifying and Improving Domain Adaptive Object Detection

Align and Distill: Unifying and Improving Domain Adaptive Object Detection

18 Mar 2024arXiv:2403.12029archive 2025-07-28

Justin Kay, Timm Haucke, Suzanne Stathatos, Siqi Deng, Erik Young, Pietro Perona, Sara Beery, Grant van Horn

Object detectors often perform poorly on data that differs from their training set. Domain adaptive object detection (DAOD) methods have recently demonstrated strong results on addressing this challenge. Unfortunately, we identify systemic benchmarking pitfalls that call past results into question and hamper further progress: (a) Overestimation of performance due to underpowered baselines, (b) Inconsistent implementation practices preventing transparent comparisons of methods, and (c) Lack of generality due to outdated backbones and lack of diversity in benchmarks. We address these problems by introducing: (1) A unified benchmarking and implementation framework, Align and Distill (ALDI), enabling comparison of DAOD methods and supporting future development, (2) A fair and modern training and evaluation protocol for DAOD that addresses benchmarking pitfalls, (3) A new DAOD benchmark dataset, CFC-DAOD, enabling evaluation on diverse real-world data, and (4) A new method, ALDI++, that achieves state-of-the-art results by a large margin. ALDI++ outperforms the previous state-of-the-art by +3.5 AP50 on Cityscapes to Foggy Cityscapes, +5.7 AP50 on Sim10k to Cityscapes (where ours is the only method to outperform a fair baseline), and +0.6 AP50 on CFC Kenai to Channel. Our framework, dataset, and state-of-the-art method offer a critical reset for DAOD and provide a strong foundation for future research. Code and data are available: https://github.com/justinkay/aldi and https://github.com/visipedia/caltech-fish-counting.

PaperPDFCode

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

Code

justinkay/aldi officialmentioned in papermentioned on GitHubpytorch report
estrellaxyu/differential-alignment-for-daod 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

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

BenchmarkingObject DetectionUnsupervised Domain Adaptationobject-detection

Datasets

Introduced by this paper, per the archive.

CFC-DAOD

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Unsupervised Domain Adaptation CFC-DAOD ALDI++ (ResNet50-FPN) AP@0.5 76.1 #1 of 6 Archive leaderboard report
Unsupervised Domain Adaptation CFC-DAOD MIC (ResNet50-FPN) AP@0.5 74.1 #2 of 6 Archive leaderboard report
Unsupervised Domain Adaptation CFC-DAOD AT (ResNet50-FPN) AP@0.5 69.1 #3 of 6 Archive leaderboard report
Unsupervised Domain Adaptation CFC-DAOD PT (ResNet50-FPN) AP@0.5 69.0 #4 of 6 Archive leaderboard report
Unsupervised Domain Adaptation CFC-DAOD UMT (ResNet50-FPN) AP@0.5 61.2 #5 of 6 Archive leaderboard report
Unsupervised Domain Adaptation CFC-DAOD SADA (ResNet50-FPN) AP@0.5 58.9 #6 of 6 Archive leaderboard report
Unsupervised Domain Adaptation Cityscapes to Foggy Cityscapes ALDI-DETR (ResNet-50, 800px) mAP@0.5 44.8 #11 of 22 Archive leaderboard report
Unsupervised Domain Adaptation SIM10K to Cityscapes ALDI++ mAP@0.5 77.8 #1 of 13 Archive leaderboard report
Unsupervised Domain Adaptation SIM10K to Cityscapes ALDI-YOLO mAP@0.5 75.0 #2 of 13 Archive leaderboard report
Unsupervised Domain Adaptation SIM10K to Cityscapes MIC(ALDI frame) mAP@0.5 73.1 #3 of 13 Archive leaderboard report
Unsupervised Domain Adaptation SIM10K to Cityscapes AT(ALDI frame) mAP@0.5 72.0 #4 of 13 Archive leaderboard report
Unsupervised Domain Adaptation SIM10K to Cityscapes SADA(ALDI frame) mAP@0.5 71.8 #5 of 13 Archive leaderboard report
Unsupervised Domain Adaptation SIM10K to Cityscapes PT(ALDI frame) mAP@0.5 70.6 #6 of 13 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

Introduced by this paper: ALDI++

ALDI++

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