Papers › MILA: Memory-Based Instance-Level Adaptation for Cross-Domain Object Detection

MILA: Memory-Based Instance-Level Adaptation for Cross-Domain Object Detection

3 Sep 2023arXiv:2309.01086archive 2025-07-28

Onkar Krishna, Hiroki Ohashi, Saptarshi Sinha

Cross-domain object detection is challenging, and it involves aligning labeled source and unlabeled target domains. Previous approaches have used adversarial training to align features at both image-level and instance-level. At the instance level, finding a suitable source sample that aligns with a target sample is crucial. A source sample is considered suitable if it differs from the target sample only in domain, without differences in unimportant characteristics such as orientation and color, which can hinder the model's focus on aligning the domain difference. However, existing instance-level feature alignment methods struggle to find suitable source instances because their search scope is limited to mini-batches. Mini-batches are often so small in size that they do not always contain suitable source instances. The insufficient diversity of mini-batches becomes problematic particularly when the target instances have high intra-class variance. To address this issue, we propose a memory-based instance-level domain adaptation framework. Our method aligns a target instance with the most similar source instance of the same category retrieved from a memory storage. Specifically, we introduce a memory module that dynamically stores the pooled features of all labeled source instances, categorized by their labels. Additionally, we introduce a simple yet effective memory retrieval module that retrieves a set of matching memory slots for target instances. Our experiments on various domain shift scenarios demonstrate that our approach outperforms existing non-memory-based methods significantly.

PaperPDFCode

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

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

Code

hitachi-rd-cv/MILA 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

Domain AdaptationObject DetectionUnsupervised Domain Adaptationobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Domain Adaptation Comic2k MILA mAP 44.6 #2 of 2 Archive leaderboard report
Domain Adaptation Foggy Cityscapes MILA mAP 50.6 #1 of 1 Archive leaderboard report
Domain Adaptation Sim10k MILA mAP 57.4 #1 of 1 Archive leaderboard report
Object Detection Pascal VOC to Clipart1K MILA mAP 49.9 #2 of 3 Archive leaderboard report
Unsupervised Domain Adaptation SIM10K to Cityscapes MILA mAP@0.5 57.4 #10 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

ALIGNFocus

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