Papers › Balanced ID-OOD tradeoff transfer makes query based detectors good few shot learners

Balanced ID-OOD tradeoff transfer makes query based detectors good few shot learners

23 May 2024High-Confidence Computing 2024 5archive 2025-07-28

Yuantao Yin, Ping Yin, Xue Xiao, Liang Yan, Siqing Sun, Xiaobo An

Fine-tuning is a popular approach to solve the few-shot object detection problem. In this paper, we attempt to introduce a new perspective on it. We formulate the few-shot novel tasks as a type of distribution shifted from its ground-truth distribution. We introduce the concept of imaginary placeholder masks to show that this distribution shift is essentially a composite of in-distribution(ID) and out-of-distribution(OOD) shifts. Our empirical investigation results show that it is significant to balance the trade-off between adapting to the available few-shot distribution and keeping the distribution-shift robustness of the pre-trained model. We explore improvements in the few-shot fine-tuning transfer in the few-shot object detection(FSOD) settings from three aspects. First, we explore the LinearProbe-Finetuning(LP-FT) technique to balance this trade-off to mitigate the feature distortion problem. Second, we explore the effectiveness of utilizing the protection freezing strategy for query-based object detectors to keep their OOD robustness. Third, we try to utilize ensembling methods to circumvent the feature distortion. All these techniques are integrated into a whole method called BIOT(Balanced ID-OOD Transfer). Evaluation results show that our method is simple yet effective and general to tap the FSOD potential of query-based object detectors. It outperforms the current SOTA method in many FSOD settings and has a promising scaling capability.

PaperPDF

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

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

Tasks

Cross-Domain Few-Shot Object DetectionFew-Shot Object DetectionObjectObject Detectionobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Cross-Domain Few-Shot Object Detection Artaxor BIOT(10-Shot) mAP 58.4 #4 of 16 Archive leaderboard report
Cross-Domain Few-Shot Object Detection Artaxor BIOT(5-Shot) mAP 53.3 #5 of 16 Archive leaderboard report
Cross-Domain Few-Shot Object Detection DIOR BIOT mAP 31.1 #3 of 15 Archive leaderboard report
Cross-Domain Few-Shot Object Detection UODD BIOT(10-shot) mAP 20.4 #3 of 16 Archive leaderboard report
Cross-Domain Few-Shot Object Detection UODD BIOT(5-shot) mAP 18.0 #4 of 16 Archive leaderboard report
Few-Shot Object Detection MS-COCO (10-shot) BIOT AP 26.3 #4 of 33 Archive leaderboard report
Few-Shot Object Detection MS-COCO (30-shot) BIOT AP 33.8 #4 of 25 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.

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