Papers › Re-Scoring Using Image-Language Similarity for Few-Shot Object Detection

Re-Scoring Using Image-Language Similarity for Few-Shot Object Detection

1 Nov 2023arXiv:2311.00278archive 2025-07-28

Min Jae Jung, Seung Dae Han, Joohee Kim

Few-shot object detection, which focuses on detecting novel objects with few labels, is an emerging challenge in the community. Recent studies show that adapting a pre-trained model or modified loss function can improve performance. In this paper, we explore leveraging the power of Contrastive Language-Image Pre-training (CLIP) and hard negative classification loss in low data setting. Specifically, we propose Re-scoring using Image-language Similarity for Few-shot object detection (RISF) which extends Faster R-CNN by introducing Calibration Module using CLIP (CM-CLIP) and Background Negative Re-scale Loss (BNRL). The former adapts CLIP, which performs zero-shot classification, to re-score the classification scores of a detector using image-class similarities, the latter is modified classification loss considering the punishment for fake backgrounds as well as confusing categories on a generalized few-shot object detection dataset. Extensive experiments on MS-COCO and PASCAL VOC show that the proposed RISF substantially outperforms the state-of-the-art approaches. The code will be available.

PaperPDFCode

Code

INFINIQ-AI1/RISF officialpytorch 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

ClassificationFew-Shot Object DetectionObjectObject DetectionZero-Shot Learningobject-detection

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Few-Shot Object Detection MS-COCO (1-shot) RISF AP 11.7 #4 of 7 Archive leaderboard report
Few-Shot Object Detection MS-COCO (10-shot) RISF (SWIN-Large) AP 25.5 #5 of 33 Archive leaderboard report
Few-Shot Object Detection MS-COCO (10-shot) RISF (Resnet-101) AP 21.9 #9 of 33 Archive leaderboard report
Few-Shot Object Detection MS-COCO (30-shot) RISF (SWIN-Large) AP 31.9 #5 of 25 Archive leaderboard report
Few-Shot Object Detection MS-COCO (30-shot) RISF (Resnet-101) AP 24.4 #9 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.

Methods

CLIPConvolutionFaster 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