Enregistré dans:
Détails bibliographiques
Auteurs principaux: Jung, Min Jae, Han, Seung Dae, Kim, Joohee
Format: Preprint
Publié: 2023
Sujets:
Accès en ligne:https://arxiv.org/abs/2311.00278
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866914884228218880
author Jung, Min Jae
Han, Seung Dae
Kim, Joohee
author_facet Jung, Min Jae
Han, Seung Dae
Kim, Joohee
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2311_00278
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Re-Scoring Using Image-Language Similarity for Few-Shot Object Detection
Jung, Min Jae
Han, Seung Dae
Kim, Joohee
Computer Vision and Pattern Recognition
Artificial Intelligence
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.
title Re-Scoring Using Image-Language Similarity for Few-Shot Object Detection
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2311.00278