paper-with-me

홈 › Papers

Read, look and detect: Bounding box annotation from image-caption pairs

2023-06-09 · Eduardo Hugo Sanchez

Various methods have been proposed to detect objects while reducing the cost of data annotation. For instance, weakly supervised object detection (WSOD) methods rely only on image-level annotations during training. Unfortunately, data annotation remains expensive since annotators must provide the categories describing the content of each image and labeling is restricted to a fixed set of categories. In this paper, we propose a method to locate and label objects in an image by using a form of weaker supervision: image-caption pairs. By leveraging recent advances in vision-language (VL) models and self-supervised vision transformers (ViTs), our method is able to perform phrase grounding and object detection in a weakly supervised manner. Our experiments demonstrate the effectiveness of our approach by achieving a 47.51% recall@1 score in phrase grounding on Flickr30k Entities and establishing a new state-of-the-art in object detection by achieving 21.1 mAP 50 and 10.5 mAP 50:95 on MS COCO when exclusively relying on image-caption pairs.

📄 PDF Abstract BibTeX arXiv:2306.06149

Code (0)

등록된 구현이 없습니다.

Tasks

Objectobject-detectionObject DetectionPhrase GroundingWeakly Supervised Object Detection

Similar Papers 제목 키워드 기반

Associative embeddings for large-scale knowledge transfer with self-assessment

2013-12-11 · CVPR 2014 6 · Alexander Vezhnevets, Vittorio Ferrari

We propose a method for knowledge transfer between semantically related classes in ImageNet. By transferring knowledge from the images that have bounding-box annotations to the others, our method is capable of automatica…

Gaussian ProcessesObject LocalizationTransfer Learning

ClipGrader: Leveraging Vision-Language Models for Robust Label Quality Assessment in Object Detection

2025-03-03 · Hong Lu, Yali Bian, Rahul C. Shah

High-quality annotations are essential for object detection models, but ensuring label accuracy - especially for bounding boxes - remains both challenging and costly. This paper introduces ClipGrader, a novel approach th…

Objectobject-detectionObject DetectionPseudo Label+1

Iterative Bounding Box Annotation for Object Detection

2020-07-02 · Bishwo Adhikari, Heikki Huttunen

Manual annotation of bounding boxes for object detection in digital images is tedious, and time and resource consuming. In this paper, we propose a semi-automatic method for efficient bounding box annotation. The method …

Objectobject-detectionObject Detection

Segmentation-Based Bounding Box Generation for Omnidirectional Pedestrian Detection

2021-04-28 · Masato Tamura, Tomoaki Yoshinaga

We propose a segmentation-based bounding box generation method for omnidirectional pedestrian detection that enables detectors to tightly fit bounding boxes to pedestrians without omnidirectional images for training. Due…

object-detectionObject DetectionPedestrian Detection

Training object class detectors with click supervision

2017-04-20 · CVPR 2017 7 · Dim P. Papadopoulos, Jasper R. R. Uijlings, Frank Keller, Vittorio Ferrari

Training object class detectors typically requires a large set of images with objects annotated by bounding boxes. However, manually drawing bounding boxes is very time consuming. In this paper we greatly reduce annotati…

Multiple Instance LearningObjectObject LocalizationWeakly-Supervised Object Localization