VEIL: Vetting Extracted Image Labels from In-the-Wild Captions for Weakly-Supervised Object Detection

Anonymous

Abstract: The use of large-scale vision-language datasets is limited for object detection due to the negative impact of label noise on localization. Prior methods have shown how such large-scale datasets can be used for pretraining, which can provide initial signal for localization, but is insufficient without clean bounding-box data for at least some categories. We propose a technique to ``vet'' labels extracted from noisy captions, and use them for weakly-supervised object detection (WSOD), without any bounding boxes. We analyze the types of label noise in captions, and train a classifier that predicts if an extracted label is actually present in the image or not. Our classifier generalizes across dataset boundaries and across categories. We compare the classifier to nine baselines on five datasets, and demonstrate that it can improve WSOD without label vetting by 30\% (31.2 to 40.5 mAP when evaluated on PASCAL VOC).

Paper Type: long

Research Area: Multimodality and Language Grounding to Vision, Robotics and Beyond

Contribution Types: NLP engineering experiment, Data resources, Data analysis

Languages Studied: English

Consent To Share Submission Details: On behalf of all authors, we agree to the terms above to share our submission details.