Boosting Weakly Supervised Object Detection with Progressive Knowledge Transfer

• URL: http://arxiv.org/abs/2007.07986v1
• Date: Wed, 15 Jul 2020 20:38:25 GMT
• Title: Boosting Weakly Supervised Object Detection with Progressive Knowledge Transfer
• Authors: Yuanyi Zhong, Jianfeng Wang, Jian Peng, Lei Zhang
• Abstract summary: We propose an effective knowledge transfer framework to boost the weakly supervised object detection accuracy. We iteratively transfer the knowledge from the source domain by a one-class universal detector and learn the target-domain detector. We achieved an mAP of $59.7%$ detection performance on the VOC test set and an mAP of $60.2%$ after retraining a fully supervised Faster RCNN.
• Score: 40.23657486941391
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this paper, we propose an effective knowledge transfer framework to boost the weakly supervised object detection accuracy with the help of an external fully-annotated source dataset, whose categories may not overlap with the target domain. This setting is of great practical value due to the existence of many off-the-shelf detection datasets. To more effectively utilize the source dataset, we propose to iteratively transfer the knowledge from the source domain by a one-class universal detector and learn the target-domain detector. The box-level pseudo ground truths mined by the target-domain detector in each iteration effectively improve the one-class universal detector. Therefore, the knowledge in the source dataset is more thoroughly exploited and leveraged. Extensive experiments are conducted with Pascal VOC 2007 as the target weakly-annotated dataset and COCO/ImageNet as the source fully-annotated dataset. With the proposed solution, we achieved an mAP of $59.7\%$ detection performance on the VOC test set and an mAP of $60.2\%$ after retraining a fully supervised Faster RCNN with the mined pseudo ground truths. This is significantly better than any previously known results in related literature and sets a new state-of-the-art of weakly supervised object detection under the knowledge transfer setting. Code: \url{https://github.com/mikuhatsune/wsod_transfer}.

Related papers

• Weakly-supervised Contrastive Learning for Unsupervised Object Discovery [52.696041556640516]
  Unsupervised object discovery is promising due to its ability to discover objects in a generic manner. We design a semantic-guided self-supervised learning model to extract high-level semantic features from images. We introduce Principal Component Analysis (PCA) to localize object regions.
  arXiv  Detail & Related papers  (2023-07-07T04:03:48Z)
• Domain Adaptable Self-supervised Representation Learning on Remote Sensing Satellite Imagery [2.796274924103132]
  This work presents a novel domain paradigm for studying contrastive self-supervised representation learning and knowledge transfer using remote sensing satellite data. The proposed approach investigates the knowledge transfer of selfsupervised representations across the distinct source and target data distributions. Experiments are conducted on three publicly available datasets, UC Merced Landuse (UCMD), SIRI-WHU, and MLRSNet.
  arXiv  Detail & Related papers  (2023-04-19T14:32:36Z)
• Target-Relevant Knowledge Preservation for Multi-Source Domain Adaptive Object Detection [47.705590047138685]
  Domain adaptive object detection (DAOD) is a promising way to alleviate performance drop of detectors in new scenes. We propose a novel approach, namely target-relevant knowledge preservation (TRKP) to unsupervised multi-sourceD. TRKP adopts the teacher-student framework, where the multi-head teacher network is built to extract knowledge from labeled source domains. The teacher network is enforced to capture target-relevant knowledge, thus benefiting decreasing domain shift when mentoring object detection in the target domain.
  arXiv  Detail & Related papers  (2022-04-17T09:50:48Z)
• Instance Relation Graph Guided Source-Free Domain Adaptive Object Detection [79.89082006155135]
  Unsupervised Domain Adaptation (UDA) is an effective approach to tackle the issue of domain shift. UDA methods try to align the source and target representations to improve the generalization on the target domain. The Source-Free Adaptation Domain (SFDA) setting aims to alleviate these concerns by adapting a source-trained model for the target domain without requiring access to the source data.
  arXiv  Detail & Related papers  (2022-03-29T17:50:43Z)
• Anchor-free Oriented Proposal Generator for Object Detection [59.54125119453818]
  Oriented object detection is a practical and challenging task in remote sensing image interpretation. Nowadays, oriented detectors mostly use horizontal boxes as intermedium to derive oriented boxes from them. We propose a novel Anchor-free Oriented Proposal Generator (AOPG) that abandons the horizontal boxes-related operations from the network architecture.
  arXiv  Detail & Related papers  (2021-10-05T10:45:51Z)
• Robust and Accurate Object Detection via Adversarial Learning [111.36192453882195]
  This work augments the fine-tuning stage for object detectors by exploring adversarial examples. Our approach boosts the performance of state-of-the-art EfficientDets by +1.1 mAP on the object detection benchmark.
  arXiv  Detail & Related papers  (2021-03-23T19:45:26Z)
• BiDet: An Efficient Binarized Object Detector [96.19708396510894]
  We propose a binarized neural network learning method called BiDet for efficient object detection. Our BiDet fully utilizes the representational capacity of the binary neural networks for object detection by redundancy removal. Our method outperforms the state-of-the-art binary neural networks by a sizable margin.
  arXiv  Detail & Related papers  (2020-03-09T08:16:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.