Journal Article10.1109/icme57554.2024.10688185
Proposal Feature Learning Using Proposal Relations for Weakly Supervised Object Detection
Zhaofei Wang,Weijia Zhang,Min-Ling Zhang +2 more
- 15 Jul 2024
pp 1-6
3
TL;DR: This work proposes two approaches, PFL-WSOD, to improve weakly supervised object detection by capturing intra-proposal and inter-proposal relations through self-attention and salient region banks, respectively, enhancing proposal representation and detection accuracy.
read more
Abstract: Weakly Supervised Object Detection (WSOD) trains detectors using only image-level annotations. Most existing WSOD models are based on pre-computed proposals and do not fully explore the relations of proposals. In this work, we address this limitation by proposing two approaches of Proposal Feature Learning for WSOD (PFL-WSOD), which effectively capture intra-proposal relations and inter-proposal relations respectively, thus improving proposal representation. To extract intra-proposal relations, we propose to utilize Self-Attention on Single Proposal for capturing relations inside each proposal. For inter-proposal relations, we propose Salient Region Banks by capturing a unique type of inter-proposal relation called deep inclusion, which significantly improves proposal representation when used in synergy with contrastive learning. Experimental results on benchmarks demonstrate the effectiveness of our methods.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
MG-STK: Weakly Supervised Multi-Granularity Learning Guided by Semantic Topological Knowledge
Qi Shen,Liu Yang,Canguang Ruan +2 more
- 30 Jun 2025
TL;DR: A weakly supervised multi-granularity learning approach, MG-STK, is proposed, leveraging semantic topological knowledge to achieve high-performance classification with minimal fine-grained annotations, outperforming comparison methods by 23.59% under 90% label missing rate.
Relational Enhancement Network for Industrial Defect Detection
Haotian Linghu,Meiqin Liu,Senlin Zhang +2 more
- 30 Jun 2025
TL;DR: This paper proposes the Relational Enhancement Network for industrial defect detection, enhancing defect features by exploring spatial and semantic relations, outperforming state-of-the-art approaches in detection precision and addressing incomplete defect detection on various industrial datasets.
Weakly Supervised Object Detection Framework based on Classification-Localization Consistency
Yihuan Zhu,Simiao Wang,Mingyu Lu,Zheng-xing Sun +3 more
- 30 Jun 2025
TL;DR: This paper proposes a novel weakly supervised object detection framework that bridges the performance gap between fully and weakly supervised object detection by introducing Max Score Pooling and Proposal Fusion Mechanism for classification-localization consistency.
References
•Proceedings Article
Attention is All you Need
Ashish Vaswani,Noam Shazeer,Niki Parmar,Jakob Uszkoreit,Llion Jones,Aidan N. Gomez,Lukasz Kaiser,Illia Polosukhin +7 more
- 12 Jun 2017
TL;DR: This paper proposed a simple network architecture based solely on an attention mechanism, dispensing with recurrence and convolutions entirely and achieved state-of-the-art performance on English-to-French translation.
ImageNet: A large-scale hierarchical image database
Jia Deng,Wei Dong,Richard Socher,Li-Jia Li,Kai Li,Li Fei-Fei +5 more
- 20 Jun 2009
TL;DR: A new database called “ImageNet” is introduced, a large-scale ontology of images built upon the backbone of the WordNet structure, much larger in scale and diversity and much more accurate than the current image datasets.
•Posted Content
Fast R-CNN
TL;DR: This paper proposes a Fast Region-based Convolutional Network method (Fast R-CNN) for object detection that builds on previous work to efficiently classify object proposals using deep convolutional networks.
20.3K
•Posted Content
End-to-End Object Detection with Transformers
Nicolas Carion,Francisco Massa,Gabriel Synnaeve,Nicolas Usunier,Alexander Kirillov,Sergey Zagoruyko +5 more
TL;DR: This work presents a new method that views object detection as a direct set prediction problem, and demonstrates accuracy and run-time performance on par with the well-established and highly-optimized Faster RCNN baseline on the challenging COCO object detection dataset.
9.1K
Instance-Aware, Context-Focused, and Memory-Efficient Weakly Supervised Object Detection
Zhongzheng Ren,Zhiding Yu,Xiaodong Yang,Ming-Yu Liu,Yong Jae Lee,Alexander G. Schwing,Jan Kautz +6 more
- 14 Jun 2020
TL;DR: Wetectron as mentioned in this paper employs an instance-aware self-training algorithm and a learnable Concrete DropBlock while devising a memory-efficient sequential batch back-propagation.