CoChat

Weakly Supervised Object Detection Using Proposal- and Semantic-Level Relationships

Zhang, Dingwen, Zeng, Wenyuan, Yao, Jieru, Han, Junwei · 2022 · IEEE Transactions on Pattern Analysis and Machine Intelligence

The DOI matches its Crossref record; 56 of the 58 references it cites were found in a registry or an index.

Abstract

In recent years, weakly supervised object detection has attracted great attention in the computer vision community. Although numerous deep learning-based approaches have been proposed in the past few years, such an ill-posed problem is still challenging and the learning performance is still behind the expectation. In fact, most of the existing approaches only consider the visual appearance of each proposal region but ignore to make use of the helpful context information. To this end, this paper introduces two levels of context into the weakly supervised learning framework. The first one is the proposal-level context, i.e., the relationship of the spatially adjacent proposals. The second one is the semantic-level context, i.e., the relationship of the co-occurring object categories. Therefore, the proposed weakly supervised learning framework contains not only the cognition process on the visual appearance but also the reasoning process on the proposal- and semantic-level relationships, which leads to the novel deep multiple instance reasoning framework. Specifically, built upon a conventional CNN-based network architecture, the proposed framework is equipped with two additional graph convolutional network-based reasoning models to implement object location reasoning and multi-label reasoning within an end-to-end network training procedure. Comprehensive experiments on the widely used PASCAL VOC and MS COCO benchmarks have been implemented, which demonstrate the superior capacity of the proposed approach when compared with other state-of-the-art methods and baseline models.

Overview

Integrity signals

Registry

Crossref · 10.1109/tpami.2020.3046647

Cites

56 of 56 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Verification

Claims the paper makes

This paper’s full text isn’t openly available, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Citations

Cites

Show all 56 references

Research works printed but not linked: 4

  1. 10.1109/CVPR.2016.311 · DOI · Paper page
  2. 10.1109/ICCV.2019.00662 · DOI
  3. Wei, TS2C: Tight box mining with surrounding segmentation context for weakly supervised object detection, 434
  4. 10.1109/CVPR.2019.00964 · DOI

Cited by

See all 132

Metadata

Authors
Zhang, D., Zeng, W., Yao, J., & Han, J.
Affiliations
Northwestern Polytechnical University (CN)
Venue
IEEE Transactions on Pattern Analysis and Machine Intelligence
Published
2022-06-01
Volume
44
Issue
6
Pages
3349-3363
ISSN
  • 0162-8828 (ISSN-L)
  • 2160-9292
  • 1939-3539
OpenAlex
W3117854388
Cited by
132
References
58
Citations by year
2026: 9 · 2025: 14 · 2024: 20 · 2023: 51 · 2022: 33
FWCI
8.65
Type
journal article
Language
en
Open access
closed
Locations
  • IEEE Transactions on Pattern Analysis and Machine Intelligence (publishedVersion)
  • PubMed (publishedVersion)
Funders
  • Key R&D Program of Guangdong Province (2019B010110001)
  • National Natural Science Foundation of China (61876140, U1801265)
  • Research Funds for Interdisciplinary subject
Topics
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image and Video Retrieval Techniques
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Visual Attention and Saliency Detection
Keywords
weakly supervised object detection, graph convolutional networks

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.