CoChat

Learning Rotation-Invariant and Fisher Discriminative Convolutional Neural Networks for Object Detection

Cheng, Gong, Han, Junwei, Zhou, Peicheng, Xu, Dong · 2019 · IEEE Transactions on Image Processing

The DOI matches its Crossref record; 71 of the 77 references it cites were found in a registry or an index.

Abstract

The performance of object detection has recently been significantly improved due to the powerful features learnt through convolutional neural networks (CNNs). Despite the remarkable success, there are still several major challenges in object detection, including object rotation, within-class diversity, and between-class similarity, which generally degenerate object detection performance. To address these issues, we build up the existing state-of-the-art object detection systems and propose a simple but effective method to train rotation-invariant and Fisher discriminative CNN models to further boost object detection performance. This is achieved by optimizing a new objective function that explicitly imposes a rotation-invariant regularizer and a Fisher discrimination regularizer on the CNN features. Specifically, the first regularizer enforces the CNN feature representations of the training samples before and after rotation to be mapped closely to each other in order to achieve rotation-invariance. The second regularizer constrains the CNN features to have small within-class scatter but large between-class separation. We implement our proposed method under four popular object detection frameworks, including region-CNN (R-CNN), Fast R- CNN, Faster R- CNN, and R- FCN. In the experiments, we comprehensively evaluate the proposed method on the PASCAL VOC 2007 and 2012 data sets and a publicly available aerial image data set. Our proposed methods outperform the existing baseline methods and achieve the state-of-the-art results.

Overview

Integrity signals

Registry

Crossref · 10.1109/tip.2018.2867198

Cites

71 of 71 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 71 references

Research works printed but not linked: 3

  1. lin, 2013, Network in Network
  2. he, 2014, Spatial pyramid pooling in deep convolutional networks for visual recognition, Proc Eur Conf Comput Vis, 346
  3. girshick, 2015, Fast R-CNN, Proc IEEE Int Conf Comput Vis, 1440

Cited by

Metadata

Authors
Cheng, G., Han, J., Zhou, P., & Xu, D.
Affiliations
  • Northwestern Polytechnical University (CN)
  • The University of Sydney (AU)
Venue
IEEE Transactions on Image Processing
Published
2019-01
Volume
28
Issue
1
Pages
265-278
ISSN
  • 1057-7149 (ISSN-L)
  • 1941-0042
OpenAlex
W2888527098
Cited by
408
References
77
Citations by year
2026: 12 · 2025: 19 · 2024: 26 · 2023: 46 · 2022: 64 · 2021: 77 · 2020: 77 · 2019: 86
FWCI
30.15
Type
journal article
Language
en
Open access
closed
Locations
  • IEEE Transactions on Image Processing (publishedVersion)
  • PubMed (publishedVersion)
Funders
  • National Natural Science Foundation of China (61772425, 61473231, 61790552)
  • Natural Science Basic Research Plan in Shaanxi Province of China (2017JM6044, 2018KJXX-029)
  • National Aerospace Science Foundation of China (2017ZC53032)
  • Fundamental Research Funds for the Central Universities (3102018zy023)
  • Australian Research Council (FT180100116)
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 › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
Keywords
object detection, rotation invariance, within-class scatter, Faster R-CNN, R-FCN, aerial images

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.