CoChat

Self Paced Deep Learning for Weakly Supervised Object Detection

Open access
Sangineto, Enver, Nabi, Moin, Culibrk, Dubravko, Sebe, Nicu · 2019 · IEEE Transactions on Pattern Analysis and Machine Intelligence

The DOI matches its Crossref record; 48 of the 49 references it cites were found in a registry or an index.

Abstract

In a weakly-supervised scenario object detectors need to be trained using image-level annotation alone. Since bounding-box-level ground truth is not available, most of the solutions proposed so far are based on an iterative, Multiple Instance Learning framework in which the current classifier is used to select the highest-confidence boxes in each image, which are treated as pseudo-ground truth in the next training iteration. However, the errors of an immature classifier can make the process drift, usually introducing many of false positives in the training dataset. To alleviate this problem, we propose in this paper a training protocol based on the self-paced learning paradigm. The main idea is to iteratively select a subset of images and boxes that are the most reliable, and use them for training. While in the past few years similar strategies have been adopted for SVMs and other classifiers, we are the first showing that a self-paced approach can be used with deep-network-based classifiers in an end-to-end training pipeline. The method we propose is built on the fully-supervised Fast-RCNN architecture and can be applied to similar architectures which represent the input image as a bag of boxes. We show state-of-the-art results on Pascal VOC 2007, Pascal VOC 2010 and ILSVRC 2013. On ILSVRC 2013 our results based on a low-capacity AlexNet network outperform even those weakly-supervised approaches which are based on much higher-capacity networks.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/tpami.2018.2804907

Cites

48 of 49 references verified0 citation errors · 1 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

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?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 49 references

Research works printed but not linked: 2

  1. [15] K. He, G. Gkioxari, P. Doll´ ar, and R. B. Girshick. Mask R-CNN. In ICCV , 2017. -
  2. [39] J. S. Supancic III and D. Ramanan. Self-paced learning for longterm tracking. In CVPR , pages 2379-2386, 2013. -

Cited by

See all 135

Metadata

Authors
Sangineto, E., Nabi, M., Culibrk, D., & Sebe, N.
Affiliations
  • University of Trento (IT)
  • Systems, Applications & Products in Data Processing (Germany) (DE)
  • University of Novi Sad (RS)
Venue
IEEE Transactions on Pattern Analysis and Machine Intelligence
Published
2019-03-01
Volume
41
Issue
3
Pages
712-725
ISSN
  • 0162-8828 (ISSN-L)
  • 2160-9292
  • 1939-3539
OpenAlex
W2494236530
Cited by
114
References
49
Citations by year
2025: 6 · 2024: 9 · 2023: 12 · 2022: 14 · 2021: 16 · 2020: 21 · 2019: 25
FWCI
8.63
Type
journal article
Language
en
Open access
Locations
  • IEEE Transactions on Pattern Analysis and Machine Intelligence (publishedVersion)
  • PubMed (publishedVersion)
  • arXiv (Cornell University) (submittedVersion)
  • Iris (University of Trento) (submittedVersion, other-oa)
  • IRIS UNIMORE (University of Modena and Reggio Emilia) (submittedVersion, cc-by)
  • arXiv (Cornell University)
Funders
Nvidia
Topics
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
  • Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image and Video Retrieval Techniques
Keywords
weakly supervised object detection, self-paced learning, image-level annotations, multiple instance learning, pseudo-labeling, training data selection, Fast R-CNN, AlexNet, Pascal VOC

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.