Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat
Sign Up
Cited by 646

The DOI matches its Crossref record; 19 of the 19 references it cites were found in a registry or an index.

DSOD: Learning Deeply Supervised Object Detectors from Scratch

Open access
Shen, Zhiqiang, Liu, Zhuang, Li, Jianguo, Jiang, Yu-Gang, Chen, Yurong, Xue, Xiangyang·2017·2017 IEEE International Conference on Computer Vision (ICCV)
DOI 10.1109/iccv.2017.212
Open this paper in CoChat — free account

Abstract

We present Deeply Supervised Object Detector (DSOD), a framework that can learn object detectors from scratch. State-of-the-art object objectors rely heavily on the off the-shelf networks pre-trained on large-scale classification datasets like Image Net, which incurs learning bias due to the difference on both the loss functions and the category distributions between classification and detection tasks. Model fine-tuning for the detection task could alleviate this bias to some extent but not fundamentally. Besides, transferring pre-trained models from classification to detection between discrepant domains is even more difficult (e.g. RGB to depth images). A better solution to tackle these two critical problems is to train object detectors from scratch, which motivates our proposed DSOD. Previous efforts in this direction mostly failed due to much more complicated loss functions and limited training data in object detection. In DSOD, we contribute a set of design principles for training object detectors from scratch. One of the key findings is that deep supervision, enabled by dense layer-wise connections, plays a critical role in learning a good detector. Combining with several other principles, we develop DSOD following the single-shot detection (SSD) framework. Experiments on PASCAL VOC 2007, 2012 and MS COCO datasets demonstrate that DSOD can achieve better results than the state-of-the-art solutions with much more compact models. For instance, DSOD outperforms SSD on all three benchmarks with real-time detection speed, while requires only 1/2 parameters to SSD and 1/10 parameters to Faster RCNN.

Overview

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

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

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

Integrity signals

Registry

Crossref · 10.1109/iccv.2017.212

Cites

19 of 19 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

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

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

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

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 19 references

Research works printed but not linked: 20

  1. 10.1109/CVPR.2015.7298594 · DOI · Paper page
  2. sun, 2015, DeepID3 Face Recognition with Very Deep Neural Networks
  3. 10.1109/ICCV.2015.164 · DOI · Paper page
  4. 10.1007/s11263-013-0620-5 · DOI · Paper page
  5. jégou, 2016, The one hundred layers tiramisu Fully convolutional DenseNets for semantic segmentation
  6. 10.1145/2647868.2654889 · DOI · Paper page
  7. kim, 2016, Pvanet Deep but lightweight neural networks for real-time object detection
  8. krasin, 2016, Openimages A public dataset for large-scale multi-label and multi-class image classification
  9. lee, 2015, Deeply-supervised nets, AISTATS
  10. li, 2016, R-fcn: Object detection via region-based fully convolutional networks, NIPS
  11. simonyan, 2015, Very deep convolutional networks for large-scale image recognition, ICLRE
  12. glorot, 2010, Understanding the difficulty of training deep feedforward neural networks, AISTATS
  13. srivastava, 2014, Dropout: a simple way to prevent neural networks from overfitting, JMLR
  14. 10.1109/CVPR.2014.81 · DOI · Paper page
  15. 10.1109/CVPR.2016.314 · DOI · Paper page
  16. lin, 2014, Microsoft coco: Common objects in context, ECCV
  17. liu, 2015, Parsenet Looking wider to see better
  18. liu, 2016, Ssd: Single shot multi-box detector, ECCV
  19. 10.1109/CVPR.2015.7298965 · DOI · Paper page
  20. 10.1109/CVPR.2017.690 · DOI · Paper page

Cited by

Metadata

Authors
Shen, Z., Liu, Z., Li, J., Jiang, Y.-G., Chen, Y., & Xue, X.
Venue
2017 IEEE International Conference on Computer Vision (ICCV)
Publisher
IEEE
Published
2017-10
Pages
1937-1945
DOI
10.1109/iccv.2017.212
OpenAlex
W2963813458
Cited by
646
References
19
FWCI
27.50
Type
conference paper
Language
en
Open access
green

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.