What Is Holding Back Convnets for Detection?
Open accessThe DOI matches its Crossref record; 15 of the 15 references it cites were found in a registry or an index.
Abstract
Convolutional neural networks have recently shown excellent results in general object detection and many other tasks. Albeit very effective, they involve many user-defined design choices. In this paper we want to better understand these choices by inspecting two key aspects “what did the network learn?”, and “what can the network learn?”. We exploit new annotations (Pascal3D+), to enable a new empirical analysis of the R-CNN detector. Despite common belief, our results indicate that existing state-of-the-art convnets are not invariant to various appearance factors. In fact, all considered networks have similar weak points which cannot be mitigated by simply increasing the training data (architectural changes are needed). We show that overall performance can improve when using image renderings as data augmentation. We report the best known results on Pascal3D+ detection and view-point estimation tasks. These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
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.
Integrity signals
Registry
Cites
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.
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
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333
Flownet: Learning optical flow with convolutional networks
Dosovitskiy, A., Fischer, P., Ilg, E., Hausser, P., Hazirbas, C., Golkov, V., Smagt, P. V. D., Cremers, D., & Brox, T. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.316 · Cited by 4,313
Return of the Devil in the Details: Delving Deep into Convolutional Nets
Chatfield, K., Simonyan, K., Vedaldi, A., & Zisserman, A. (2014) · Proceedings of the British Machine Vision Conference 2014 · doi:10.5244/c.28.6 · Cited by 3,335
Torralba, A., & Efros, A. A. (2011) · CVPR 2011 · doi:10.1109/cvpr.2011.5995347 · Cited by 2,440 · cited 1×
“Texture transfer All datasets suffer from bias [35], and it is hard to identify it by hand.”
BackgroundUnderstanding deep image representations by inverting them
Mahendran, A., & Vedaldi, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7299155 · Cited by 1,827
Building high-level features using large scale unsupervised learning
Le, Q. V. (2013) · 2013 IEEE International Conference on Acoustics, Speech and Signal Processing · doi:10.1109/icassp.2013.6639343 · Cited by 1,695 · cited 2×
“Previous analyses have either focused on highlighting the versatility of its features [27,26], learning equivariant mappings [19], training issues [5,16], theoretical arguments for its expressive power [2], discussing the brittleness of the decision boundary [34,14], visualising specific patterns emerging inside the n…”
BackgroundIdentifying and attacking the saddle point problem in high-dimensional non-convex optimization
Dauphin, Y., Pascanu, R., Gulcehre, C., Cho, K., Ganguli, S., & Bengio, Y. (2014) · arXiv · doi:10.48550/arxiv.1406.2572 · Cited by 827 · cited 1×
“Previous analyses have either focused on highlighting the versatility of its features [27,26], learning equivariant mappings [19], training issues [5,16], theoretical arguments for its expressive power [2], discussing the brittleness of the decision boundary [34,14], visualising specific patterns emerging inside the n…”
BackgroundThe 2005 PASCAL Visual Object Classes Challenge
Everingham, M., Zisserman, A., Williams, C. K. I., Van Gool, L., Allan, M., Bishop, C. M., Chapelle, O., Dalal, N., Deselaers, T., Dorkó, G., et al. (2006) · Lecture Notes in Computer Science · doi:10.1007/11736790_8 · Cited by 765
Self-citationHolistically-nested edge detection
Xie, S., & Tu, Z. (2017) · International Journal of Computer Vision · doi:10.1007/s11263-017-1004-z · Cited by 682 · cited 1×
“Classical problems such as general image classification [17], object detection [12], pose estimation [4], face recognition [28], object tracking [20], keypoint matching [10], stereo matching [40], optical flow [9], boundary estimation [38], and semantic labelling [21], have now all top performing results based on a di…”
Background
Cited by
DeepFool: A Simple and Accurate Method to Fool Deep Neural Networks
Moosavi-Dezfooli, S.-M., Fawzi, A., & Frossard, P. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.282 · Cited by 5,317
“Similarly to the binary case, we first present the proposed approach for the linear case and then we generalize it to other classifiers.”
MethodDeep Learning for Generic Object Detection: A Survey
Liu, L., Ouyang, W., Wang, X., Fieguth, P., Chen, J., Liu, X., & Pietikäinen, M. (2018) · arXiv · doi:10.48550/arxiv.1809.02165 · Cited by 2,965
Deep Learning for Generic Object Detection: A Survey
Liu, L., Ouyang, W., Wang, X., Fieguth, P., Chen, J., Liu, X., & Pietikäinen, M. (2020) · International Journal of Computer Vision · doi:10.1007/s11263-019-01247-4 · Cited by 2,965
“These modalities raise new challenges in effectively using depth (Chen et al. 2015c; Pepik et al. 2015; Xiang et al. 2014; Wu et al. 2015), video (Feichtenhofer et al.”
BackgroundR-CNN for Small Object Detection
Chen, C., Liu, M.-Y., Tuzel, O., & Xiao, J. (2017) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-54193-8_14 · Cited by 392
On the Robustness of Semantic Segmentation Models to Adversarial Attacks
Arnab, A., Miksik, O., & Torr, P. H. S. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00099 · Cited by 319
Metadata
- Authors
- Pepik, B., Benenson, R., Ritschel, T., & Schiele, B.
- Venue
- Lecture Notes in Computer Science
- Publisher
- Springer International Publishing
- Published
- 2015
- Pages
- 517-528
- ISSN
- 0302-9743 (ISSN-L)
- 1611-3349
- OpenAlex
- W1769599646
- Cited by
- 43
- References
- 15
- FWCI
- 4.16
- Type
- conference paper
- Language
- en
- Open access
- hybrid
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: What Is Holding Back Convnets for Detection? https://app.cochat.ai/papers/10.1007/978-3-319-24947-6_43
- The paper
- Pepik, B., Benenson, R., Ritschel, T., & Schiele, B. (2015). What Is Holding Back Convnets for Detection? Lecture Notes in Computer Science. https://doi.org/10.1007/978-3-319-24947-6_43
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.