---
title: "DeCAF — paper by Donahue et al. (2013) — summary and ideas"
description: "The paper asks whether the internal activations of a large convolutional network… 58.75% accuracy. 45 references, cited by 170 papers here."
authors: ["Jeff Donahue", "Yangqing Jia", "Oriol Vinyals", "Judy Hoffman", "Ning Zhang", "Eric Tzeng", "Trevor Darrell"]
year: 2013
venue: "arXiv:1310.1531"
source: "https://arxiv.org/abs/1310.1531"
doi: "10.48550/arxiv.1310.1531"
arxiv: "1310.1531"
licence: "arXiv — non-exclusive licence to distribute"
licence_url: "http://arxiv.org/licenses/nonexclusive-distrib/1.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/donahue-2013-decaf-deep-convolutional-activation-feature/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/donahue-2013-decaf-deep-convolutional-activation-feature/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2013](https://md.research.elamur.ai/free/en/papers/2013/) / DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition

# DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition

**Authors:** [Jeff Donahue](https://md.research.elamur.ai/free/en/authors/jeff-donahue/), [Yangqing Jia](https://md.research.elamur.ai/free/en/authors/yangqing-jia/), [Oriol Vinyals](https://md.research.elamur.ai/free/en/authors/oriol-vinyals/), [Judy Hoffman](https://md.research.elamur.ai/free/en/authors/judy-hoffman/), [Ning Zhang](https://md.research.elamur.ai/free/en/authors/ning-zhang/), Eric Tzeng and [Trevor Darrell](https://md.research.elamur.ai/free/en/authors/trevor-jackson-darrell/) · **Year:** 2013 · **Venue:** arXiv:1310.1531 · **Licence:** [arXiv — non-exclusive licence to distribute](http://arxiv.org/licenses/nonexclusive-distrib/1.0/)

**Links:** [Publisher's page](https://arxiv.org/abs/1310.1531) · [PDF](https://arxiv.org/pdf/1310.1531) · [DOI 10.48550/arxiv.1310.1531](https://doi.org/10.48550/arxiv.1310.1531) · [arXiv 1310.1531](https://arxiv.org/abs/1310.1531) · [OpenAlex](https://openalex.org/W2155541015)

**Citations:** 3,293 citations (OpenAlex, 2026-10-14) · [170](https://md.research.elamur.ai/free/en/papers/donahue-2013-decaf-deep-convolutional-activation-feature/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
The paper asks whether the internal activations of a large convolutional network, trained with full supervision on ImageNet object classes, can serve as a ready-made image descriptor for different vision problems that lack enough data to train deep models. The authors retrain the Krizhevsky et al. (2012) architecture (five convolutional and three fully-connected layers) on ILSVRC-2012. They then freeze it and use activations from various layers as fixed features, with no fine-tuning. Simple classifiers are trained on top. They compare these features with hand-crafted descriptors such as GIST and LLC using t-SNE plots, and test them on object recognition (Caltech-101), domain adaptation (Office), fine-grained bird classification (Caltech-UCSD Birds) and scene recognition (SUN-397). The deep features, especially from the upper hidden layers, group images by semantic category more clearly than traditional descriptors. They also beat prior state-of-the-art pipelines, including multi-kernel combinations of many engineered features. The work matters because it established pretrained CNN activations as a generic off-the-shelf representation. It also released the code and weights publicly as DeCAF.

## Key points
- The authors' single instance of the model reaches 42.9% top-1 error on the ILSVRC-2012 validation set, compared with 40.7% for the original single model. Inputs are 224×224 crops of images warped to 256×256.
- The open-source Python/C implementation, decaf, runs on CPU and processes roughly 40 images per second on an 8-core machine. It is released together with the trained network parameters.
- On Caltech-UCSD Birds, DeCAF6 alone reaches 58.75% accuracy. Combining it with the part-based DPD pipeline gives 64.96%, versus 50.98% for DPD and 56.78% for POOF.
- On SUN-397 (50 train / 50 test images per class), the best setting, using DeCAF7 features, scores 40.94%. The previous best of 38.0% (Xiao et al., 2010) relied on multi-kernel learning over many features.
- t-SNE visualizations on ILSVRC-2012 validation data and SUN-397 show that deeper layers (e.g., DeCAF6) separate semantic categories much better than DeCAF1, GIST or LLC.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [University of California, Berkeley](https://md.research.elamur.ai/free/en/universities/university-of-california-berkeley/) — University, Berkeley, United States · 209 works · 244,782 citations
- [International Computer Science Institute](https://md.research.elamur.ai/free/en/labs/international-computer-science-institute/) — Research institute, Berkeley, United States · 18 works · 16,608 citations

📚 Shelves (3): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works · [👁️ Computer Vision and Pattern Recognition](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · 3,486 works

## Cite

Cite as: Jeff Donahue, Yangqing Jia, Oriol Vinyals, Judy Hoffman, Ning Zhang, Eric Tzeng and Trevor Darrell. 2013. DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition. arXiv:1310.1531.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@misc{donahue2013decaf,
  title = {{DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition}},
  author = {Jeff Donahue, Yangqing Jia, Oriol Vinyals, Judy Hoffman, Ning Zhang, Eric Tzeng and Trevor Darrell},
  year = {2013},
  doi = {10.48550/arxiv.1310.1531},
  eprint = {1310.1531},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.1310.1531}
}
```

- [← previous Linguistic Regularities in Continuous Space Word Representations](https://md.research.elamur.ai/free/en/papers/mikolov-2013-linguistic-regularities-continuous-space-word/)
- [next → Semantic Parsing on Freebase from Question-Answer Pairs](https://md.research.elamur.ai/free/en/papers/berant-2013-semantic-parsing-freebase-question-answer/)
- [↑ back to papers of 2013](https://md.research.elamur.ai/free/en/papers/2013/)

## References

45 references, 2 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Ando, R. and Zhang, T. A framework for learning predictive structures from multiple tasks and unlabeled data. JMLR, 6, 2005. [find](https://scholar.google.com/scholar?q=Ando%2C+R%2E+and+Zhang%2C+T%2E+A+framework+for+learning+predictive+structures+from+multiple+tasks+and+unlabeled+data%2E+JMLR%2C+6%2C+2005%2E)
2. Argyriou, Andreas, Evgeniou, Theodoros, and Pontil, Massimiliano. Multi-task feature learning. In NIPS, 2006. [find](https://scholar.google.com/scholar?q=Argyriou%2C+Andreas%2C+Evgeniou%2C+Theodoros%2C+and+Pontil%2C+Massimiliano%2E+Multi%2Dtask+feature+learning%2E+In+NIPS%2C+2006%2E)
3. Bay, H., Tuytelaars, T., and Gool, L. Van. SURF: Speeded up robust features. In ECCV, 2006. [find](https://scholar.google.com/scholar?q=Bay%2C+H%2E%2C+Tuytelaars%2C+T%2E%2C+and+Gool%2C+L%2E+Van%2E+SURF%3A+Speeded+up+robust+features%2E+In+ECCV%2C+2006%2E)
4. Berg, A., Deng, J., and Fei-Fei, L. ImageNet large scale visual recognition challenge 2012. 2012. URL [http://www.image-net.org/challenges/LSVRC/2012/](http://www.image-net.org/challenges/LSVRC/2012/). [↗](http://www.image-net.org/challenges/LSVRC/2012/)
5. Berg, T. and Belhumeur, P. POOF: Part-based one-vs-one features for fine-grained categorization, face verification, and attribute estimation. In CVPR, 2013. [find](https://scholar.google.com/scholar?q=Berg%2C+T%2E+and+Belhumeur%2C+P%2E+POOF%3A+Part%2Dbased+one%2Dvs%2Done+features+for+fine%2Dgrained+categorization%2C+face+verification%2C+and+attribute+estimation%2E+In+CVPR%2C+2013%2E)
6. Bo, L., Ren, X., and Fox, D. Kernel descriptors for visual recognition. In NIPS, 2010. [find](https://scholar.google.com/scholar?q=Bo%2C+L%2E%2C+Ren%2C+X%2E%2C+and+Fox%2C+D%2E+Kernel+descriptors+for+visual+recognition%2E+In+NIPS%2C+2010%2E)
7. Bourdev, Lubomir, Maji, Subhransu, and Malik, Jitendra. Describing people: A poselet-based approach to attribute classification. In ICCV, 2011. [find](https://scholar.google.com/scholar?q=Bourdev%2C+Lubomir%2C+Maji%2C+Subhransu%2C+and+Malik%2C+Jitendra%2E+Describing+people%3A+A+poselet%2Dbased+approach+to+attribute+classification%2E+In+ICCV%2C+2011%2E)
8. Caruana, R. Multitask learning. Machine Learning, 28, 1997. [find](https://scholar.google.com/scholar?q=Caruana%2C+R%2E+Multitask+learning%2E+Machine+Learning%2C+28%2C+1997%2E)
9. Chopra, S., Balakrishnan, S., and Gopalan, R. Dlid: Deep learning for domain adaptation by interpolating between domains. In ICML Workshop on Challenges in Representation Learning, 2013. [find](https://scholar.google.com/scholar?q=Chopra%2C+S%2E%2C+Balakrishnan%2C+S%2E%2C+and+Gopalan%2C+R%2E+Dlid%3A+Deep+learning+for+domain+adaptation+by+interpolating+between+domains%2E+In+ICML+Workshop+on+Challenges+in+Representation+Learning%2C+2013%2E)
10. Dalal, N. and Triggs, B. Histograms of oriented gradients for human detection. In CVPR, 2005. [find](https://scholar.google.com/scholar?q=Dalal%2C+N%2E+and+Triggs%2C+B%2E+Histograms+of+oriented+gradients+for+human+detection%2E+In+CVPR%2C+2005%2E)
11. Daume III, H. [Frustratingly easy domain adaptation](https://md.research.elamur.ai/free/en/papers/iii-2007-frustratingly-easy-domain-adaptation/). In ACL, 2007.
12. Deng, J., Dong, W., Socher, R., Li, L., Li, K., and Fei-Fei, L. ImageNet: A Large-Scale Hierarchical Image Database. In CVPR, 2009. [find](https://scholar.google.com/scholar?q=Deng%2C+J%2E%2C+Dong%2C+W%2E%2C+Socher%2C+R%2E%2C+Li%2C+L%2E%2C+Li%2C+K%2E%2C+and+Fei%2DFei%2C+L%2E+ImageNet%3A+A+Large%2DScale+Hierarchical+Image+Database%2E+In+CVPR%2C+2009%2E)
13. Fei-Fei, L., Fergus, R., and Perona, P. Learning generative visual models from few training examples: an incremental Bayesian approach tested on 101 object categories. In CVPR, 2004. [find](https://scholar.google.com/scholar?q=Fei%2DFei%2C+L%2E%2C+Fergus%2C+R%2E%2C+and+Perona%2C+P%2E+Learning+generative+visual+models+from+few+training+examples%3A+an+incremental+Bayesian+approach+tested+on+101+object+categories%2E+In+CVPR%2C+2004%2E)
14. Felzenszwalb, P., Girshick, R., McAllester, D., and Ramanan, D. Object detection with discriminatively trained part-based models. PAMI, 32, 2010. [find](https://scholar.google.com/scholar?q=Felzenszwalb%2C+P%2E%2C+Girshick%2C+R%2E%2C+McAllester%2C+D%2E%2C+and+Ramanan%2C+D%2E+Object+detection+with+discriminatively+trained+part%2Dbased+models%2E+PAMI%2C+32%2C+2010%2E)
15. Fidler, S. and Leonardis, A. Towards scalable representations of object categories: Learning a hierarchy of parts. In CVPR, 2007. [find](https://scholar.google.com/scholar?q=Fidler%2C+S%2E+and+Leonardis%2C+A%2E+Towards+scalable+representations+of+object+categories%3A+Learning+a+hierarchy+of+parts%2E+In+CVPR%2C+2007%2E)
16. Gong, B., Shi, Y., Sha, F., and Grauman, K. Geodesic flow kernel for unsupervised domain adaptation. In CVPR, 2012. [find](https://scholar.google.com/scholar?q=Gong%2C+B%2E%2C+Shi%2C+Y%2E%2C+Sha%2C+F%2E%2C+and+Grauman%2C+K%2E+Geodesic+flow+kernel+for+unsupervised+domain+adaptation%2E+In+CVPR%2C+2012%2E)
17. Hinton, G. and Salakhutdinov, R. Reducing the dimensionality of data with neural networks. Science, 2006. [find](https://scholar.google.com/scholar?q=Hinton%2C+G%2E+and+Salakhutdinov%2C+R%2E+Reducing+the+dimensionality+of+data+with+neural+networks%2E+Science%2C+2006%2E)
18. Hinton, G., Srivastava, N., Krizhevsky, A., Sutskever, I., and Salakhutdinov, R. Improving neural networks by preventing co-adaptation of feature detectors. arXiv preprint arXiv:1207.0580, 2012. [find](https://scholar.google.com/scholar?q=Hinton%2C+G%2E%2C+Srivastava%2C+N%2E%2C+Krizhevsky%2C+A%2E%2C+Sutskever%2C+I%2E%2C+and+Salakhutdinov%2C+R%2E+Improving+neural+networks+by+preventing+co%2Dadaptation+of+feature+detectors%2E+arXiv+preprint+arXiv%3A1207%2E0580%2C+2012%2E)
19. Hoffman, J., Rodner, E., Donahue, J., Saenko, K., and Darrell, T. Efficient learning of domain-invariant image representations. In ICLR, 2013. [find](https://scholar.google.com/scholar?q=Hoffman%2C+J%2E%2C+Rodner%2C+E%2E%2C+Donahue%2C+J%2E%2C+Saenko%2C+K%2E%2C+and+Darrell%2C+T%2E+Efficient+learning+of+domain%2Dinvariant+image+representations%2E+In+ICLR%2C+2013%2E)
20. Hsu, D., Kakade, S., Langford, J., and Zhang, T. Multi-label prediction via compressed sensing. arXiv preprint arXiv:0902.1284, 2009. [find](https://scholar.google.com/scholar?q=Hsu%2C+D%2E%2C+Kakade%2C+S%2E%2C+Langford%2C+J%2E%2C+and+Zhang%2C+T%2E+Multi%2Dlabel+prediction+via+compressed+sensing%2E+arXiv+preprint+arXiv%3A0902%2E1284%2C+2009%2E)
21. Jarrett, K., Kavukcuoglu, K., Ranzato, M., and LeCun, Y. What is the best multi-stage architecture for object recognition? In ICCV, 2009. [find](https://scholar.google.com/scholar?q=Jarrett%2C+K%2E%2C+Kavukcuoglu%2C+K%2E%2C+Ranzato%2C+M%2E%2C+and+LeCun%2C+Y%2E+What+is+the+best+multi%2Dstage+architecture+for+object+recognition%3F+In+ICCV%2C+2009%2E)
22. Kennedy, L. and Hauptmann, A. LSCOM lexicon definitions and annotations (version 1.0). 2006. [find](https://scholar.google.com/scholar?q=Kennedy%2C+L%2E+and+Hauptmann%2C+A%2E+LSCOM+lexicon+definitions+and+annotations+%28version+1%2E0%29%2E+2006%2E)
23. Krizhevsky, A., Sutskever, I., and Hinton, G. E. [ImageNet classification with deep convolutional neural networks](https://md.research.elamur.ai/free/en/papers/krizhevsky-2012-imagenet-classification-deep-convolutional/). In NIPS, 2012.
24. Kulis, B., Saenko, K., and Darrell, T. What you saw is not what you get: Domain adaptation using asymmetric kernel transforms. In CVPR, 2011. [find](https://scholar.google.com/scholar?q=Kulis%2C+B%2E%2C+Saenko%2C+K%2E%2C+and+Darrell%2C+T%2E+What+you+saw+is+not+what+you+get%3A+Domain+adaptation+using+asymmetric+kernel+transforms%2E+In+CVPR%2C+2011%2E)
25. Le, Q., Zou, W., Yeung, S., and Ng, A. Learning hierarchical invariant spatio-temporal features for action recognition with independent subspace analysis. In CVPR, 2011. [find](https://scholar.google.com/scholar?q=Le%2C+Q%2E%2C+Zou%2C+W%2E%2C+Yeung%2C+S%2E%2C+and+Ng%2C+A%2E+Learning+hierarchical+invariant+spatio%2Dtemporal+features+for+action+recognition+with+independent+subspace+analysis%2E+In+CVPR%2C+2011%2E)
26. Le, Q., Ranzato, M., Monga, R., Devin, M., Chen, K., Corrado, G., Dean, J., and Ng, A. Building high-level features using large scale unsupervised learning. In ICML, 2012. [find](https://scholar.google.com/scholar?q=Le%2C+Q%2E%2C+Ranzato%2C+M%2E%2C+Monga%2C+R%2E%2C+Devin%2C+M%2E%2C+Chen%2C+K%2E%2C+Corrado%2C+G%2E%2C+Dean%2C+J%2E%2C+and+Ng%2C+A%2E+Building+high%2Dlevel+features+using+large+scale+unsupervised+learning%2E+In+ICML%2C+2012%2E)
27. LeCun, Y., Boser, B., Denker, J., Henderson, D., Howard, R., Hubbard, W., and Jackel, L. Backpropagation applied to handwritten zip code recognition. Neural Computation, 1989. [find](https://scholar.google.com/scholar?q=LeCun%2C+Y%2E%2C+Boser%2C+B%2E%2C+Denker%2C+J%2E%2C+Henderson%2C+D%2E%2C+Howard%2C+R%2E%2C+Hubbard%2C+W%2E%2C+and+Jackel%2C+L%2E+Backpropagation+applied+to+handwritten+zip+code+recognition%2E+Neural+Computation%2C+1989%2E)
28. LeCun, Y., Bottou, L., Bengio, Y., and Haffner, P. Gradient-based learning applied to document recognition. In IEEE, 1998. [find](https://scholar.google.com/scholar?q=LeCun%2C+Y%2E%2C+Bottou%2C+L%2E%2C+Bengio%2C+Y%2E%2C+and+Haffner%2C+P%2E+Gradient%2Dbased+learning+applied+to+document+recognition%2E+In+IEEE%2C+1998%2E)
29. Li, L., Su, H., Fei-Fei, L., and Xing, E. Object bank: A high-level image representation for scene classification & semantic feature sparsification. In NIPS, 2010. [find](https://scholar.google.com/scholar?q=Li%2C+L%2E%2C+Su%2C+H%2E%2C+Fei%2DFei%2C+L%2E%2C+and+Xing%2C+E%2E+Object+bank%3A+A+high%2Dlevel+image+representation+for+scene+classification+%26+semantic+feature+sparsification%2E+In+NIPS%2C+2010%2E)
30. Mesnil, G., Dauphin, Y., Glorot, X., Rifai, S., Bengio, Y., Goodfellow, I., Lavoie, E., Muller, X., Desjardins, G., Warde-Farley, D., Vincent, P., Courville, A., and Berkgstra, J. Unsupervised and transfer learning challenge: a deep learning approach. JMLR, 27, 2012. [find](https://scholar.google.com/scholar?q=Mesnil%2C+G%2E%2C+Dauphin%2C+Y%2E%2C+Glorot%2C+X%2E%2C+Rifai%2C+S%2E%2C+Bengio%2C+Y%2E%2C+Goodfellow%2C+I%2E%2C+Lavoie%2C+E%2E%2C+Muller%2C+X%2E%2C+Desjardins%2C+G%2E%2C+Warde%2DFarley%2C+D%2E%2C+Vincent%2C+P%2E%2C+Courville%2C+A%2E%2C+and+Berkgstra%2C+J%2E+Unsupervised+and+tra)
31. Oliva, A. and Torralba, A. Modeling the shape of the scene: A holistic representation of the spatial envelope. IJCV, 2001. [find](https://scholar.google.com/scholar?q=Oliva%2C+A%2E+and+Torralba%2C+A%2E+Modeling+the+shape+of+the+scene%3A+A+holistic+representation+of+the+spatial+envelope%2E+IJCV%2C+2001%2E)
32. Quattoni, A., Collins, M., and Darrell, T. Transfer learning for image classication with sparse prototype representations. In CVPR, 2008. [find](https://scholar.google.com/scholar?q=Quattoni%2C+A%2E%2C+Collins%2C+M%2E%2C+and+Darrell%2C+T%2E+Transfer+learning+for+image+classication+with+sparse+prototype+representations%2E+In+CVPR%2C+2008%2E)
33. Raina, R. at, Battle, A., Lee, H., Packer, B., and Ng, A. Self-taught learning: Transfer learning from unlabeled data. In ICML, 2007. [find](https://scholar.google.com/scholar?q=Raina%2C+R%2E+at%2C+Battle%2C+A%2E%2C+Lee%2C+H%2E%2C+Packer%2C+B%2E%2C+and+Ng%2C+A%2E+Self%2Dtaught+learning%3A+Transfer+learning+from+unlabeled+data%2E+In+ICML%2C+2007%2E)
34. Ren, X. and Ramanan, D. Histograms of sparse codes for object detection. In CVPR, 2013. [find](https://scholar.google.com/scholar?q=Ren%2C+X%2E+and+Ramanan%2C+D%2E+Histograms+of+sparse+codes+for+object+detection%2E+In+CVPR%2C+2013%2E)
35. Saenko, K., Kulis, B., Fritz, M., and Darrell, T. Adapting visual category models to new domains. In ECCV, 2010. [find](https://scholar.google.com/scholar?q=Saenko%2C+K%2E%2C+Kulis%2C+B%2E%2C+Fritz%2C+M%2E%2C+and+Darrell%2C+T%2E+Adapting+visual+category+models+to+new+domains%2E+In+ECCV%2C+2010%2E)
36. Singh, S., Gupta, A., and Efros, A. Unsupervised discovery of mid-level discriminative patches. In ECCV, 2012. [find](https://scholar.google.com/scholar?q=Singh%2C+S%2E%2C+Gupta%2C+A%2E%2C+and+Efros%2C+A%2E+Unsupervised+discovery+of+mid%2Dlevel+discriminative+patches%2E+In+ECCV%2C+2012%2E)
37. Thrun, S. Is learning the n-th thing any easier than learning the first? In NIPS, 1996. [find](https://scholar.google.com/scholar?q=Thrun%2C+S%2E+Is+learning+the+n%2Dth+thing+any+easier+than+learning+the+first%3F+In+NIPS%2C+1996%2E)
38. Torralba, A. and Efros, A. Unbiased look at dataset bias. In CVPR, 2011. [find](https://scholar.google.com/scholar?q=Torralba%2C+A%2E+and+Efros%2C+A%2E+Unbiased+look+at+dataset+bias%2E+In+CVPR%2C+2011%2E)
39. Torresani, L., Szummer, M., and Fitzgibbon, A. Efficient object category recognition using classemes. In ECCV. 2010. van der Maaten, L. and Hinton, G. Visualizing data using t-sne. JMLR, 9, 2008. [find](https://scholar.google.com/scholar?q=Torresani%2C+L%2E%2C+Szummer%2C+M%2E%2C+and+Fitzgibbon%2C+A%2E+Efficient+object+category+recognition+using+classemes%2E+In+ECCV%2E+2010%2E+van+der+Maaten%2C+L%2E+and+Hinton%2C+G%2E+Visualizing+data+using+t%2Dsne%2E+JMLR%2C+9%2C+2008%2E)
40. Wang, J., Yang, J., Yu, K., Lv, F., Huang, T., and Gong, Y. Locality-constrained linear coding for image classification. In CVPR, 2010. [find](https://scholar.google.com/scholar?q=Wang%2C+J%2E%2C+Yang%2C+J%2E%2C+Yu%2C+K%2E%2C+Lv%2C+F%2E%2C+Huang%2C+T%2E%2C+and+Gong%2C+Y%2E+Locality%2Dconstrained+linear+coding+for+image+classification%2E+In+CVPR%2C+2010%2E)
41. Welinder, P., Branson, S., Mita, T., Wah, C., Schroff, F., Belongie, S., and Perona, P. Caltech-UCSD Birds 200. Technical Report CNS-TR-2010-001, California Institute of Technology, 2010. [find](https://scholar.google.com/scholar?q=Welinder%2C+P%2E%2C+Branson%2C+S%2E%2C+Mita%2C+T%2E%2C+Wah%2C+C%2E%2C+Schroff%2C+F%2E%2C+Belongie%2C+S%2E%2C+and+Perona%2C+P%2E+Caltech%2DUCSD+Birds+200%2E+Technical+Report+CNS%2DTR%2D2010%2D001%2C+California+Institute+of+Technology%2C+2010%2E)
42. Xiao, J., Hays, J., Ehinger, K., Oliva, A., and Torralba, A. Sun database: Large-scale scene recognition from abbey to zoo. In CVPR, 2010. [find](https://scholar.google.com/scholar?q=Xiao%2C+J%2E%2C+Hays%2C+J%2E%2C+Ehinger%2C+K%2E%2C+Oliva%2C+A%2E%2C+and+Torralba%2C+A%2E+Sun+database%3A+Large%2Dscale+scene+recognition+from+abbey+to+zoo%2E+In+CVPR%2C+2010%2E)
43. Yang, J., L., Y., Tian, Y., Duan, L., and Gao, W. Group-sensitive multiple kernel learning for object categorization. In ICCV, 2009. [find](https://scholar.google.com/scholar?q=Yang%2C+J%2E%2C+L%2E%2C+Y%2E%2C+Tian%2C+Y%2E%2C+Duan%2C+L%2E%2C+and+Gao%2C+W%2E+Group%2Dsensitive+multiple+kernel+learning+for+object+categorization%2E+In+ICCV%2C+2009%2E)
44. Zhang, N., Farrell, R., Iandola, F., and Darrell, T. Deformable part descriptors for fine-grained recognition and attribute prediction. In ICCV, 2013. [find](https://scholar.google.com/scholar?q=Zhang%2C+N%2E%2C+Farrell%2C+R%2E%2C+Iandola%2C+F%2E%2C+and+Darrell%2C+T%2E+Deformable+part+descriptors+for+fine%2Dgrained+recognition+and+attribute+prediction%2E+In+ICCV%2C+2013%2E)
45. Zhu, L., Chen, Y., and Yuille, A. Unsupervised learning of a probabilistic grammar for object detection and parsing. In NIPS, 2007. [find](https://scholar.google.com/scholar?q=Zhu%2C+L%2E%2C+Chen%2C+Y%2E%2C+and+Yuille%2C+A%2E+Unsupervised+learning+of+a+probabilistic+grammar+for+object+detection+and+parsing%2E+In+NIPS%2C+2007%2E)

*Updated 2 November 2026*