---
title: "Focal Loss for Dense Object Detection — Lin 2017"
description: "One-stage detectors such as SSD and YOLO scan a dense grid of candidate boxes."
authors: ["Tsung-Yi Lin", "Priya Goyal", "Ross Girshick", "Kaiming He", "Piotr Dollár"]
year: 2017
venue: "arXiv:1708.02002"
source: "https://arxiv.org/abs/1708.02002"
doi: "10.48550/arxiv.1708.02002"
arxiv: "1708.02002"
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/lin-2017-focal-loss-dense-object-detection/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/lin-2017-focal-loss-dense-object-detection/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2017](https://md.research.elamur.ai/free/en/papers/2017/page/2/) / Focal Loss for Dense Object Detection

# Focal Loss for Dense Object Detection

**Authors:** [Tsung-Yi Lin](https://md.research.elamur.ai/free/en/authors/tsung-yi-lin/), Priya Goyal, [Ross Girshick](https://md.research.elamur.ai/free/en/authors/ross-girshick/), [Kaiming He](https://md.research.elamur.ai/free/en/authors/kaiming-he/), [Piotr Dollár](https://md.research.elamur.ai/free/en/authors/piotr-dollar/) · **Year:** 2017 · **Venue:** arXiv:1708.02002 · **Licence:** [arXiv — non-exclusive licence to distribute](http://arxiv.org/licenses/nonexclusive-distrib/1.0/)

**Links:** [Publisher's page](https://arxiv.org/abs/1708.02002) · [PDF](https://arxiv.org/pdf/1708.02002) · [DOI 10.48550/arxiv.1708.02002](https://doi.org/10.48550/arxiv.1708.02002) · [arXiv 1708.02002](https://arxiv.org/abs/1708.02002) · [OpenAlex](https://openalex.org/W2743473392)

**Citations:** 1222 citations (openalex-snapshot · 2026-10-14) · [645](#cited-by) in our library, of the 140673 papers whose bibliographies we read

## Summary
One-stage detectors such as SSD and YOLO scan a dense grid of candidate boxes. That makes them simpler and faster than proposal-based two-stage systems like Faster R-CNN, but they had been less accurate. The authors argue that the main reason is a severe foreground–background imbalance during training. A dense detector scores around 100k locations per image, and most of them are easy background cases that dominate the loss and the gradients. Earlier work handled this with sampling heuristics or hard example mining. Instead, the paper changes the cross entropy loss by multiplying it by (1 − p_t)^γ. This factor shrinks the penalty for predictions that are already confident and correct, so training concentrates on the hard ones. To test this Focal Loss, the authors built RetinaNet, a plain single-stage network that uses a Feature Pyramid Network backbone and anchor boxes, and evaluated it on COCO. RetinaNet runs about as fast as other one-stage models and beat all previously published single models in accuracy, including two-stage ones. The result points to the training objective, rather than network architecture, as what had been holding dense detectors back.

## Key points
- **Loss definition:** FL(p_t) = −α_t (1 − p_t)^γ log(p_t). With γ = 0 it is the same as cross entropy. γ = 2 worked best, together with α = 0.25. At γ = 2, an example with p_t = 0.9 gets 100× less loss than with CE, and one with p_t ≈ 0.968 gets about 1000× less.
- **Main result:** RetinaNet-101-800 (ResNet-101-FPN) scores 39.1 AP on COCO test-dev at about 5 fps. That is 5.9 AP above the strongest one-stage competitor, DSSD (33.2), and 2.3 AP above the best Faster R-CNN variant (Inception-ResNet-v2-TDM). Switching to a ResNeXt-32x8d-101-FPN backbone raises it to 40.8 AP.
- **Ablations (RetinaNet-50-600):** plain CE reaches 31.1 AP and focal loss 34.0 AP. A single square anchor already gives 30.3 AP, and 9 anchors per location (3 scales × 3 aspect ratios) give 34.0. Adding more anchors beyond that brought no further gain.
- **Form of the loss is flexible:** an alternative version, FL*, with steepness and shift parameters (γ, β), reaches 33.8–33.9 AP, about the same as FL. Any loss that down-weights well-classified examples appears to work.
- **Code:** released in Detectron (github.com/facebookresearch/Detectron).

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

Fields: [Other](https://md.research.elamur.ai/free/en/shelves/other/)

## Cited by

Cited by

645 papers of our library cite it (of the 140673 whose bibliographies we read); 19 of them have a page here, 626 not yet.

- [TTLab at AlexandriaX-2026: A Fine-Tuned Surface Tagger for Arabic Machine-Translation Error-Span Detection and Classification](https://md.research.elamur.ai/free/en/papers/abusaleh-2026-ttlab-alexandriax-2026-fine-tuned/)
- [Findings of the 2021 Conference on Machine Translation (WMT21)](https://md.research.elamur.ai/free/en/papers/akhbardeh-2021-findings-2021-conference-machine-translation/)
- [Improving Arabic Multi-Label Emotion Classification using Stacked Embeddings and Hybrid Loss Function](https://md.research.elamur.ai/free/en/papers/aslam-2024-improving-arabic-multi-label-emotion/)
- [InternLM2 Technical Report](https://md.research.elamur.ai/free/en/papers/cai-2024-internlm2-technical-report/)
- [The IDC System for Sentiment Classification and Sarcasm Detection in Arabic](https://md.research.elamur.ai/free/en/papers/israeli-2021-idc-system-sentiment-classification-sarcasm/)
- [Segment Anything](https://md.research.elamur.ai/free/en/papers/kirillov-2023-segment-anything/)
- [Dice Loss for Data-imbalanced NLP Tasks](https://md.research.elamur.ai/free/en/papers/li-2020-dice-loss-data-imbalanced-nlp/)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://md.research.elamur.ai/free/en/papers/liu-2023-grounding-dino-marrying-dino-grounded/)
- [Skywork-Reward: Bag of Tricks for Reward Modeling in LLMs](https://md.research.elamur.ai/free/en/papers/liu-2024-skywork-reward-bag-tricks/)
- [System Report for CCL25-Eval Task 4: Prompting, Scheduling, and Arbitration Strategies for Chinese Factivity Inference](https://md.research.elamur.ai/free/en/papers/liu-2025-system-report-ccl25-eval-task/)
- [Multi-Label Classification for Implicit Discourse Relation Recognition](https://md.research.elamur.ai/free/en/papers/long-2024-multi-label-classification-implicit-discourse/)
- [Inter-GPS: Interpretable Geometry Problem Solving with Formal Language and Symbolic Reasoning](https://md.research.elamur.ai/free/en/papers/lu-2021-inter-gps-interpretable-geometry-problem/)
- [End-to-End Bias Mitigation by Modelling Biases in Corpora](https://md.research.elamur.ai/free/en/papers/mahabadi-2020-end-end-bias-mitigation-modelling/)
- [CS-UM6P at SemEval-2022 Task 6: Transformer-based Models for Intended Sarcasm Detection in English and Arabic](https://md.research.elamur.ai/free/en/papers/mahdaouy-2022-cs-um6p-semeval-2022-task/)
- [Deep Multi-Task Models for Misogyny Identification and Categorization on Arabic Social Media](https://md.research.elamur.ai/free/en/papers/mahdaouy-2022-deep-multi-task-models-misogyny/)
- [COMICORDA: Dialogue Act Recognition in Comic Books](https://md.research.elamur.ai/free/en/papers/martinek-2024-comicorda-dialogue-act-recognition-comic/)
- [SPARTQA: A Textual Question Answering Benchmark for Spatial Reasoning](https://md.research.elamur.ai/free/en/papers/mirzaee-2021-spartqa-textual-question-answering-benchmark/)
- [Stanceosaurus: Classifying Stance Towards Multilingual Misinformation](https://md.research.elamur.ai/free/en/papers/zheng-2022-stanceosaurus-classifying-stance-towards-multilingual/)
- [Learning Transferable Architectures for Scalable Image Recognition](https://md.research.elamur.ai/free/en/papers/zoph-2017-learning-transferable-architectures-scalable-image/)

## Cite

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

```bibtex
@misc{lin2017focal,
  title = {{Focal Loss for Dense Object Detection}},
  author = {Lin, Tsung-Yi and Goyal, Priya and Girshick, Ross and He, Kaiming and Dollár, Piotr},
  year = {2017},
  doi = {10.48550/arxiv.1708.02002},
  eprint = {1708.02002},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.1708.02002}
}
```

- [← previous Fixing the Infix: Unsupervised Discovery of Root-and-Pattern Morphology](https://md.research.elamur.ai/free/en/papers/langstream-2017-sakakini-fixing-infix-unsupervised-discovery-root/)
- [next → Frame-Semantic Parsing with Softmax-Margin Segmental RNNs and a Syntactic Scaffold](https://md.research.elamur.ai/free/en/papers/swayamdipta-2017-frame-semantic-parsing-softmax-margin/)
- [↑ back to papers of 2017](https://md.research.elamur.ai/free/en/papers/2017/page/2/)

## References

39 references, 3 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. S. Bell, C. L. Zitnick, K. Bala, and R. Girshick. Inside-outside net: Detecting objects in context with skip pooling and recurrent neural networks. In CVPR, 2016. 6 [find](https://scholar.google.com/scholar?q=S%2E+Bell%2C+C%2E+L%2E+Zitnick%2C+K%2E+Bala%2C+and+R%2E+Girshick%2E+Inside%2Doutside+net%3A+Detecting+objects+in+context+with+skip+pooling+and+recurrent+neural+networks%2E+In+CVPR%2C+2016%2E+6)
2. S. R. Bulo, G. Neuhold, and P. Kontschieder. Loss max-pooling for semantic image segmentation. In CVPR, 2017. 3 [find](https://scholar.google.com/scholar?q=S%2E+R%2E+Bulo%2C+G%2E+Neuhold%2C+and+P%2E+Kontschieder%2E+Loss+max%2Dpooling+for+semantic+image+segmentation%2E+In+CVPR%2C+2017%2E+3)
3. J. Dai, Y. Li, K. He, and J. Sun. R-FCN: Object detection via region-based fully convolutional networks. In NIPS, 2016. 1 [find](https://scholar.google.com/scholar?q=J%2E+Dai%2C+Y%2E+Li%2C+K%2E+He%2C+and+J%2E+Sun%2E+R%2DFCN%3A+Object+detection+via+region%2Dbased+fully+convolutional+networks%2E+In+NIPS%2C+2016%2E+1)
4. N. Dalal and B. Triggs. Histograms of oriented gradients for human detection. In CVPR, 2005. 2 [find](https://scholar.google.com/scholar?q=N%2E+Dalal+and+B%2E+Triggs%2E+Histograms+of+oriented+gradients+for+human+detection%2E+In+CVPR%2C+2005%2E+2)
5. P. Dollár, Z. Tu, P. Perona, and S. Belongie. Integral channel features. In BMVC, 2009. 2, 3 [find](https://scholar.google.com/scholar?q=P%2E+Dolla%CC%81r%2C+Z%2E+Tu%2C+P%2E+Perona%2C+and+S%2E+Belongie%2E+Integral+channel+features%2E+In+BMVC%2C+2009%2E+2%2C+3)
6. D. Erhan, C. Szegedy, A. Toshev, and D. Anguelov. Scalable object detection using deep neural networks. In CVPR, 2014. 2 [find](https://scholar.google.com/scholar?q=D%2E+Erhan%2C+C%2E+Szegedy%2C+A%2E+Toshev%2C+and+D%2E+Anguelov%2E+Scalable+object+detection+using+deep+neural+networks%2E+In+CVPR%2C+2014%2E+2)
7. M. Everingham, L. Van Gool, C. K. Williams, J. Winn, and A. Zisserman. The PASCAL Visual Object Classes (VOC) Challenge. IJCV, 2010. 2 [find](https://scholar.google.com/scholar?q=M%2E+Everingham%2C+L%2E+Van+Gool%2C+C%2E+K%2E+Williams%2C+J%2E+Winn%2C+and+A%2E+Zisserman%2E+The+PASCAL+Visual+Object+Classes+%28VOC%29+Challenge%2E+IJCV%2C+2010%2E+2)
8. P. F. Felzenszwalb, R. B. Girshick, and D. McAllester. Cascade object detection with deformable part models. In CVPR, 2010. 2, 3 [find](https://scholar.google.com/scholar?q=P%2E+F%2E+Felzenszwalb%2C+R%2E+B%2E+Girshick%2C+and+D%2E+McAllester%2E+Cascade+object+detection+with+deformable+part+models%2E+In+CVPR%2C+2010%2E+2%2C+3)
9. C.-Y. Fu, W. Liu, A. Ranga, A. Tyagi, and A. C. Berg. DSSD: Deconvolutional single shot detector. arXiv:1701.06659, 2016. 1, 2, 8 — [arXiv:1701.06659](https://arxiv.org/abs/1701.06659) [find](https://scholar.google.com/scholar?q=C%2E%2DY%2E+Fu%2C+W%2E+Liu%2C+A%2E+Ranga%2C+A%2E+Tyagi%2C+and+A%2E+C%2E+Berg%2E+DSSD%3A+Deconvolutional+single+shot+detector%2E+arXiv%3A1701%2E06659%2C+2016%2E+1%2C+2%2C+8+%E2%80%94+%5BarXiv%3A1701%2E06659%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F1701%2E06659%29)
10. R. Girshick. Fast R-CNN. In ICCV, 2015. 1, 2, 4, 6, 8 [find](https://scholar.google.com/scholar?q=R%2E+Girshick%2E+Fast+R%2DCNN%2E+In+ICCV%2C+2015%2E+1%2C+2%2C+4%2C+6%2C+8)
11. R. Girshick, J. Donahue, T. Darrell, and J. Malik. Rich feature hierarchies for accurate object detection and semantic segmentation. In CVPR, 2014. 1, 2, 5 [find](https://scholar.google.com/scholar?q=R%2E+Girshick%2C+J%2E+Donahue%2C+T%2E+Darrell%2C+and+J%2E+Malik%2E+Rich+feature+hierarchies+for+accurate+object+detection+and+semantic+segmentation%2E+In+CVPR%2C+2014%2E+1%2C+2%2C+5) [our card](https://md.research.elamur.ai/free/en/papers/girshick-2013-rich-feature-hierarchies-accurate-object/)
12. R. Girshick, I. Radosavovic, G. Gkioxari, P. Dollár, and K. He. Detectron. [https://github.com/facebookresearch/detectron](https://github.com/facebookresearch/detectron), 2018. 8 [↗](https://github.com/facebookresearch/detectron)
13. T. Hastie, R. Tibshirani, and J. Friedman. The elements of statistical learning. Springer series in statistics Springer, Berlin, 2008. 3, 7 [find](https://scholar.google.com/scholar?q=T%2E+Hastie%2C+R%2E+Tibshirani%2C+and+J%2E+Friedman%2E+The+elements+of+statistical+learning%2E+Springer+series+in+statistics+Springer%2C+Berlin%2C+2008%2E+3%2C+7)
14. K. He, G. Gkioxari, P. Dollár, and R. Girshick. Mask R-CNN. In ICCV, 2017. 1, 2, 4 [find](https://scholar.google.com/scholar?q=K%2E+He%2C+G%2E+Gkioxari%2C+P%2E+Dolla%CC%81r%2C+and+R%2E+Girshick%2E+Mask+R%2DCNN%2E+In+ICCV%2C+2017%2E+1%2C+2%2C+4)
15. K. He, X. Zhang, S. Ren, and J. Sun. Spatial pyramid pooling in deep convolutional networks for visual recognition. In ECCV. 2014. 2 [find](https://scholar.google.com/scholar?q=K%2E+He%2C+X%2E+Zhang%2C+S%2E+Ren%2C+and+J%2E+Sun%2E+Spatial+pyramid+pooling+in+deep+convolutional+networks+for+visual+recognition%2E+In+ECCV%2E+2014%2E+2)
16. K. He, X. Zhang, S. Ren, and J. Sun. Deep residual learning for image recognition. In CVPR, 2016. 2, 4, 5, 6, 8 [find](https://scholar.google.com/scholar?q=K%2E+He%2C+X%2E+Zhang%2C+S%2E+Ren%2C+and+J%2E+Sun%2E+Deep+residual+learning+for+image+recognition%2E+In+CVPR%2C+2016%2E+2%2C+4%2C+5%2C+6%2C+8)
17. J. Huang, V. Rathod, C. Sun, M. Zhu, A. Korattikara, A. Fathi, I. Fischer, Z. Wojna, Y. Song, S. Guadarrama, and K. Murphy. Speed/accuracy trade-offs for modern convolutional object detectors. In CVPR, 2017. 2, 8 [find](https://scholar.google.com/scholar?q=J%2E+Huang%2C+V%2E+Rathod%2C+C%2E+Sun%2C+M%2E+Zhu%2C+A%2E+Korattikara%2C+A%2E+Fathi%2C+I%2E+Fischer%2C+Z%2E+Wojna%2C+Y%2E+Song%2C+S%2E+Guadarrama%2C+and+K%2E+Murphy%2E+Speed%2Faccuracy+trade%2Doffs+for+modern+convolutional+object+detectors%2E+In+CVPR)
18. A. Krizhevsky, I. Sutskever, and G. Hinton. ImageNet classification with deep convolutional neural networks. In NIPS, 2012. 2 [find](https://scholar.google.com/scholar?q=A%2E+Krizhevsky%2C+I%2E+Sutskever%2C+and+G%2E+Hinton%2E+ImageNet+classification+with+deep+convolutional+neural+networks%2E+In+NIPS%2C+2012%2E+2)
19. Y. LeCun, B. Boser, J. S. Denker, D. Henderson, R. E. Howard, W. Hubbard, and L. D. Jackel. Backpropagation applied to handwritten zip code recognition. Neural computation, 1989. 2 [find](https://scholar.google.com/scholar?q=Y%2E+LeCun%2C+B%2E+Boser%2C+J%2E+S%2E+Denker%2C+D%2E+Henderson%2C+R%2E+E%2E+Howard%2C+W%2E+Hubbard%2C+and+L%2E+D%2E+Jackel%2E+Backpropagation+applied+to+handwritten+zip+code+recognition%2E+Neural+computation%2C+1989%2E+2)
20. T.-Y. Lin, P. Dollár, R. Girshick, K. He, B. Hariharan, and S. Belongie. Feature pyramid networks for object detection. In CVPR, 2017. 1, 2, 4, 5, 6, 8 [find](https://scholar.google.com/scholar?q=T%2E%2DY%2E+Lin%2C+P%2E+Dolla%CC%81r%2C+R%2E+Girshick%2C+K%2E+He%2C+B%2E+Hariharan%2C+and+S%2E+Belongie%2E+Feature+pyramid+networks+for+object+detection%2E+In+CVPR%2C+2017%2E+1%2C+2%2C+4%2C+5%2C+6%2C+8)
21. T.-Y. Lin, M. Maire, S. Belongie, J. Hays, P. Perona, D. Ramanan, P. Dollár, and C. L. Zitnick. Microsoft COCO: Common objects in context. In ECCV, 2014. 1, 6 [find](https://scholar.google.com/scholar?q=T%2E%2DY%2E+Lin%2C+M%2E+Maire%2C+S%2E+Belongie%2C+J%2E+Hays%2C+P%2E+Perona%2C+D%2E+Ramanan%2C+P%2E+Dolla%CC%81r%2C+and+C%2E+L%2E+Zitnick%2E+Microsoft+COCO%3A+Common+objects+in+context%2E+In+ECCV%2C+2014%2E+1%2C+6) [our card](https://md.research.elamur.ai/free/en/papers/lin-2014-microsoft-coco-common-objects-context/)
22. W. Liu, D. Anguelov, D. Erhan, C. Szegedy, and S. Reed. SSD: Single shot multibox detector. In ECCV, 2016. 1, 2, 3, 6, 7, 8 [find](https://scholar.google.com/scholar?q=W%2E+Liu%2C+D%2E+Anguelov%2C+D%2E+Erhan%2C+C%2E+Szegedy%2C+and+S%2E+Reed%2E+SSD%3A+Single+shot+multibox+detector%2E+In+ECCV%2C+2016%2E+1%2C+2%2C+3%2C+6%2C+7%2C+8)
23. J. Long, E. Shelhamer, and T. Darrell. Fully convolutional networks for semantic segmentation. In CVPR, 2015. 4 [find](https://scholar.google.com/scholar?q=J%2E+Long%2C+E%2E+Shelhamer%2C+and+T%2E+Darrell%2E+Fully+convolutional+networks+for+semantic+segmentation%2E+In+CVPR%2C+2015%2E+4)
24. P. O. Pinheiro, R. Collobert, and P. Dollar. Learning to segment object candidates. In NIPS, 2015. 2, 4 [find](https://scholar.google.com/scholar?q=P%2E+O%2E+Pinheiro%2C+R%2E+Collobert%2C+and+P%2E+Dollar%2E+Learning+to+segment+object+candidates%2E+In+NIPS%2C+2015%2E+2%2C+4)
25. P. O. Pinheiro, T.-Y. Lin, R. Collobert, and P. Dollár. Learning to refine object segments. In ECCV, 2016. 2 [find](https://scholar.google.com/scholar?q=P%2E+O%2E+Pinheiro%2C+T%2E%2DY%2E+Lin%2C+R%2E+Collobert%2C+and+P%2E+Dolla%CC%81r%2E+Learning+to+refine+object+segments%2E+In+ECCV%2C+2016%2E+2)
26. J. Redmon, S. Divvala, R. Girshick, and A. Farhadi. You only look once: Unified, real-time object detection. In CVPR, 2016. 1, 2 [find](https://scholar.google.com/scholar?q=J%2E+Redmon%2C+S%2E+Divvala%2C+R%2E+Girshick%2C+and+A%2E+Farhadi%2E+You+only+look+once%3A+Unified%2C+real%2Dtime+object+detection%2E+In+CVPR%2C+2016%2E+1%2C+2)
27. J. Redmon and A. Farhadi. YOLO9000: Better, faster, stronger. In CVPR, 2017. 1, 2, 8 [find](https://scholar.google.com/scholar?q=J%2E+Redmon+and+A%2E+Farhadi%2E+YOLO9000%3A+Better%2C+faster%2C+stronger%2E+In+CVPR%2C+2017%2E+1%2C+2%2C+8)
28. S. Ren, K. He, R. Girshick, and J. Sun. Faster R-CNN: Towards real-time object detection with region proposal networks. In NIPS, 2015. 1, 2, 4, 5, 8 [find](https://scholar.google.com/scholar?q=S%2E+Ren%2C+K%2E+He%2C+R%2E+Girshick%2C+and+J%2E+Sun%2E+Faster+R%2DCNN%3A+Towards+real%2Dtime+object+detection+with+region+proposal+networks%2E+In+NIPS%2C+2015%2E+1%2C+2%2C+4%2C+5%2C+8) [our card](https://md.research.elamur.ai/free/en/papers/ren-2015-faster-r-cnn-towards-real/)
29. H. Rowley, S. Baluja, and T. Kanade. Human face detection in visual scenes. Technical Report CMU-CS-95-158R, Carnegie Mellon University, 1995. 2 [find](https://scholar.google.com/scholar?q=H%2E+Rowley%2C+S%2E+Baluja%2C+and+T%2E+Kanade%2E+Human+face+detection+in+visual+scenes%2E+Technical+Report+CMU%2DCS%2D95%2D158R%2C+Carnegie+Mellon+University%2C+1995%2E+2)
30. P. Sermanet, D. Eigen, X. Zhang, M. Mathieu, R. Fergus, and Y. LeCun. Overfeat: Integrated recognition, localization and detection using convolutional networks. In ICLR, 2014. 2 [find](https://scholar.google.com/scholar?q=P%2E+Sermanet%2C+D%2E+Eigen%2C+X%2E+Zhang%2C+M%2E+Mathieu%2C+R%2E+Fergus%2C+and+Y%2E+LeCun%2E+Overfeat%3A+Integrated+recognition%2C+localization+and+detection+using+convolutional+networks%2E+In+ICLR%2C+2014%2E+2)
31. A. Shrivastava, A. Gupta, and R. Girshick. Training region-based object detectors with online hard example mining. In CVPR, 2016. 2, 3, 6, 7 [find](https://scholar.google.com/scholar?q=A%2E+Shrivastava%2C+A%2E+Gupta%2C+and+R%2E+Girshick%2E+Training+region%2Dbased+object+detectors+with+online+hard+example+mining%2E+In+CVPR%2C+2016%2E+2%2C+3%2C+6%2C+7)
32. A. Shrivastava, R. Sukthankar, J. Malik, and A. Gupta. Beyond skip connections: Top-down modulation for object detection. arXiv:1612.06851, 2016. 2, 8 — [arXiv:1612.06851](https://arxiv.org/abs/1612.06851) [find](https://scholar.google.com/scholar?q=A%2E+Shrivastava%2C+R%2E+Sukthankar%2C+J%2E+Malik%2C+and+A%2E+Gupta%2E+Beyond+skip+connections%3A+Top%2Ddown+modulation+for+object+detection%2E+arXiv%3A1612%2E06851%2C+2016%2E+2%2C+8+%E2%80%94+%5BarXiv%3A1612%2E06851%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F1612%2E0)
33. K.-K. Sung and T. Poggio. Learning and Example Selection for Object and Pattern Detection. In MIT A.I. Memo No. 1521, 1994. 2, 3 [find](https://scholar.google.com/scholar?q=K%2E%2DK%2E+Sung+and+T%2E+Poggio%2E+Learning+and+Example+Selection+for+Object+and+Pattern+Detection%2E+In+MIT+A%2EI%2E+Memo+No%2E+1521%2C+1994%2E+2%2C+3)
34. C. Szegedy, S. Ioffe, V. Vanhoucke, and A. A. Alemi. Inception-v4, inception-resnet and the impact of residual connections on learning. In AAAI Conference on Artificial Intelligence, 2017. 8 [find](https://scholar.google.com/scholar?q=C%2E+Szegedy%2C+S%2E+Ioffe%2C+V%2E+Vanhoucke%2C+and+A%2E+A%2E+Alemi%2E+Inception%2Dv4%2C+inception%2Dresnet+and+the+impact+of+residual+connections+on+learning%2E+In+AAAI+Conference+on+Artificial+Intelligence%2C+2017%2E+8)
35. J. R. Uijlings, K. E. van de Sande, T. Gevers, and A. W. Smeulders. Selective search for object recognition. IJCV, 2013. 2, 4 [find](https://scholar.google.com/scholar?q=J%2E+R%2E+Uijlings%2C+K%2E+E%2E+van+de+Sande%2C+T%2E+Gevers%2C+and+A%2E+W%2E+Smeulders%2E+Selective+search+for+object+recognition%2E+IJCV%2C+2013%2E+2%2C+4)
36. R. Vaillant, C. Monrocq, and Y. LeCun. Original approach for the localisation of objects in images. IEE Proc. on Vision, Image, and Signal Processing, 1994. 2 [find](https://scholar.google.com/scholar?q=R%2E+Vaillant%2C+C%2E+Monrocq%2C+and+Y%2E+LeCun%2E+Original+approach+for+the+localisation+of+objects+in+images%2E+IEE+Proc%2E+on+Vision%2C+Image%2C+and+Signal+Processing%2C+1994%2E+2)
37. P. Viola and M. Jones. Rapid object detection using a boosted cascade of simple features. In CVPR, 2001. 2, 3 [find](https://scholar.google.com/scholar?q=P%2E+Viola+and+M%2E+Jones%2E+Rapid+object+detection+using+a+boosted+cascade+of+simple+features%2E+In+CVPR%2C+2001%2E+2%2C+3)
38. S. Xie, R. Girshick, P. Dollár, Z. Tu, and K. He. Aggregated residual transformations for deep neural networks. In CVPR, 2017. 8 [find](https://scholar.google.com/scholar?q=S%2E+Xie%2C+R%2E+Girshick%2C+P%2E+Dolla%CC%81r%2C+Z%2E+Tu%2C+and+K%2E+He%2E+Aggregated+residual+transformations+for+deep+neural+networks%2E+In+CVPR%2C+2017%2E+8)
39. C. L. Zitnick and P. Dollár. Edge boxes: Locating object proposals from edges. In ECCV, 2014. 2 [find](https://scholar.google.com/scholar?q=C%2E+L%2E+Zitnick+and+P%2E+Dolla%CC%81r%2E+Edge+boxes%3A+Locating+object+proposals+from+edges%2E+In+ECCV%2C+2014%2E+2)