MearcAll papers

arXiv 1506.02640 · cs.CV

You Only Look Once: Unified, Real-Time Object Detection

Joseph Redmon, Santosh Divvala, Ross Girshick, Ali Farhadi

Claims were extracted automatically by reducer-1 on 2026-11-12. The paper's license does not allow republishing it, so long claims are shortened to a quotation. Read the full text on arXiv.

No reproduction recordedclm_e11e560b
We present YOLO, a new approach to object detection.

Abstract · page 1 · Automated extraction, not reviewed · 0 reviewed reproductions

No reproduction recordedres_74ea5374
A smaller version of the network, Fast YOLO, processes an astounding 155 frames per second while still achieving double the mAP of other real-time detectors.

Abstract · page 1 · Automated extraction, not reviewed · 0 reviewed reproductions

No reproduction recordedclm_bf1f92db
It outperforms other detection methods, including DPM and R-CNN, when generalizing from natural images to other domains like artwork.

Abstract · page 1 · Automated extraction, not reviewed · 0 reviewed reproductions

No reproduction recordedclm_9602769f
When trained on natural images and tested on artwork, YOLO outperforms top detection methods like DPM and R-CNN by a wide margin.

Introduction · page 2 · Automated extraction, not reviewed · 0 reviewed reproductions

No reproduction recordedres_0e8c9196
We train this network for approximately a week and achieve a single crop top-5 accuracy of 88% on the ImageNet 2012 validation set, comparable to the GoogLeNet models in Caffe’s … (excerpt)

Training · page 3 · Automated extraction, not reviewed · 0 reviewed reproductions

No reproduction recordedclm_8c167175
Based on the different error profiles we show that YOLO can be used to rescore Fast R-CNN detections and reduce the errors from background false positives, giving a significant performance … (excerpt)

Experiments · page 5 · Automated extraction, not reviewed · 0 reviewed reproductions

No reproduction recordedclm_519f29ec
Finally, we show that YOLO generalizes to new domains better than other detectors on two artwork datasets.

Experiments · page 5 · Automated extraction, not reviewed · 0 reviewed reproductions

No reproduction recordedres_e07c99ba
The recent Faster R-CNN replaces selective search with a neural network to propose bounding boxes, similar to Szegedy et al. [8] In our tests, their most accurate model achieves 7 … (excerpt)

Comparison to Other Real-Time Systems · page 6 · Automated extraction, not reviewed · 0 reviewed reproductions

No reproduction recordedres_eed02e77
The VGG-16 version of Faster R-CNN is 10 mAP higher but is also 6 times slower than YOLO.

Comparison to Other Real-Time Systems · page 6 · Automated extraction, not reviewed · 0 reviewed reproductions

No reproduction recordedclm_493f601b
To further examine the differences between YOLO and state-of-the-art detectors, we look at a detailed breakdown of results on VOC 2007.

VOC 2007 Error Analysis · page 6 · Automated extraction, not reviewed · 0 reviewed reproductions

No reproduction recordedres_95bb66d9
The best Fast R-CNN model achieves a mAP of 71.8% on the VOC 2007 test set.

Combining Fast R-CNN and YOLO · page 6 · Automated extraction, not reviewed · 0 reviewed reproductions

No reproduction recordedres_80612851
This is lower than the current state of the art, closer to the original R-CNN using VGG-16, see Table 3.

VOC 2012 Results · page 7 · Automated extraction, not reviewed · 0 reviewed reproductions

No reproduction recordedres_24221c17
On categories like bottle, sheep, and tv/monitor YOLO scores 8-10% lower than R-CNN or Feature Edit.

VOC 2012 Results · page 7 · Automated extraction, not reviewed · 0 reviewed reproductions

No reproduction recordedres_9ee16932
Fast R-CNN gets a 2.3% improvement from the combination with YOLO, boosting it 5 spots up on the public leaderboard.

VOC 2012 Results · page 7 · Automated extraction, not reviewed · 0 reviewed reproductions

Reproduced one of these claims?

Record your result in the Mearc app on your own machine, then use Publish this result with this paper's id (1506.02640) and the claim id shown next to the claim. Mearc creates a file that holds only what you choose to publish. Add it to the public claim data by pull request; a maintainer other than you reviews it before it counts.