Title | ||
---|---|---|
Fast and Accurate Quantized Camera Scene Detection on Smartphones, Mobile AI 2021 Challenge: Report |
Abstract | ||
---|---|---|
Camera scene detection is among the most popular computer vision problem on smartphones. While many custom solutions were developed for this task by phone vendors, none of the designed models were available publicly up until now. To address this problem, we introduce the first Mobile AI challenge, where the target is to develop quantized deep learning-based camera scene classification solutions that can demonstrate a real-time performance on smartphones and IoT platforms. For this, the participants were provided with a large-scale CamSDD dataset consisting of more than 11K images belonging to the 30 most important scene categories. The runtime of all models was evaluated on the popular Apple Bionic A11 platform that can be found in many iOS devices. The proposed solutions are fully compatible with all major mobile AI accelerators and can demonstrate more than 100-200 FPS on the majority of recent smartphone platforms while achieving a top-3 accuracy of more than 98%. A detailed description of all models developed in the challenge is provided in this paper. |
Year | DOI | Venue |
---|---|---|
2021 | 10.1109/CVPRW53098.2021.00289 | 2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGITION WORKSHOPS (CVPRW 2021) |
DocType | ISSN | Citations |
Conference | 2160-7508 | 0 |
PageRank | References | Authors |
0.34 | 0 | 31 |
Name | Order | Citations | PageRank |
---|---|---|---|
Andrey Ignatov | 1 | 30 | 6.66 |
Grigory Malivenko | 2 | 0 | 0.68 |
Radu Timofte | 3 | 1880 | 118.45 |
Sheng Chen | 4 | 0 | 0.34 |
Xin Xia | 5 | 0 | 0.68 |
Zhaoyan Liu | 6 | 0 | 0.34 |
Yuwei Zhang | 7 | 0 | 0.34 |
Feng Zhu | 8 | 0 | 0.34 |
Jiashi Li | 9 | 0 | 0.34 |
Xuefeng Xiao | 10 | 0 | 1.01 |
Yuan Tian | 11 | 0 | 0.34 |
Xinglong Wu | 12 | 0 | 0.34 |
Christos Kyrkou | 13 | 0 | 0.68 |
Yixin Chen | 14 | 4326 | 299.19 |
Zexin Zhang | 15 | 0 | 1.01 |
Yunbo Peng | 16 | 1 | 1.41 |
Yue Lin | 17 | 1 | 1.41 |
Saikat Dutta | 18 | 0 | 0.68 |
Sourya Dipta Das | 19 | 7 | 4.47 |
Nisarg Shah | 20 | 5 | 3.46 |
Himanshu Kumar | 21 | 27 | 6.10 |
Chao Ge | 22 | 0 | 0.68 |
Pei-Lin Wu | 23 | 0 | 0.68 |
Jin-Hua Du | 24 | 0 | 0.68 |
Andrew Batutin | 25 | 0 | 0.34 |
Juan Pablo Federico | 26 | 0 | 0.34 |
Konrad Lyda | 27 | 0 | 0.34 |
Levon Khojoyan | 28 | 0 | 0.34 |
Abhishek Thanki | 29 | 0 | 0.34 |
Sayak Paul | 30 | 3 | 1.40 |
Shahid Siddiqui | 31 | 0 | 0.34 |