no code implementations • 19 Jan 2024 • Preeti Meena, Himanshu Kumar, Sandeep Yadav
Thus, tasks such as scene classification, identification, indexing, etc., can be performed efficiently using the unique summary.
no code implementations • 17 Aug 2022 • Himanshu Kumar, Abeer Banerjee, Sumeet Saurav, Sanjay Singh
Also, the images suffer from color bleeding and desaturated backgrounds since a single model trained on full image features is insufficient for learning the diverse data modes.
no code implementations • 17 May 2021 • Andrey Ignatov, Grigory Malivenko, Radu Timofte, Sheng Chen, Xin Xia, Zhaoyan Liu, Yuwei Zhang, Feng Zhu, Jiashi Li, Xuefeng Xiao, Yuan Tian, Xinglong Wu, Christos Kyrkou, Yixin Chen, Zexin Zhang, Yunbo Peng, Yue Lin, Saikat Dutta, Sourya Dipta Das, Nisarg A. Shah, Himanshu Kumar, Chao Ge, Pei-Lin Wu, Jin-Hua Du, Andrew Batutin, Juan Pablo Federico, Konrad Lyda, Levon Khojoyan, Abhishek Thanki, Sayak Paul, Shahid Siddiqui
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.
no code implementations • 18 Feb 2021 • Sourya Dipta Das, Nisarg A. Shah, Saikat Dutta, Himanshu Kumar
Custom and natural lighting conditions can be emulated in images of the scene during post-editing.
Ranked #4 on Image Relighting on VIDIT’20 validation set
1 code implementation • 27 Dec 2017 • Aritra Ghosh, Himanshu Kumar, P. S. Sastry
For binary classification there exist theoretical results on loss functions that are robust to label noise.