1 code implementation • 22 Jun 2023 • Ganesh Tata, Katyani Singh, Eric Van Oeveren, Nilanjan Ray
In this work, we propose two sample selection algorithms to train an OCR preprocessor with less than 10% of the original system's OCR engine queries, resulting in more than 60% reduction of the total training time without significant loss of accuracy.
no code implementations • 12 Oct 2022 • Ganesh Tata, Gautham Krishna Gudur, Gopinath Chennupati, Mohammad Emtiyaz Khan
Calibration can reduce overconfident predictions of deep neural networks, but can calibration also accelerate training?
1 code implementation • 16 Aug 2022 • Preetam Anbukarasu, Shailesh Nanisetty, Ganesh Tata, Nilanjan Ray
Further, a hybrid pipeline consisting of the upsampler and classifier, followed by a peak detection algorithm was developed.