The performance of any deep learning model depends heavily on the data, using which it has been trained. The quality of the trained deep models improve with the availability of large number of uncorrelated datapoints. If the data available for training is not sufficiently large, the deep models overfit and do not generalize. Evidently, data plays a very crucial role in training any deep neural network model. However, data is ‘precious’, and may not be freely available all the time. Many companies have proprietary rights over their data. For example, models trained by Google and Facebook might utilize proprietary data such as JFT-300M, SFC. Also, the data may not be shared if it contains sensitive information, specially, when dealing with biometric data of large population, healthcare data of patients etc. In a nutshell, data is often more precious than anything else in the era of deep learning and hence efficient utilization of data is of utmost importance. My research work in my PhD, therefore, looked into developing data efficient deep learning algorithms for computer vision tasks and was supported by fellowship from UGC-NET (JRF).
[Sept 2023] Reviewed five papers for WACV 2024.
[Sept 2023] One paper accepted in NeurIPS 2023.
[Aug 2023] Cisco Research Proposal got accepted.
[Aug 2023] One paper accepted in DeCaF, MICCAI Workshop, 2023
[Jun 2023] Reviewed six papers for NeurIPS 2023.
[May 2023] Successfully defended PhD Thesis
[Jan 2023] Joined as PostDoc in CRCV dept at UCF, Florida
[Aug 2022] One paper accepted in WACV 2023
[Apr 2022] One paper accepted in HCIS, CVPR Workshop, 2022
[Dec 2021] Selected for Doctoral Consortium at WACV 2022
[Oct 2021] One paper accepted in WACV 2022 and two papers accepted in BMVC 2021.
[Sept 2021] Our work "Mining Data Impressions from Deep Models as Substitute for the Unavailable Training Data" [Paper] has been accepted in the IEEE Trans. on PAMI journal.
[Jul-Aug-Sept 2021] Reviewed six papers in BMVC 2021 and two papers in WACV 2022
[Feb 2021] Reviewed a paper on Person Reidentification for Pattern Recognition Journal.
[Jan 2021] WACV 2021 - Presented our paper on "Effectiveness of Arbitrary Transfer Sets for Data-free Knowledge Distillation" [Slides]
[Oct 2020] Reviewed two papers for WACV 2021
[Sept 2020] IEEE BigMM 2020 - Presented our paper on "Fusion of Deep and Non-Deep Methods for Fast Super-Resolution of Satellite Images" [Slides]
[June 2020] QIF India 2020 Finalist, presented innovation proposal [Certificate]
[May 2020 - Ongoing] Reviewer for Elsevier Pattern Recognition Journal [Certificate]
[May-June 2020] Reviewed Research Papers for BMVC 2020
[Dec 2019] NCVPRIPG 2019 (Conference on Computer Vision) - Presented our ICML paper on "Zero-Shot Knowledge Distillation" paper in session on "VISION INDIA" [Slides]
[Sep 2019] ICIP 2019 - Presented our paper on "Efficient Person Re-Identification in Videos Using Sequence Lazy Greedy Determinantal Point Process (SLGDPP)" paper [Poster]
[2019-2021] Appointed as Chair IEEE-IISc joint student chapter, Computational Intelligence and Computer Society.