1 code implementation • 8 Jul 2021 • Subhranil Bagchi, Deepti R. Bathula
Different categories of visual stimuli activate different responses in the human brain.
no code implementations • 4 Aug 2021 • Apoorva Sikka, Skand, Jitender Singh Virk, Deepti R. Bathula
Medical imaging datasets are inherently high dimensional with large variability and low sample sizes that limit the effectiveness of deep learning algorithms.
no code implementations • 21 Oct 2021 • Usma Niyaz, Deepti R. Bathula
Knowledge distillation (KD) is an effective model compression technique where a compact student network is taught to mimic the behavior of a complex and highly trained teacher network.
no code implementations • 21 Oct 2021 • Abhishek Singh Sambyal, Narayanan C. Krishnan, Deepti R. Bathula
The proposed method was evaluated on a benchmark medical imaging dataset with image reconstruction as the self-supervised task and segmentation as the image analysis task.
no code implementations • 1 Nov 2021 • Ranjana Roy Chowdhury, Deepti R. Bathula
Conventional PN attributes equal importance to all samples and generates prototypes by simply averaging the support sample embeddings belonging to each class.
no code implementations • 19 Aug 2022 • Ranjana Roy Chowdhury, Deepti R. Bathula
Further, the influence factor of a sample is measured using MMD based on the shift in the distribution in the absence of that sample.
no code implementations • 6 Dec 2022 • Usma Niyaz, Abhishek Singh Sambyal, Deepti R. Bathula
These experimental results demonstrate that knowledge diversification in a combined KD and ML framework outperforms conventional KD or ML techniques (with similar network configuration) that only use predictions with an average improvement of 2%.
no code implementations • 22 Sep 2023 • Abhishek Singh Sambyal, Usma Niyaz, Narayanan C. Krishnan, Deepti R. Bathula
We considered fully supervised training, which is the prevailing approach in the community, as well as rotation-based self-supervised method with and without transfer learning, across various datasets and architecture sizes.