48 citations · 54 across the 3 of their papers we have counts for
7 papers
Balancing Uncertainty and Diversity of Samples: Leveraging Diversity of Least, High Confidence Samples for Effective Active Learning
Vipul Arya, S. H. Shabbeer Basha, Srikrishna U N +2
Deep learning models, including Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs), have achieved state-of-the-art performance on various computer vision tasks suc…
HRel: Filter Pruning based on High Relevance between Activation Maps and Class Labels
CH Sarvani, Mrinmoy Ghorai, Shiv Ram Dubey +1
This paper proposes an Information Bottleneck theory based filter pruning method that uses a statistical measure called Mutual Information (MI). The MI between filters and class la…
AutoTune: Automatically Tuning Convolutional Neural Networks for Improved Transfer Learning
S. H. Shabbeer Basha, Sravan Kumar Vinakota, Viswanath Pulabaigari +2
Transfer learning enables solving a specific task having limited data by using the pre-trained deep networks trained on large-scale datasets. Typically, while transferring the lear…
An Information-rich Sampling Technique over Spatio-Temporal CNN for Classification of Human Actions in Videos
S. H. Shabbeer Basha, Viswanath Pulabaigari, Snehasis Mukherjee
We propose a novel scheme for human action recognition in videos, using a 3-dimensional Convolutional Neural Network (3D CNN) based classifier. Traditionally in deep learning based…
AutoFCL: Automatically Tuning Fully Connected Layers for Handling Small Dataset
S. H. Shabbeer Basha, Sravan Kumar Vinakota, Shiv Ram Dubey +2
Deep Convolutional Neural Networks (CNN) have evolved as popular machine learning models for image classification during the past few years, due to their ability to learn the probl…
Impact of Fully Connected Layers on Performance of Convolutional Neural Networks for Image Classification
S. H. Shabbeer Basha, Shiv Ram Dubey, Viswanath Pulabaigari +1
The Convolutional Neural Networks (CNNs), in domains like computer vision, mostly reduced the need for handcrafted features due to its ability to learn the problem-specific feature…