Related papers: Developing efficient transfer learning strategies …

The development of scene text recognition (STR) in the era of deep learning has been mainly focused on novel architectures of STR models. However, training protocol (i.e., settings of the hyper-parameters involved in the training of STR…

Lightweight convolutional and transformer-based networks are increasingly preferred for real-time image classification, especially on resource-constrained devices. This study evaluates the impact of hyperparameter optimization on the…

This paper presents a novel and sustainable approach for improving beam selection in 5G and beyond networks using transfer learning and Reinforcement Learning (RL). Traditional RL-based beam selection models require extensive training time…

In the context of medical imaging and machine learning, one of the most pressing challenges is the effective adaptation of pre-trained models to specialized medical contexts. Despite the availability of advanced pre-trained models, their…

Scene text recognition in low-resource Indian languages is challenging because of complexities like multiple scripts, fonts, text size, and orientations. In this work, we investigate the power of transfer learning for all the layers of deep…

Deep learning models operating in the image domain are vulnerable to small input perturbations. For years, robustness to such perturbations was pursued by training models from scratch (i.e., with random initializations) using specialized…

Purpose: Neural networks have received recent interest for reconstruction of undersampled MR acquisitions. Ideally network performance should be optimized by drawing the training and testing data from the same domain. In practice, however,…

Deep 3-dimensional (3D) Convolutional Network (ConvNet) has shown promising performance on video recognition tasks because of its powerful spatio-temporal information fusion ability. However, the extremely intensive requirements on memory…

The study explores the integration of transfer learning (TL) with mobile-enabled convolutional neural networks (MbNets) to enhance Arabic Handwritten Character Recognition (AHCR). Addressing challenges like extensive computational…

Modern deep convolutional networks (CNNs) are often criticized for not generalizing under distributional shifts. However, several recent breakthroughs in transfer learning suggest that these networks can cope with severe distribution shifts…

Deep learning has transformed visual data analysis, with Convolutional Neural Networks (CNNs) becoming highly effective in learning meaningful feature representations directly from images. Unlike traditional manual feature engineering…

Point Transformers are near state-of-the-art models for classification, segmentation, and detection tasks on Point Cloud data. They utilize a self attention based mechanism to model large range spatial dependencies between multiple point…

We study the task of robust feature representations, aiming to generalize well on multiple datasets for action recognition. We build our method on Transformers for its efficacy. Although we have witnessed great progress for video action…

Transfer learning is one of the subjects undergoing intense study in the area of machine learning. In object recognition and object detection there are known experiments for the transferability of parameters, but not for neural networks…

We propose a network architecture to perform efficient scene understanding. This work presents three main novelties: the first is an Improved Guided Upsampling Module that can replace in toto the decoder part in common semantic segmentation…

This work proposes a new end-to-end DCNN based approach for motion segmentation, especially for video sequences captured with such non-static cameras, called MOSNET. While other approaches focus on spatial or temporal context only, the…

Enhancing images in low-light scenes is a challenging but widely concerned task in the computer vision. The mainstream learning-based methods mainly acquire the enhanced model by learning the data distribution from the specific scenes,…

This study investigates the performance of the two most relevant computer vision deep learning architectures, Convolutional Neural Network and Vision Transformer, for event-based cameras. These cameras capture scene changes, unlike…

Deep convolutional neural networks have largely benefited computer vision tasks. However, the high computational complexity limits their real-world applications. To this end, many methods have been proposed for efficient network learning,…

The dissertation presents four key contributions toward fairness and robustness in vision learning. First, to address the problem of large-scale data requirements, the dissertation presents a novel Fairness Domain Adaptation approach…