Small-object detection based on YOLOv5 in autonomous driving systems

B Mahaur, KK Mishra - Pattern Recognition Letters, 2023 - Elsevier
With the rapid advancements in the field of autonomous driving, the need for faster and more
accurate object detection frameworks has become a necessity. Many recent deep learning …

Leveraging filter correlations for deep model compression

P Singh, VK Verma, P Rai… - Proceedings of the …, 2020 - openaccess.thecvf.com
We present a filter correlation based model compression approach for deep convolutional
neural networks. Our approach iteratively identifies pairs of filters with the largest pairwise …

Accuracy booster: Performance boosting using feature map re-calibration

P Singh, P Mazumder… - Proceedings of the IEEE …, 2020 - openaccess.thecvf.com
Abstract Convolution Neural Networks (CNN) have been extremely successful in solving
intensive computer vision tasks. The convolutional filters used in CNNs have played a major …

A" Network Pruning Network''Approach to Deep Model Compression

VK Verma, P Singh, V Namboodri… - Proceedings of the …, 2020 - openaccess.thecvf.com
We present a filter pruning approach for deep model compression, using a multitask
network. Our approach is based on learning aa pruner network to prune a pre-trained target …

Cpwc: Contextual point wise convolution for object recognition

P Mazumder, P Singh… - ICASSP 2020-2020 IEEE …, 2020 - ieeexplore.ieee.org
Convolutional layers are a major driving force behind the successes of deep learning.
Pointwise convolution (PWC) is a 1× 1 convolutional filter that is primarily used for parameter …

Learning speaker-specific lip-to-speech generation

M Varshney, R Yadav, VP Namboodiri… - 2022 26th …, 2022 - ieeexplore.ieee.org
Understanding the lip movement and inferring the speech from it is notoriously difficult for
the common person. The task of accurate lip-reading gets help from various cues of the …

Multi-output incremental back-propagation

R Chaudhari, D Agarwal, K Ravishankar… - Neural Computing and …, 2023 - Springer
Deep learning techniques can form generalized models that can solve any problem that is
not solvable by traditional approaches. It explains the omnipresence of deep learning …

SkipConv: skip convolution for computationally efficient deep CNNs

P Singh, VP Namboodiri - 2020 International Joint Conference …, 2020 - ieeexplore.ieee.org
Convolution operation in deep convolutional neural networks is the most computationally
expensive as compared to other operations. Most of the model computation (FLOPS) in the …

Improving convergence speed of the neural network model using Meta heuristic algorithms for weight initialization

VV Priya, P Natesan, K Venu… - … Conference on Computer …, 2021 - ieeexplore.ieee.org
Neural network is widely used nowadays as it shows great result in solving the data
classification and regression problems. The neuron is a basic unit in the artificial neural …

Dynamic perturbation of weights for improved data reconstruction in unsupervised learning

MD Samad, R Hossain… - 2021 International Joint …, 2021 - ieeexplore.ieee.org
The concept of weight pruning has shown success in neural network model compression
with marginal loss in classification performance. However, similar concepts have not been …