Small-object detection based on YOLOv5 in autonomous driving systems
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 …
accurate object detection frameworks has become a necessity. Many recent deep learning …
Leveraging filter correlations for deep model compression
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 …
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 …
intensive computer vision tasks. The convolutional filters used in CNNs have played a major …
A" Network Pruning Network''Approach to Deep Model Compression
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 …
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 …
Pointwise convolution (PWC) is a 1× 1 convolutional filter that is primarily used for parameter …
Learning speaker-specific lip-to-speech generation
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 …
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 …
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 …
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
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 …
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
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 …
with marginal loss in classification performance. However, similar concepts have not been …