23 Result(s)
within
Rakesh Kumar Sanodiya
-
Article
Frequency disentangled residual network
Residual networks (ResNets) have been utilized for various computer vision and image processing applications. The residual connection improves the training of the network with better gradient flow. A residual ...
-
Article
Kernelized global-local discriminant information preservation for unsupervised domain adaptation
Visual recognition has become inevitable in applications such as object detection, biometric tracking, autonomous vehicles, and social media platforms. The images have multiple factors such as image resolution...
-
Chapter and Conference Paper
Unsupervised Domain Adaptation Supplemented with Generated Images
With Domain Adaptation we aim to leverage a given source dataset to model a classifier on the target domain. In an unsupervised setting, the goal is to derive class-based features and adapt it to a different d...
-
Chapter and Conference Paper
Context Unaware Knowledge Distillation for Image Retrieval
Existing data-dependent hashing methods use large backbone networks with millions of parameters and are computationally complex. Existing knowledge distillation methods use logits and other features of the dee...
-
Chapter and Conference Paper
Virtual Try-On Using Style Transfer
Achieving Clothing Try-On with 2D images is always complicated because retrieving all the characteristics of a person and the clothing can be difficult. The absence of an ideal dataset and the presence of cons...
-
Chapter and Conference Paper
Kernelized Transfer Joint Matching for Unsupervised Domain Adaptation
Transfer learning is an emerging technique through which the machine can learn a new task from the previous experience of another related task to solve the problem of insufficient labelled data. Existing work ...
-
Chapter and Conference Paper
Joint Geometrical and Statistical Alignment Using Triplet Loss for Deep Domain Adaptation
Although the primitive and deep learning methods have made significant progress, problems can arise if there are large differences or distribution gaps between the training and test images. To overcome this pr...
-
Chapter and Conference Paper
A Particle Swarm Optimization Based Feature Selection Approach for Multi-source Visual Domain Adaptation
Labeled data plays a pivotal role in training primitive machine learning models to classify the target domain information. But acquiring the necessary amount of labeled data is not always possible. Hence Domai...
-
Chapter and Conference Paper
Statistical and Geometrical Alignment for Unsupervised Deep Domain Adaptation
The concept of domain adaptation (DA) is based on the principle of information transfer from one domain (usually called source domain) to a different but related other domain (usually called target domain). Th...
-
Chapter and Conference Paper
A Novel Multi-source Domain Learning Approach to Unsupervised Deep Domain Adaptation
Even though it is anticipated that training and test data come from same distribution, but in many practical applications, they usually have different distributions, resulting in poor classification performanc...
-
Chapter and Conference Paper
A Novel Metric Learning Framework for Semi-supervised Domain Adaptation
In many real-life problems, test and training data belong to different distributions. As a result, a classifier trained on a particular data distribution may produce unsatisfactory results on a different test ...
-
Chapter and Conference Paper
Kernelized Transfer Feature Learning on Manifolds
In the past few years in computer vision and machine learning, transfer learning has become an emerging research for leveraging richly labeled data in the source domain to construct a robust and accurate class...
-
Article
A particle swarm optimization-based feature selection for unsupervised transfer learning
Transfer learning (TL) method has captured an attractive presence because it facilitates the learning ability in the target domain by acquiring knowledge from well-established source domains. To gain strong kn...
-
Article
Particle swarm optimization based parameter selection technique for unsupervised discriminant analysis in transfer learning framework
The purpose of transfer learning is to utilize the knowledge gained from the existing (source) domain to enhance the performance on a distinct but related (target) domain. Existing works on transfer learning a...
-
Article
Semi-supervised orthogonal discriminant analysis with relative distance : integration with a MOO approach
In discriminant analysis, trace ratio is an important criterion for minimizing the between-class similarity and maximizing the within-class similarity, simultaneously. In brief, we address the trace ratio prob...
-
Chapter and Conference Paper
A Particle Swarm Optimization Based Joint Geometrical and Statistical Alignment Approach with Laplacian Regularization
Transfer Learning or Domain Adaptation is an emerging sub-field of Machine learning in which the source domain carrying ample amount of labeled data is employed to classify a diverse but inter-related target ...
-
Chapter and Conference Paper
A Modified Joint Geometrical and Statistical Alignment Approach for Low-Resolution Face Recognition
Domain Adaptation (DA) or Transfer Learning (TL) makes use of the already available source domain information for training the target domain classifier. Traditional ML algorithms require abundant amount of lab...
-
Chapter and Conference Paper
A Feature Selection Approach to Visual Domain Adaptation in Classification
In machine learning, we presume datasets to be labeled while performing any operation. But, is it true in real-life scenarios? To its contrary, we have an enormous amount of unlabeled datasets available in the...
-
Chapter and Conference Paper
Unified Framework for Visual Domain Adaptation Using Globality-Locality Preserving Projections
Domain Adaptation is a segment of machine learning that allows us to learn from a labelled source data distribution to classify different but related unlabelled target data distribution. In this paper, we pro...
-
Chapter and Conference Paper
Semi-supervised Regularized Coplanar Discriminant Analysis
Dimensionality Reduction is a widely used method of removing redundant features and data compression. Dimensionality reduction usually occurs in a supervised setting in which all the samples are labelled. Howe...
