41 citations · 81 across the 21 of their papers we have counts for
11 papers · 1 filter
Label Smoothing++: Enhanced Label Regularization for Training Neural Networks
Sachin Chhabra, Hemanth Venkateswara, Baoxin Li
Training neural networks with one-hot target labels often results in overconfidence and overfitting. Label smoothing addresses this issue by perturbing the one-hot target labels by…
Dataset Augmentation by Mixing Visual Concepts
Abdullah Al Rahat, Hemanth Venkateswara
This paper proposes a dataset augmentation method by fine-tuning pre-trained diffusion models. Generating images using a pre-trained diffusion model with textual conditioning often…
Domain Adaptation Using Pseudo Labels
Sachin Chhabra, Hemanth Venkateswara, Baoxin Li
In the absence of labeled target data, unsupervised domain adaptation approaches seek to align the marginal distributions of the source and target domains in order to train a class…
PatchRot: A Self-Supervised Technique for Training Vision Transformers
Sachin Chhabra, Prabal Bijoy Dutta, Hemanth Venkateswara +1
Vision transformers require a huge amount of labeled data to outperform convolutional neural networks. However, labeling a huge dataset is a very expensive process. Self-supervised…
Partial Domain Adaptation Using Selective Representation Learning For Class-Weight Computation
Sandipan Choudhuri, Riti Paul, Arunabha Sen +2
The generalization power of deep-learning models is dependent on rich-labelled data. This supervision using large-scaled annotated information is restrictive in most real-world sce…
Leveraging Seen and Unseen Semantic Relationships for Generative Zero-Shot Learning
Maunil R Vyas, Hemanth Venkateswara, Sethuraman Panchanathan
Zero-shot learning (ZSL) addresses the unseen class recognition problem by leveraging semantic information to transfer knowledge from seen classes to unseen classes. Generative mod…
Multiresolution Match Kernels for Gesture Video Classification
Hemanth Venkateswara, Vineeth N. Balasubramanian, Prasanth Lade +1
The emergence of depth imaging technologies like the Microsoft Kinect has renewed interest in computational methods for gesture classification based on videos. For several years no…
Coupled Support Vector Machines for Supervised Domain Adaptation
Hemanth Venkateswara, Prasanth Lade, Jieping Ye +1
Popular domain adaptation (DA) techniques learn a classifier for the target domain by sampling relevant data points from the source and combining it with the target data. We presen…
Nonlinear Embedding Transform for Unsupervised Domain Adaptation
Hemanth Venkateswara, Shayok Chakraborty, Sethuraman Panchanathan
The problem of domain adaptation (DA) deals with adapting classifier models trained on one data distribution to different data distributions. In this paper, we introduce the Nonlin…
Deep Hashing Network for Unsupervised Domain Adaptation
Hemanth Venkateswara, Jose Eusebio, Shayok Chakraborty +1
In recent years, deep neural networks have emerged as a dominant machine learning tool for a wide variety of application domains. However, training a deep neural network requires a…
A Strategy for an Uncompromising Incremental Learner
Ragav Venkatesan, Hemanth Venkateswara, Sethuraman Panchanathan +1
Multi-class supervised learning systems require the knowledge of the entire range of labels they predict. Often when learnt incrementally, they suffer from catastrophic forgetting.…