169 citations · 327 across the 13 of their papers we have counts for
16 papers · 1 filter
Spatio-Temporal Pixel-Level Contrastive Learning-based Source-Free Domain Adaptation for Video Semantic Segmentation
Shao-Yuan Lo, Poojan Oza, Sumanth Chennupati +2
Unsupervised Domain Adaptation (UDA) of semantic segmentation transfers labeled source knowledge to an unlabeled target domain by relying on accessing both the source and target da…
Towards Online Domain Adaptive Object Detection
Vibashan VS, Poojan Oza, Vishal M. Patel
Existing object detection models assume both the training and test data are sampled from the same source domain. This assumption does not hold true when these detectors are deploye…
Instance Relation Graph Guided Source-Free Domain Adaptive Object Detection
Vibashan VS, Poojan Oza, Vishal M. Patel
Unsupervised Domain Adaptation (UDA) is an effective approach to tackle the issue of domain shift. Specifically, UDA methods try to align the source and target representations to i…
Adversarially Robust One-class Novelty Detection
Shao-Yuan Lo, Poojan Oza, Vishal M. Patel
One-class novelty detectors are trained with examples of a particular class and are tasked with identifying whether a query example belongs to the same known class. Most recent adv…
Image Fusion Transformer
Vibashan VS, Jeya Maria Jose Valanarasu, Poojan Oza +1
In image fusion, images obtained from different sensors are fused to generate a single image with enhanced information. In recent years, state-of-the-art methods have adopted Convo…
Unsupervised Domain Adaptation of Object Detectors: A Survey
Poojan Oza, Vishwanath A. Sindagi, Vibashan VS +1
Recent advances in deep learning have led to the development of accurate and efficient models for various computer vision applications such as classification, segmentation, and det…
Federated Learning-based Active Authentication on Mobile Devices
Poojan Oza, Vishal M. Patel
User active authentication on mobile devices aims to learn a model that can correctly recognize the enrolled user based on device sensor information. Due to lack of negative class…
MeGA-CDA: Memory Guided Attention for Category-Aware Unsupervised Domain Adaptive Object Detection
Vibashan VS, Vikram Gupta, Poojan Oza +2
Existing approaches for unsupervised domain adaptive object detection perform feature alignment via adversarial training. While these methods achieve reasonable improvements in per…
Medical Transformer: Gated Axial-Attention for Medical Image Segmentation
Jeya Maria Jose Valanarasu, Poojan Oza, Ilker Hacihaliloglu +1
Over the past decade, Deep Convolutional Neural Networks have been widely adopted for medical image segmentation and shown to achieve adequate performance. However, due to the inhe…
One-Class Classification: A Survey
Pramuditha Perera, Poojan Oza, Vishal M. Patel
One-Class Classification (OCC) is a special case of multi-class classification, where data observed during training is from a single positive class. The goal of OCC is to learn a r…
Anomaly Detection-Based Unknown Face Presentation Attack Detection
Yashasvi Baweja, Poojan Oza, Pramuditha Perera +1
Anomaly detection-based spoof attack detection is a recent development in face Presentation Attack Detection (fPAD), where a spoof detector is learned using only non-attacked image…
Prior-based Domain Adaptive Object Detection for Hazy and Rainy Conditions
Vishwanath A. Sindagi, Poojan Oza, Rajeev Yasarla +1
Adverse weather conditions such as haze and rain corrupt the quality of captured images, which cause detection networks trained on clean images to perform poorly on these images. T…
C2AE: Class Conditioned Auto-Encoder for Open-set Recognition
Poojan Oza, Vishal M Patel
Models trained for classification often assume that all testing classes are known while training. As a result, when presented with an unknown class during testing, such closed-set…
Deep CNN-based Multi-task Learning for Open-Set Recognition
Poojan Oza, Vishal M. Patel
We propose a novel deep convolutional neural network (CNN) based multi-task learning approach for open-set visual recognition. We combine a classifier network and a decoder network…
Active Authentication using an Autoencoder regularized CNN-based One-Class Classifier
Poojan Oza, Vishal M. Patel
Active authentication refers to the process in which users are unobtrusively monitored and authenticated continuously throughout their interactions with mobile devices. Generally,…
One-Class Convolutional Neural Network
Poojan Oza, Vishal M. Patel
We present a novel Convolutional Neural Network (CNN) based approach for one class classification. The idea is to use a zero centered Gaussian noise in the latent space as the pseu…