Search Results for author: Poojan Oza

Found 17 papers, 6 papers with code

Utilizing Patch-level Category Activation Patterns for Multiple Class Novelty Detection

no code implementations ECCV 2020 Poojan Oza, Vishal M. Patel

For any recognition system, the ability to identify novel class samples during inference is an important aspect of the system’s robustness.

Multiple Class Novelty Detection Under Data Distribution Shift

no code implementations ECCV 2020 Poojan Oza, Hien V. Nguyen, Vishal M. Patel

To this end, we consider the problem of multiple class novelty detection under dataset distribution shift to improve the novelty detection performance.

Domain Adaptation Object Recognition

Towards Online Domain Adaptive Object Detection

1 code implementation11 Apr 2022 Vibashan VS, Poojan Oza, Vishal M. Patel

To the best of our knowledge, this is the first work to address online and offline adaptation settings for object detection.

Object Detection Representation Learning +1

Instance Relation Graph Guided Source-Free Domain Adaptive Object Detection

1 code implementation29 Mar 2022 Vibashan VS, Poojan Oza, Vishal M. Patel

The Source-Free Domain Adaptation (SFDA) setting aims to alleviate these concerns by adapting a source-trained model for the target domain without requiring access to the source data.

Knowledge Distillation Object Detection +2

Adversarially Robust One-class Novelty Detection

no code implementations25 Aug 2021 Shao-Yuan Lo, Poojan Oza, Vishal M. Patel

To this end, we propose a defense strategy that manipulates the latent space of novelty detectors to improve the robustness against adversarial examples.

Adversarial Robustness

Image Fusion Transformer

1 code implementation19 Jul 2021 Vibashan VS, Jeya Maria Jose Valanarasu, Poojan Oza, Vishal M. Patel

Furthermore, we show the effectiveness of the proposed ST fusion strategy with an ablation analysis.

Unsupervised Domain Adaptation of Object Detectors: A Survey

no code implementations27 May 2021 Poojan Oza, Vishwanath A. Sindagi, Vibashan VS, Vishal M. Patel

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 detection.

Autonomous Navigation Object Detection +2

Federated Learning-based Active Authentication on Mobile Devices

no code implementations14 Apr 2021 Poojan Oza, Vishal M. Patel

Using FL/SL frameworks, we can alleviate the lack of negative data problem by training a user authentication model over multiple user data distributed across devices.

Federated Learning

Medical Transformer: Gated Axial-Attention for Medical Image Segmentation

1 code implementation21 Feb 2021 Jeya Maria Jose Valanarasu, Poojan Oza, Ilker Hacihaliloglu, Vishal M. Patel

The proposed Medical Transformer (MedT) is evaluated on three different medical image segmentation datasets and it is shown that it achieves better performance than the convolutional and other related transformer-based architectures.

Medical Image Segmentation Semantic Segmentation

One-Class Classification: A Survey

no code implementations8 Jan 2021 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.

Classification General Classification +1

Anomaly Detection-Based Unknown Face Presentation Attack Detection

1 code implementation11 Jul 2020 Yashasvi Baweja, Poojan Oza, Pramuditha Perera, Vishal M. Patel

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 images of users.

Anomaly Detection Face Presentation Attack Detection +1

Prior-based Domain Adaptive Object Detection for Hazy and Rainy Conditions

no code implementations ECCV 2020 Vishwanath A. Sindagi, Poojan Oza, Rajeev Yasarla, Vishal M. Patel

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.

Object Detection

C2AE: Class Conditioned Auto-Encoder for Open-set Recognition

no code implementations CVPR 2019 Poojan Oza, Vishal M. Patel

It refers to the problem of identifying the unknown classes during testing, while maintaining performance on the known classes.

Classification General Classification +2

Deep CNN-based Multi-task Learning for Open-Set Recognition

no code implementations7 Mar 2019 Poojan Oza, Vishal M. Patel

We propose a novel deep convolutional neural network (CNN) based multi-task learning approach for open-set visual recognition.

General Classification Image Classification +2

Active Authentication using an Autoencoder regularized CNN-based One-Class Classifier

no code implementations4 Mar 2019 Poojan Oza, Vishal M. Patel

Generally, an active authentication problem is modelled as a one class classification problem due to the unavailability of data from the impostor users.

Classification General Classification +1

One-Class Convolutional Neural Network

4 code implementations24 Jan 2019 Poojan Oza, Vishal M. Patel

We present a novel Convolutional Neural Network (CNN) based approach for one class classification.

Anomaly Detection General Classification

Cannot find the paper you are looking for? You can Submit a new open access paper.