Search Results for author: Pramuditha Perera

Found 21 papers, 7 papers with code

Meaning Representations from Trajectories in Autoregressive Models

1 code implementation23 Oct 2023 Tian Yu Liu, Matthew Trager, Alessandro Achille, Pramuditha Perera, Luca Zancato, Stefano Soatto

We propose to extract meaning representations from autoregressive language models by considering the distribution of all possible trajectories extending an input text.

Semantic Similarity Semantic Textual Similarity

Prompt Algebra for Task Composition

no code implementations1 Jun 2023 Pramuditha Perera, Matthew Trager, Luca Zancato, Alessandro Achille, Stefano Soatto

We investigate whether prompts learned independently for different tasks can be later combined through prompt algebra to obtain a model that supports composition of tasks.

Classification

Train/Test-Time Adaptation with Retrieval

no code implementations CVPR 2023 Luca Zancato, Alessandro Achille, Tian Yu Liu, Matthew Trager, Pramuditha Perera, Stefano Soatto

Second, we apply ${\rm T^3AR}$ for test-time adaptation and show that exploiting a pool of external images at test-time leads to more robust representations over existing methods on DomainNet-126 and VISDA-C, especially when few adaptation data are available (up to 8%).

Retrieval Test

Open-set Adversarial Defense with Clean-Adversarial Mutual Learning

1 code implementation12 Feb 2022 Rui Shao, Pramuditha Perera, Pong C. Yuen, Vishal M. Patel

This paper proposes an Open-Set Defense Network with Clean-Adversarial Mutual Learning (OSDN-CAML) as a solution to the OSAD problem.

Adversarial Defense Denoising +2

Federated Generalized Face Presentation Attack Detection

no code implementations14 Apr 2021 Rui Shao, Pramuditha Perera, Pong C. Yuen, Vishal M. Patel

A face presentation attack detection model with good generalization can be obtained when it is trained with face images from different input distributions and different types of spoof attacks.

Disentanglement Face Presentation Attack Detection +2

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 +2

Open-set Adversarial Defense

1 code implementation ECCV 2020 Rui Shao, Pramuditha Perera, Pong C. Yuen, Vishal M. Patel

In this paper, we show that open-set recognition systems are vulnerable to adversarial attacks.

Adversarial Defense Denoising +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

Quickest Intruder Detection for Multiple User Active Authentication

no code implementations21 Jun 2020 Pramuditha Perera, Julian Fierrez, Vishal M. Patel

In this paper, we investigate how to detect intruders with low latency for Active Authentication (AA) systems with multiple-users.

Change Detection

Generative-Discriminative Feature Representations for Open-Set Recognition

no code implementations CVPR 2020 Pramuditha Perera, Vlad I. Morariu, Rajiv Jain, Varun Manjunatha, Curtis Wigington, Vicente Ordonez, Vishal M. Patel

We address the problem of open-set recognition, where the goal is to determine if a given sample belongs to one of the classes used for training a model (known classes).

Open Set Learning

Federated Face Presentation Attack Detection

no code implementations29 May 2020 Rui Shao, Pramuditha Perera, Pong C. Yuen, Vishal M. Patel

A face presentation attack detection model with good generalization can be obtained when it is trained with face images from different input distributions and different types of spoof attacks.

Face Anti-Spoofing Face Presentation Attack Detection +2

Deep Transfer Learning for Multiple Class Novelty Detection

1 code implementation CVPR 2019 Pramuditha Perera, Vishal M. Patel

We show that thresholding the maximal activation of the proposed network can be used to identify novel objects effectively.

Novelty Detection Transfer Learning

Learning Deep Features for One-Class Classification

5 code implementations16 Jan 2018 Pramuditha Perera, Vishal M. Patel

We propose a deep learning-based solution for the problem of feature learning in one-class classification.

Descriptive General Classification +3

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