Search Results for author: Debasmit Das

Found 20 papers, 3 papers with code

PosSAM: Panoptic Open-vocabulary Segment Anything

1 code implementation14 Mar 2024 Vibashan VS, Shubhankar Borse, Hyojin Park, Debasmit Das, Vishal Patel, Munawar Hayat, Fatih Porikli

In this paper, we introduce an open-vocabulary panoptic segmentation model that effectively unifies the strengths of the Segment Anything Model (SAM) with the vision-language CLIP model in an end-to-end framework.

Open Vocabulary Panoptic Segmentation Panoptic Segmentation +1

Towards Open-Set Test-Time Adaptation Utilizing the Wisdom of Crowds in Entropy Minimization

no code implementations ICCV 2023 Jungsoo Lee, Debasmit Das, Jaegul Choo, Sungha Choi

To be more specific, entropy minimization attempts to raise the confidence values of an individual sample's prediction, but individual confidence values may rise or fall due to the influence of signals from numerous other predictions (i. e., wisdom of crowds).

Image Classification Semantic Segmentation +1

Progressive Random Convolutions for Single Domain Generalization

no code implementations CVPR 2023 Seokeon Choi, Debasmit Das, Sungha Choi, Seunghan Yang, Hyunsin Park, Sungrack Yun

Single domain generalization aims to train a generalizable model with only one source domain to perform well on arbitrary unseen target domains.

Domain Generalization Image Augmentation

DejaVu: Conditional Regenerative Learning to Enhance Dense Prediction

no code implementations CVPR 2023 Shubhankar Borse, Debasmit Das, Hyojin Park, Hong Cai, Risheek Garrepalli, Fatih Porikli

Next, we use a conditional regenerator, which takes the redacted image and the dense predictions as inputs, and reconstructs the original image by filling in the missing structural information.

Depth Estimation

TransAdapt: A Transformative Framework for Online Test Time Adaptive Semantic Segmentation

no code implementations24 Feb 2023 Debasmit Das, Shubhankar Borse, Hyojin Park, Kambiz Azarian, Hong Cai, Risheek Garrepalli, Fatih Porikli

Test-time adaptive (TTA) semantic segmentation adapts a source pre-trained image semantic segmentation model to unlabeled batches of target domain test images, different from real-world, where samples arrive one-by-one in an online fashion.

Segmentation Semantic Segmentation +1

Online Adaptive Personalization for Face Anti-spoofing

1 code implementation4 Jul 2022 Davide Belli, Debasmit Das, Bence Major, Fatih Porikli

Face authentication systems require a robust anti-spoofing module as they can be deceived by fabricating spoof images of authorized users.

Face Anti-Spoofing

Domain Agnostic Few-shot Learning for Speaker Verification

no code implementations28 Jun 2022 Seunghan Yang, Debasmit Das, Janghoon Cho, Hyoungwoo Park, Sungrack Yun

Deep learning models for verification systems often fail to generalize to new users and new environments, even though they learn highly discriminative features.

Domain Generalization Few-Shot Learning +1

A Multi-stage Framework with Mean Subspace Computation and Recursive Feedback for Online Unsupervised Domain Adaptation

no code implementations24 Jun 2022 Jihoon Moon, Debasmit Das, C. S. George Lee

To project the data from the source and the target domains to a common subspace and manipulate the projected data in real-time, our proposed framework institutes a novel method, called an Incremental Computation of Mean-Subspace (ICMS) technique, which computes an approximation of mean-target subspace on a Grassmann manifold and is proven to be a close approximate to the Karcher mean.

Online unsupervised domain adaptation

A personalized benchmark for face anti-spoofing

1 code implementation WACV 2022 Davide Belli, Debasmit Das, Bence Major, Fatih Porikli

In real-world scenarios, however, face authentication systems often have an initial enrollment step where a few live images of the user are recorded and stored for identification purposes.

Face Anti-Spoofing

Distribution Estimation to Automate Transformation Policies for Self-Supervision

no code implementations24 Nov 2021 Seunghan Yang, Debasmit Das, Simyung Chang, Sungrack Yun, Fatih Porikli

However, it is observed that image transformations already present in the dataset might be less effective in learning such self-supervised representations.

Generative Adversarial Network Self-Supervised Learning

Data-driven Weight Initialization with Sylvester Solvers

no code implementations2 May 2021 Debasmit Das, Yash Bhalgat, Fatih Porikli

The initialization is cast as an optimization problem where we minimize a combination of encoding and decoding losses of the input activations, which is further constrained by a user-defined latent code.

Few-shot Image Recognition with Manifolds

no code implementations22 Oct 2020 Debasmit Das, J. H. Moon, C. S. George Lee

In this paper, we extend the traditional few-shot learning (FSL) problem to the situation when the source-domain data is not accessible but only high-level information in the form of class prototypes is available.

Few-Shot Learning Privacy Preserving

Multi-step Online Unsupervised Domain Adaptation

no code implementations20 Feb 2020 J. H. Moon, Debasmit Das, C. S. George Lee

The traditional methods on the OUDA problem mainly focus on transforming each arriving target data to the source domain, and they do not sufficiently consider the temporal coherency and accumulative statistics among the arriving target data.

Online unsupervised domain adaptation

A Two-Stage Approach to Few-Shot Learning for Image Recognition

no code implementations10 Dec 2019 Debasmit Das, C. S. George Lee

This paper proposes a multi-layer neural network structure for few-shot image recognition of novel categories.

Few-Shot Learning General Classification +1

Zero-shot Image Recognition Using Relational Matching, Adaptation and Calibration

no code implementations27 Mar 2019 Debasmit Das, C. S. George Lee

Secondly, we propose test-time domain adaptation to adapt the semantic embedding of the unseen classes to the test data.

Domain Adaptation General Classification +2

Unsupervised Domain Adaptation using Regularized Hyper-graph Matching

no code implementations22 May 2018 Debasmit Das, C. S. George Lee

Domain adaptation (DA) addresses the real-world image classification problem of discrepancy between training (source) and testing (target) data distributions.

Graph Matching Image Classification +2

Sample-to-Sample Correspondence for Unsupervised Domain Adaptation

no code implementations1 May 2018 Debasmit Das, C. S. George Lee

The procedure of tackling this discrepancy between the training (source) and testing (target) domains is known as domain adaptation.

General Classification Image Classification +3

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