Search Results for author: Subhasis Chaudhuri

Found 22 papers, 4 papers with code

FRIDA -- Generative Feature Replay for Incremental Domain Adaptation

no code implementations28 Dec 2021 Sayan Rakshit, Anwesh Mohanty, Ruchika Chavhan, Biplab Banerjee, Gemma Roig, Subhasis Chaudhuri

Inspired by the notion of generative feature replay, we propose a novel framework called Feature Replay based Incremental Domain Adaptation (FRIDA) which leverages a new incremental generative adversarial network (GAN) called domain-generic auxiliary classification GAN (DGAC-GAN) for producing domain-specific feature representations seamlessly.

Unsupervised Domain Adaptation

Deep Learning based Novel View Synthesis

no code implementations14 Jul 2021 Amit More, Subhasis Chaudhuri

In this work, we propose a deep convolutional neural network (CNN) which learns to predict novel views of a scene from given collection of images.

Novel View Synthesis

A Unified Batch Selection Policy for Active Metric Learning

no code implementations15 Feb 2021 Priyadarshini K, Siddhartha Chaudhuri, Vivek Borkar, Subhasis Chaudhuri

To avoid redundancy between triplets, our method collectively selects batches with maximum joint entropy, which simultaneously captures both informativeness and diversity.

Active Learning Informativeness +1

3D-NVS: A 3D Supervision Approach for Next View Selection

no code implementations3 Dec 2020 Kumar Ashutosh, Saurabh Kumar, Subhasis Chaudhuri

We present a classification based approach for the next best view selection and show how we can plausibly obtain a supervisory signal for this task.

3D Reconstruction

A Novel Actor Dual-Critic Model for Remote Sensing Image Captioning

no code implementations5 Oct 2020 Ruchika Chavhan, Biplab Banerjee, Xiao Xiang Zhu, Subhasis Chaudhuri

We deal with the problem of generating textual captions from optical remote sensing (RS) images using the notion of deep reinforcement learning.

Image Captioning

Enhancing Haptic Distinguishability of Surface Materials with Boosting Technique

no code implementations5 Oct 2020 Priyadarshini K, Subhasis Chaudhuri

Discriminative features are crucial for several learning applications, such as object detection and classification.

General Classification Object Detection +1

Batch Decorrelation for Active Metric Learning

1 code implementation20 May 2020 Priyadarshini K, Ritesh Goru, Siddhartha Chaudhuri, Subhasis Chaudhuri

We present an active learning strategy for training parametric models of distance metrics, given triplet-based similarity assessments: object $x_i$ is more similar to object $x_j$ than to $x_k$.

Active Learning Informativeness +1

Generative Model-driven Structure Aligning Discriminative Embeddings for Transductive Zero-shot Learning

no code implementations9 May 2020 Omkar Gune, Mainak Pal, Preeti Mukherjee, Biplab Banerjee, Subhasis Chaudhuri

We propose a transductive approach to reduce the effect of domain shift, where we utilize unlabeled visual data from unseen classes to generate corresponding semantic features for unseen class visual samples.

Transfer Learning Zero-Shot Learning

DeFraudNet:End2End Fingerprint Spoof Detection using Patch Level Attention

1 code implementation19 Feb 2020 B. V. S Anusha, Sayan Banerjee, Subhasis Chaudhuri

These descriptors are extracted using DenseNet which significantly improves cross-sensor, cross-material and cross-dataset performance.

A Semi-Supervised Maximum Margin Metric Learning Approach for Small Scale Person Re-identification

no code implementations9 Oct 2019 T M Feroz Ali, Subhasis Chaudhuri

In this paper, we propose a semi-supervised metric learning approach that can utilize information in unlabelled data with the help of a few labelled training samples.

Metric Learning Person Re-Identification

Multiple Kernel Fisher Discriminant Metric Learning for Person Re-identification

no code implementations9 Oct 2019 T M Feroz Ali, Kalpesh K Patel, Rajbabu Velmurugan, Subhasis Chaudhuri

We derive a Mahalanobis metric induced by KFDA and argue that KFDA is efficient to be applied for metric learning in person re-identification.

Metric Learning Person Re-Identification

On the Separability of Classes with the Cross-Entropy Loss Function

no code implementations16 Sep 2019 Rudrajit Das, Subhasis Chaudhuri

The main result of our analysis is the derivation of a lower bound for the probability with which the inter-class distance is more than the intra-class distance in this feature space, as a function of the loss value.

Online Sensor Hallucination via Knowledge Distillation for Multimodal Image Classification

no code implementations28 Aug 2019 Saurabh Kumar, Biplab Banerjee, Subhasis Chaudhuri

We deal with the problem of information fusion driven satellite image/scene classification and propose a generic hallucination architecture considering that all the available sensor information are present during training while some of the image modalities may be absent while testing.

Decision Making General Classification +4

PerceptNet: Learning Perceptual Similarity of Haptic Textures in Presence of Unorderable Triplets

1 code implementation8 May 2019 Priyadarshini Kumari, Siddhartha Chaudhuri, Subhasis Chaudhuri

In order to design haptic icons or build a haptic vocabulary, we require a set of easily distinguishable haptic signals to avoid perceptual ambiguity, which in turn requires a way to accurately estimate the perceptual (dis)similarity of such signals.

Maximum Margin Metric Learning Over Discriminative Nullspace for Person Re-identification

no code implementations ECCV 2018 T M Feroz Ali, Subhasis Chaudhuri

In this paper we propose a novel metric learning framework called Nullspace Kernel Maximum Margin Metric Learning (NK3ML) which efficiently addresses the small sample size (SSS) problem inherent in person re-identification and offers a significant performance gain over existing state-of-the-art methods.

Metric Learning Person Re-Identification

Spatio-temporal interaction model for crowd video analysis

no code implementations31 Oct 2017 Neha Bhargava, Subhasis Chaudhuri

We present an unsupervised approach to analyze crowd at various levels of granularity $-$ individual, group and collective.

An Integrated Approach to Crowd Video Analysis: From Tracking to Multi-level Activity Recognition

no code implementations30 Oct 2017 Neha Bhargava, Subhasis Chaudhuri

We show that estimation of this hidden structure corresponds to track association and group detection.

Activity Recognition

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