Search Results for author: Biplab Banerjee

Found 40 papers, 7 papers with code

Hierarchical Metric Learning for Optical Remote Sensing Scene Categorization

no code implementations4 Aug 2017 Akashdeep Goel, Biplab Banerjee, Aleksandra Pizurica

We address the problem of scene classification from optical remote sensing (RS) images based on the paradigm of hierarchical metric learning.

Clustering Metric Learning +2

CMIR-NET : A Deep Learning Based Model For Cross-Modal Retrieval In Remote Sensing

1 code implementation9 Apr 2019 Ushasi Chaudhuri, Biplab Banerjee, Avik Bhattacharya, Mihai Datcu

In particular, we are interested in two application scenarios: i) cross-modal retrieval between panchromatic (PAN) and multi-spectral imagery, and ii) multi-label image retrieval between very high resolution (VHR) images and speech based label annotations.

Cross-Modal Retrieval Information Retrieval +2

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.

Classification Decision Making +8

LEt-SNE: A Hybrid Approach To Data Embedding and Visualization of Hyperspectral Imagery

2 code implementations19 Oct 2019 Megh Shukla, Biplab Banerjee, Krishna Mohan Buddhiraju

Some popular techniques among these falter when applied to Hyperspectral Imagery due to the famed curse of dimensionality.

Clustering Dimensionality Reduction

Distilling Spikes: Knowledge Distillation in Spiking Neural Networks

no code implementations1 May 2020 Ravi Kumar Kushawaha, Saurabh Kumar, Biplab Banerjee, Rajbabu Velmurugan

We also present a multi-stage knowledge distillation technique for SNNs using an intermediate network to obtain higher performance from the student network.

Image Classification Knowledge Distillation +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

Discriminative Dictionary Design for Action Classification in Still Images and Videos

no code implementations20 May 2020 Abhinaba Roy, Biplab Banerjee, Amir Hussain, Soujanya Poria

Specifically, we pose the selection of potent local descriptors as filtering based feature selection problem which ranks the local features per category based on a novel measure of distinctiveness.

Action Classification Action Recognition +2

Teaching CNNs to mimic Human Visual Cognitive Process & regularise Texture-Shape bias

1 code implementation25 Jun 2020 Satyam Mohla, Anshul Nasery, Biplab Banerjee

Recent experiments in computer vision demonstrate texture bias as the primary reason for supreme results in models employing Convolutional Neural Networks (CNNs), conflicting with early works claiming that these networks identify objects using shape.

Object Recognition

Saliency-driven Class Impressions for Feature Visualization of Deep Neural Networks

no code implementations31 Jul 2020 Sravanti Addepalli, Dipesh Tamboli, R. Venkatesh Babu, Biplab Banerjee

Existing visualization methods develop high confidence images consisting of both background and foreground features.

A Zero-Shot Sketch-based Inter-Modal Object Retrieval Scheme for Remote Sensing Images

1 code implementation12 Aug 2020 Ushasi Chaudhuri, Biplab Banerjee, Avik Bhattacharya, Mihai Datcu

We perform a thorough bench-marking of this dataset and demonstrate that the proposed network outperforms other state-of-the-art methods for zero-shot sketch-based retrieval framework in remote sensing.

Retrieval

Multimodal Noisy Segmentation based fragmented burn scars identification in Amazon Rainforest

no code implementations10 Sep 2020 Satyam Mohla, Sidharth Mohla, Anupam Guha, Biplab Banerjee

However, the task to segment burn marks is difficult because of its indistinguishably with similar looking land patterns, severe fragmented nature of burn marks and partially labelled noisy datasets.

Management

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 Sentence

Empowering Knowledge Distillation via Open Set Recognition for Robust 3D Point Cloud Classification

no code implementations25 Oct 2020 Ayush Bhardwaj, Sakshee Pimpale, Saurabh Kumar, Biplab Banerjee

We demonstrate the effectiveness of the proposed method via various experiments on how it allows us to obtain a much smaller model, which takes a minimal hit in performance while being capable of open set recognition for 3D point cloud data.

3D Point Cloud Classification General Classification +4

Trusting small training dataset for supervised change detection

no code implementations9 Apr 2021 Sudipan Saha, Biplab Banerjee, Xiao Xiang Zhu

Deep learning (DL) based supervised change detection (CD) models require large labeled training data.

Change Detection

CrossATNet - A Novel Cross-Attention Based Framework for Sketch-Based Image Retrieval

no code implementations20 Apr 2021 Ushasi Chaudhuri, Biplab Banerjee, Avik Bhattacharya, Mihai Datcu

While we define a cross-modal triplet loss to ensure the discriminative nature of the shared space, an innovative cross-modal attention learning strategy is also proposed to guide feature extraction from the image domain exploiting information from the respective sketch counterpart.

Retrieval Sketch-Based Image Retrieval +1

Two Headed Dragons: Multimodal Fusion and Cross Modal Transactions

no code implementations24 Jul 2021 Rupak Bose, Shivam Pande, Biplab Banerjee

The model is composed of stacked auto encoders that harness the cross key-value pairs for HSI and LiDAR, thus establishing a communication between the two modalities, while simultaneously using the CNNs to extract the spectral and spatial information from HSI and LiDAR.

Vocal Bursts Valence Prediction

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.

Generative Adversarial Network Unsupervised Domain Adaptation

Zero-Shot Sketch Based Image Retrieval using Graph Transformer

no code implementations25 Jan 2022 Sumrit Gupta, Ushasi Chaudhuri, Biplab Banerjee

To bridge the domain gap between the visual features, we propose minimizing the Wasserstein distance between images and sketches in a learned domain-shared space.

Retrieval Sketch-Based Image Retrieval

Prototypical quadruplet for few-shot class incremental learning

no code implementations5 Nov 2022 Sanchar Palit, Biplab Banerjee, Subhasis Chaudhuri

We demonstrate the effectiveness of our method by showing that the embedding space remains intact after training the model with new classes and outperforms existing state-of-the-art algorithms in terms of accuracy across different sessions.

Few-Shot Class-Incremental Learning Incremental Learning

StyLIP: Multi-Scale Style-Conditioned Prompt Learning for CLIP-based Domain Generalization

no code implementations18 Feb 2023 Shirsha Bose, Ankit Jha, Enrico Fini, Mainak Singha, Elisa Ricci, Biplab Banerjee

Our method focuses on a domain-agnostic prompt learning strategy, aiming to disentangle the visual style and content information embedded in CLIP's pre-trained vision encoder, enabling effortless adaptation to novel domains during inference.

Domain Generalization Zero-shot Generalization

APPLeNet: Visual Attention Parameterized Prompt Learning for Few-Shot Remote Sensing Image Generalization using CLIP

1 code implementation12 Apr 2023 Mainak Singha, Ankit Jha, Bhupendra Solanki, Shirsha Bose, Biplab Banerjee

APPLeNet emphasizes the importance of multi-scale feature learning in RS scene classification and disentangles visual style and content primitives for domain generalization tasks.

Domain Generalization Scene Classification

USIM-DAL: Uncertainty-aware Statistical Image Modeling-based Dense Active Learning for Super-resolution

no code implementations27 May 2023 Vikrant Rangnekar, Uddeshya Upadhyay, Zeynep Akata, Biplab Banerjee

Dense regression is a widely used approach in computer vision for tasks such as image super-resolution, enhancement, depth estimation, etc.

Active Learning Depth Estimation +3

Semi-Supervised Learning for hyperspectral images by non parametrically predicting view assignment

no code implementations19 Jun 2023 Shivam Pande, Nassim Ait Ali Braham, Yi Wang, Conrad M Albrecht, Biplab Banerjee, Xiao Xiang Zhu

Recently, to effectively train the deep learning models with minimal labelled samples, the unlabeled samples are also being leveraged in self-supervised and semi-supervised setting.

Pseudo Label

Physically Plausible 3D Human-Scene Reconstruction from Monocular RGB Image using an Adversarial Learning Approach

no code implementations27 Jul 2023 Sandika Biswas, Kejie Li, Biplab Banerjee, Subhasis Chaudhuri, Hamid Rezatofighi

This paper proposes using an implicit feature representation of the scene elements to distinguish a physically plausible alignment of humans and objects from an implausible one.

3D Reconstruction Robot Navigation

Temporal DINO: A Self-supervised Video Strategy to Enhance Action Prediction

no code implementations8 Aug 2023 Izzeddin Teeti, Rongali Sai Bhargav, Vivek Singh, Andrew Bradley, Biplab Banerjee, Fabio Cuzzolin

The emerging field of action prediction plays a vital role in various computer vision applications such as autonomous driving, activity analysis and human-computer interaction.

Activity Recognition Autonomous Driving +2

AD-CLIP: Adapting Domains in Prompt Space Using CLIP

no code implementations10 Aug 2023 Mainak Singha, Harsh Pal, Ankit Jha, Biplab Banerjee

We leverage the frozen vision backbone of CLIP to extract both image style (domain) and content information, which we apply to learn prompt tokens.

Contrastive Learning Unsupervised Domain Adaptation

GOPro: Generate and Optimize Prompts in CLIP using Self-Supervised Learning

no code implementations22 Aug 2023 Mainak Singha, Ankit Jha, Biplab Banerjee

GOPro is trained end-to-end on all three loss objectives, combining the strengths of CLIP and SSL in a principled manner.

Domain Generalization Self-Supervised Learning

Domain Adaptive Few-Shot Open-Set Learning

1 code implementation ICCV 2023 Debabrata Pal, Deeptej More, Sai Bhargav, Dipesh Tamboli, Vaneet Aggarwal, Biplab Banerjee

Few-shot learning has made impressive strides in addressing the crucial challenges of recognizing unknown samples from novel classes in target query sets and managing visual shifts between domains.

cross-domain few-shot learning Few-Shot Learning +1

HAVE-Net: Hallucinated Audio-Visual Embeddings for Few-Shot Classification with Unimodal Cues

no code implementations23 Sep 2023 Ankit Jha, Debabrata Pal, Mainak Singha, Naman Agarwal, Biplab Banerjee

Even though joint training of audio-visual modalities improves classification performance in a low-data regime, it has yet to be thoroughly investigated in the RS domain.

Few-Shot Learning

Learning Class and Domain Augmentations for Single-Source Open-Domain Generalization

no code implementations5 Nov 2023 Prathmesh Bele, Valay Bundele, Avigyan Bhattacharya, Ankit Jha, Gemma Roig, Biplab Banerjee

Single-source open-domain generalization (SS-ODG) addresses the challenge of labeled source domains with supervision during training and unlabeled novel target domains during testing.

Domain Generalization

C-SAW: Self-Supervised Prompt Learning for Image Generalization in Remote Sensing

no code implementations27 Nov 2023 Avigyan Bhattacharya, Mainak Singha, Ankit Jha, Biplab Banerjee

To this end, we introduce C-SAW, a method that complements CLIP with a self-supervised loss in the visual space and a novel prompt learning technique that emphasizes both visual domain and content-specific features.

Language Modelling Zero-shot Generalization

Scaling Vision-and-Language Navigation With Offline RL

no code implementations27 Mar 2024 Valay Bundele, Mahesh Bhupati, Biplab Banerjee, Aditya Grover

The study of vision-and-language navigation (VLN) has typically relied on expert trajectories, which may not always be available in real-world situations due to the significant effort required to collect them.

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