Search Results for author:
Found 55 papers, 14 papers with code
Multi-Source Open-Set Deep Adversarial Domain Adaptation
Besides, an adversarial learning strategy is followed to model the discriminator between the target-domain known and unknown classes.
ASTRA: A Scene-aware TRAnsformer-based model for trajectory prediction
We present ASTRA (A} Scene-aware TRAnsformer-based model for trajectory prediction), a light-weight pedestrian trajectory forecasting model that integrates the scene context, spatial dynamics, social inter-agent interactions and temporal progressions for precise forecasting.
"My life is miserable, have to sign 500 autographs everyday": Exposing Humblebragging, the Brags in Disguise
For the first time, we introduce the task of automatically detecting humblebragging in text.
Foundation Models and Adaptive Feature Selection: A Synergistic Approach to Video Question Answering
This paper tackles the intricate challenge of video question-answering (VideoQA).
Anomaly detection using Diffusion-based methods
This paper explores the utility of diffusion-based models for anomaly detection, focusing on their efficacy in identifying deviations in both compact and high-resolution datasets.
Deep evolving semi-supervised anomaly detection
The aim of this paper is to formalise the task of continual semi-supervised anomaly detection (CSAD), with the aim of highlighting the importance of such a problem formulation which assumes as close to real-world conditions as possible.
Revised Regularization for Efficient Continual Learning through Correlation-Based Parameter Update in Bayesian Neural Networks
In the continual learning framework employing variational inference, our study introduces a regularization term that specifically targets the dynamics and population of the mean and variance of the parameters.
GraphVL: Graph-Enhanced Semantic Modeling via Vision-Language Models for Generalized Class Discovery
Generalized Category Discovery (GCD) aims to cluster unlabeled images into known and novel categories using labeled images from known classes.
TFS-NeRF: Template-Free NeRF for Semantic 3D Reconstruction of Dynamic Scene
Despite advancements in Neural Implicit models for 3D surface reconstruction, handling dynamic environments with interactions between arbitrary rigid, non-rigid, or deformable entities remains challenging.
Incremental Open-set Domain Adaptation
In the second step, this pseudo source is adapted to the present target domain.
COSMo: CLIP Talks on Open-Set Multi-Target Domain Adaptation
To the best of our knowledge, COSMo is the first method to address Open-Set Multi-Target DA (OSMTDA), offering a more realistic representation of real-world scenarios and addressing the challenges of both open-set and multi-target DA.
Ranked #1 on
Open-Set Multi-Target Domain Adaptation
on Office-31
Multi-target Domain Adaptation
Open-Set Multi-Target Domain Adaptation
Elevating All Zero-Shot Sketch-Based Image Retrieval Through Multimodal Prompt Learning
SpLIP implements a bi-directional prompt-sharing strategy that enables mutual knowledge exchange between CLIP's visual and textual encoders, fostering a more cohesive and synergistic prompt processing mechanism that significantly reduces the semantic gap between the sketch and photo embeddings.
Few Shot Class Incremental Learning using Vision-Language models
Our proposed framework not only empowers the model to embrace novel classes with limited data, but also ensures the preservation of performance on base classes.
class-incremental learning
Few-Shot Class-Incremental Learning
+2
CDAD-Net: Bridging Domain Gaps in Generalized Category Discovery
In Generalized Category Discovery (GCD), we cluster unlabeled samples of known and novel classes, leveraging a training dataset of known classes.
Unknown Prompt, the only Lacuna: Unveiling CLIP's Potential for Open Domain Generalization
Central to our approach is modeling a unique prompt tailored for detecting unknown class samples, and to train this, we employ a readily accessible stable diffusion model, elegantly generating proxy images for the open class.
Scaling Vision-and-Language Navigation With Offline RL
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.
Unknown Prompt the only Lacuna: Unveiling CLIP's Potential for Open Domain Generalization
We delve into Open Domain Generalization (ODG) marked by domain and category shifts between training's labeled source and testing's unlabeled target domains.
C-SAW: Self-Supervised Prompt Learning for Image Generalization in Remote Sensing
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.
Learning Class and Domain Augmentations for Single-Source Open-Domain Generalization
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.
HAVE-Net: Hallucinated Audio-Visual Embeddings for Few-Shot Classification with Unimodal Cues
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.
Domain Adaptive Few-Shot Open-Set Learning
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.
Ranked #1 on
cross-domain few-shot learning
on Office-Home
GOPro: Generate and Optimize Prompts in CLIP using Self-Supervised Learning
GOPro is trained end-to-end on all three loss objectives, combining the strengths of CLIP and SSL in a principled manner.
AD-CLIP: Adapting Domains in Prompt Space Using CLIP
We leverage the frozen vision backbone of CLIP to extract both image style (domain) and content information, which we apply to learn prompt tokens.
Temporal DINO: A Self-supervised Video Strategy to Enhance Action Prediction
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.
Physically Plausible 3D Human-Scene Reconstruction from Monocular RGB Image using an Adversarial Learning Approach
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.
Visual Question Answering in Remote Sensing with Cross-Attention and Multimodal Information Bottleneck
In this research, we deal with the problem of visual question answering (VQA) in remote sensing.
Semi-Supervised Learning for hyperspectral images by non parametrically predicting view assignment
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.
USIM-DAL: Uncertainty-aware Statistical Image Modeling-based Dense Active Learning for Super-resolution
Dense regression is a widely used approach in computer vision for tasks such as image super-resolution, enhancement, depth estimation, etc.
APPLeNet: Visual Attention Parameterized Prompt Learning for Few-Shot Remote Sensing Image Generalization using CLIP
APPLeNet emphasizes the importance of multi-scale feature learning in RS scene classification and disentangles visual style and content primitives for domain generalization tasks.
StyLIP: Multi-Scale Style-Conditioned Prompt Learning for CLIP-based Domain Generalization
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.
MultiScale Probability Map guided Index Pooling with Attention-based learning for Road and Building Segmentation
Efficient road and building footprint extraction from satellite images are predominant in many remote sensing applications.
Prototypical quadruplet for few-shot class incremental learning
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.
class-incremental learning
Few-Shot Class-Incremental Learning
+1
RSINet: Inpainting Remotely Sensed Images Using Triple GAN Framework
We tackle the problem of image inpainting in the remote sensing domain.
Zero-Shot Sketch Based Image Retrieval using Graph Transformer
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.
BDA-SketRet: Bi-Level Domain Adaptation for Zero-Shot SBIR
The efficacy of zero-shot sketch-based image retrieval (ZS-SBIR) models is governed by two challenges.
FRIDA -- Generative Feature Replay for Incremental Domain Adaptation
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
A distillation based approach for the diagnosis of diseases
Presently, Covid-19 is a serious threat to the world at large.
Two Headed Dragons: Multimodal Fusion and Cross Modal Transactions
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.
Federated Action Recognition on Heterogeneous Embedded Devices
Federated learning allows a large number of devices to jointly learn a model without sharing data.
CrossATNet - A Novel Cross-Attention Based Framework for Sketch-Based Image Retrieval
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.
Trusting small training dataset for supervised change detection
Deep learning (DL) based supervised change detection (CD) models require large labeled training data.
Empowering Knowledge Distillation via Open Set Recognition for Robust 3D Point Cloud Classification
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.
A Novel Actor Dual-Critic Model for Remote Sensing Image Captioning
We deal with the problem of generating textual captions from optical remote sensing (RS) images using the notion of deep reinforcement learning.
Multimodal Noisy Segmentation based fragmented burn scars identification in Amazon Rainforest
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.
A Zero-Shot Sketch-based Inter-Modal Object Retrieval Scheme for Remote Sensing Images
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.
Saliency-driven Class Impressions for Feature Visualization of Deep Neural Networks
Existing visualization methods develop high confidence images consisting of both background and foreground features.
Teaching CNNs to mimic Human Visual Cognitive Process & regularise Texture-Shape bias
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.
Discriminative Dictionary Design for Action Classification in Still Images and Videos
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.
Generative Model-driven Structure Aligning Discriminative Embeddings for Transductive Zero-shot Learning
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.
Distilling Spikes: Knowledge Distillation in Spiking Neural Networks
We also present a multi-stage knowledge distillation technique for SNNs using an intermediate network to obtain higher performance from the student network.
Image-based phenotyping of diverse Rice (Oryza Sativa L.) Genotypes
The present investigation is carried out for discriminating drought tolerant, and susceptible genotypes.
LEt-SNE: A Hybrid Approach To Data Embedding and Visualization of Hyperspectral Imagery
Some popular techniques among these falter when applied to Hyperspectral Imagery due to the famed curse of dimensionality.
Online Sensor Hallucination via Knowledge Distillation for Multimodal Image Classification
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.
CMIR-NET : A Deep Learning Based Model For Cross-Modal Retrieval In Remote Sensing
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.
Hierarchical Metric Learning for Optical Remote Sensing Scene Categorization
We address the problem of scene classification from optical remote sensing (RS) images based on the paradigm of hierarchical metric learning.
