Ankit Jha
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Ankit Jha has a total of 52 co-authors. Here are the top co-authors by number of shared publications:
- Biplab Banerjee
Indian Institute of Technology Bombay
12 shared publications - Mainak Singha
Indian Institute of Technology Bombay, Mumbai, IN
10 shared publications Biplab Banerjee
7 shared publications- Shirsha Bose
Department of Informatics, Technical University of Munich, Munich, Bavaria 85748, Germany
5 shared publications Mainak Singha
Indian Institue of Technology Bombay
3 shared publicationsAshwin Nair
IISER Thiruvananthapuram,India
2 shared publications
Latest Publications
- 18 June 2026
- Published by Springer Nature in Journal of the Indian Society of Remote Sensing
- Vol. 54 (10) , 1-14
Slum Detection Using U-Net Attention Gate on Mid-Resolution Satellite Imagery
- 18 June 2026
- Published by Springer Nature in Journal of the Indian Society of Remote Sensing
- Vol. 54 (10) , 1-14
Slum Detection Using U-Net Attention Gate on Mid-Resolution Satellite Imagery
- Open Access
SDHSI-Net: Learning Better Representations for Hyperspectral Images via Self-Distillation
Hyperspectral image (HSI) classification presents unique challenges due to its high spectral dimensionality and limited labeled data. Traditional deep learning models often suffer from overfitting and high computational costs. Self-distillation (SD), a variant of knowledge distillation where a network learns from its own predictions, has recently emerged as a promising strategy to enhance model performance without requiring external teacher networks. In this work, we explore the application of SD to HSI by treating earlier outputs as soft targets, thereby enforcing consistency between intermediate and final predictions. This process improves intra-class compactness and inter-class separability in the learned feature space. Our approach is validated on two benchmark HSI datasets and demonstrates significant improvements in classification accuracy and robustness, highlighting the effectiveness of SD for spectral-spatial learning. Codes are available at https://github.com/Prachet-Dev-Singh/SDHSI.
Open AccessSDHSI-Net: Learning Better Representations for Hyperspectral Images via Self-Distillation
Hyperspectral image (HSI) classification presents unique challenges due to its high spectral dimensionality and limited labeled data. Traditional deep learning models often suffer from overfitting and high computational costs. Self-distillation (SD), a variant of knowledge distillation where a network learns from its own predictions, has recently emerged as a promising strategy to enhance model performance without requiring external teacher networks. In this work, we explore the application of SD to HSI by treating earlier outputs as soft targets, thereby enforcing consistency between intermediate and final predictions. This process improves intra-class compactness and inter-class separability in the learned feature space. Our approach is validated on two benchmark HSI datasets and demonstrates significant improvements in classification accuracy and robustness, highlighting the effectiveness of SD for spectral-spatial learning. Codes are available at https://github.com/Prachet-Dev-Singh/SDHSI.
- Open Access
Reconstruction Guided Few-shot Network For Remote Sensing Image Classification
Few-shot remote sensing image classification is challenging due to limited labeled samples and high variability in land-cover types. We propose a reconstruction-guided few-shot network (RGFS-Net) that enhances generalization to unseen classes while preserving consistency for seen categories. Our method incorporates a masked image reconstruction task, where parts of the input are occluded and reconstructed to encourage semantically rich feature learning. This auxiliary task strengthens spatial understanding and improves class discrimination under low-data settings. We evaluated the efficacy of EuroSAT and PatternNet datasets under 1-shot and 5-shot protocols, our approach consistently outperforms existing baselines. The proposed method is simple, effective, and compatible with standard backbones, offering a robust solution for few-shot remote sensing classification. Codes are available at https://github.com/stark0908/RGFS.
Open AccessReconstruction Guided Few-shot Network For Remote Sensing Image Classification
Few-shot remote sensing image classification is challenging due to limited labeled samples and high variability in land-cover types. We propose a reconstruction-guided few-shot network (RGFS-Net) that enhances generalization to unseen classes while preserving consistency for seen categories. Our method incorporates a masked image reconstruction task, where parts of the input are occluded and reconstructed to encourage semantically rich feature learning. This auxiliary task strengthens spatial understanding and improves class discrimination under low-data settings. We evaluated the efficacy of EuroSAT and PatternNet datasets under 1-shot and 5-shot protocols, our approach consistently outperforms existing baselines. The proposed method is simple, effective, and compatible with standard backbones, offering a robust solution for few-shot remote sensing classification. Codes are available at https://github.com/stark0908/RGFS.
- 19 February 2025
- Published by Elsevier in Solar Energy
- Vol. 290
Leveraging large-scale aerial data for accurate urban rooftop solar potential estimation via multitask learning
- 19 February 2025
- Published by Elsevier in Solar Energy
- Vol. 290
Leveraging large-scale aerial data for accurate urban rooftop solar potential estimation via multitask learning
- 1 January 2025
- Published by Springer Nature
- p. 390-398
HAVE-Net: Hallucinated Audio-Visual Embeddings for Few-Shot Classification with Unimodal Cues
- 1 January 2025
- Published by Springer Nature
- p. 390-398
HAVE-Net: Hallucinated Audio-Visual Embeddings for Few-Shot Classification with Unimodal Cues
- Open Access
- 13 December 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-10
Can Commonsense Knowledge Improve CLIP's Performance in Cross-Domain VQA?
- 13 December 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-10
Open AccessCan Commonsense Knowledge Improve CLIP's Performance in Cross-Domain VQA?
- Open Access
- 13 December 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-10
GraphVL: Graph-Enhanced Semantic Modeling via Vision-Language Models for Generalized Class Discovery
- 13 December 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-10
Open AccessGraphVL: Graph-Enhanced Semantic Modeling via Vision-Language Models for Generalized Class Discovery
- Open Access
Foundation Models and Adaptive Feature Selection: A Synergistic Approach to Video Question Answering
This paper tackles the intricate challenge of video question-answering (VideoQA). Despite notable progress, current methods fall short of effectively integrating questions with video frames and semantic object-level abstractions to create question-aware video representations. We introduce Local-Global Question Aware Video Embedding (LGQAVE), which incorporates three major innovations to integrate multi-modal knowledge better and emphasize semantic visual concepts relevant to specific questions. LGQAVE moves beyond traditional ad-hoc frame sampling by utilizing a cross-attention mechanism that precisely identifies the most relevant frames concerning the questions. It captures the dynamics of objects within these frames using distinct graphs, grounding them in question semantics with the miniGPT model. These graphs are processed by a question-aware dynamic graph transformer (Q-DGT), which refines the outputs to develop nuanced global and local video representations. An additional cross-attention module integrates these local and global embeddings to generate the final video embeddings, which a language model uses to generate answers. Extensive evaluations across multiple benchmarks demonstrate that LGQAVE significantly outperforms existing models in delivering accurate multi-choice and open-ended answers.
Open AccessFoundation Models and Adaptive Feature Selection: A Synergistic Approach to Video Question Answering
This paper tackles the intricate challenge of video question-answering (VideoQA). Despite notable progress, current methods fall short of effectively integrating questions with video frames and semantic object-level abstractions to create question-aware video representations. We introduce Local-Global Question Aware Video Embedding (LGQAVE), which incorporates three major innovations to integrate multi-modal knowledge better and emphasize semantic visual concepts relevant to specific questions. LGQAVE moves beyond traditional ad-hoc frame sampling by utilizing a cross-attention mechanism that precisely identifies the most relevant frames concerning the questions. It captures the dynamics of objects within these frames using distinct graphs, grounding them in question semantics with the miniGPT model. These graphs are processed by a question-aware dynamic graph transformer (Q-DGT), which refines the outputs to develop nuanced global and local video representations. An additional cross-attention module integrates these local and global embeddings to generate the final video embeddings, which a language model uses to generate answers. Extensive evaluations across multiple benchmarks demonstrate that LGQAVE significantly outperforms existing models in delivering accurate multi-choice and open-ended answers.
- 10 December 2024
- Published by Elsevier in Computer Vision and Image Understanding
- Vol. 251
RSLip: Consistency for remote sensing image classification on part embeddings using self-supervised learning and CLIP- 10 December 2024
- Published by Elsevier in Computer Vision and Image Understanding
- Vol. 251
RSLip: Consistency for remote sensing image classification on part embeddings using self-supervised learning and CLIP- Open Access
In the Era of Prompt Learning with Vision-Language Models
Large-scale foundation models like CLIP have shown strong zero-shot generalization but struggle with domain shifts, limiting their adaptability. In our work, we introduce \textsc{StyLIP}, a novel domain-agnostic prompt learning strategy for Domain Generalization (DG). StyLIP disentangles visual style and content in CLIP`s vision encoder by using style projectors to learn domain-specific prompt tokens and combining them with content features. Trained contrastively, this approach enables seamless adaptation across domains, outperforming state-of-the-art methods on multiple DG benchmarks. Additionally, we propose AD-CLIP for unsupervised domain adaptation (DA), leveraging CLIP`s frozen vision backbone to learn domain-invariant prompts through image style and content features. By aligning domains in embedding space with entropy minimization, AD-CLIP effectively handles domain shifts, even when only target domain samples are available. Lastly, we outline future work on class discovery using prompt learning for semantic segmentation in remote sensing, focusing on identifying novel or rare classes in unstructured environments. This paves the way for more adaptive and generalizable models in complex, real-world scenarios.
Open AccessIn the Era of Prompt Learning with Vision-Language Models
Large-scale foundation models like CLIP have shown strong zero-shot generalization but struggle with domain shifts, limiting their adaptability. In our work, we introduce \textsc{StyLIP}, a novel domain-agnostic prompt learning strategy for Domain Generalization (DG). StyLIP disentangles visual style and content in CLIP`s vision encoder by using style projectors to learn domain-specific prompt tokens and combining them with content features. Trained contrastively, this approach enables seamless adaptation across domains, outperforming state-of-the-art methods on multiple DG benchmarks. Additionally, we propose AD-CLIP for unsupervised domain adaptation (DA), leveraging CLIP`s frozen vision backbone to learn domain-invariant prompts through image style and content features. By aligning domains in embedding space with entropy minimization, AD-CLIP effectively handles domain shifts, even when only target domain samples are available. Lastly, we outline future work on class discovery using prompt learning for semantic segmentation in remote sensing, focusing on identifying novel or rare classes in unstructured environments. This paves the way for more adaptive and generalizable models in complex, real-world scenarios.