Ankit Jha

Ankit Jha

Auto-generated profile, based on publicly available information

Ankit Jha

Dept. of CSE The LNMIIT Jaipur

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
16 June 2024
Verified
Conference Paper
Closed access
MSMainak Singha
Mainak Singha
AJAnkit Jha
Ankit Jha
SBShirsha Bose
Shirsha Bose
ANAshwin Nair
Ashwin Nair
MAMoloud Abdar
Moloud Abdar
Biplab BanerjeeBiplab Banerjee
Biplab Banerjee
We delve into Open Domain Generalization (ODG), marked by domain and category shifts between training's labeled source and testing's unlabeled target domains. Existing solutions to ODG face limitations due to constrained generalizations of traditional CNN backbones and errors in detecting target open samples in the absence of prior knowledge. Addressing these pitfalls, we introduce ODG-CLIP, harnessing the semantic prowess of the vision-language model, CLIP. Our framework brings forth three primary innovations: Firstly, distinct from prevailing paradigms, we conceptualize ODG as a multi-class classification challenge encompassing both known and novel categories. 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. Secondly, aiming for domain-tailored classification (prompt) weights while ensuring a balance of precision and simplicity, we devise a novel visual stylecentric prompt learning mechanism. Finally, we infuse images with class-discriminative knowledge derived from the prompt space to augment the fidelity of CLIP's visual embeddings. We introduce a novel objective to safeguard the continuity of this infused semantic intel across domains, especially for the shared classes. Through rigorous testing on diverse datasets, covering closed and open-set DG contexts, ODG-CLIP demonstrates clear supremacy, consistently outpacing peers with performance boosts between 8%-16%. Code will be available at https://github.com/mainaksingha01/ODG-CLIP.

19 February 2025 in Solar Energy
Verified
Journal Article
Closed access
ABAlessia Boccalatte
Alessia Boccalatte
AJAnkit Jha
Ankit Jha
JCJocelyn Chanussot
Jocelyn Chanussot

16 August 2023 in Pattern Recognition Letters
Verified
Journal Article
Closed access
DPDebabrata Pal
Debabrata Pal
SBShirsha Bose
Shirsha Bose
DMDeeptej More
Deeptej More
AJAnkit Jha
Ankit Jha
BBBiplab Banerjee
Biplab Banerjee
YJYogananda Jeppu
Yogananda Jeppu

16 October 2023 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
AJAnkit Jha
Ankit Jha
Biplab BanerjeeBiplab Banerjee
Biplab Banerjee
Deep neural networks are highly specialized for a given task and visual domain, which can limit their practical use. To address this issue, recent studies have proposed to learn universal feature extractors that can be used across multiple domains simultaneously, inspired by the success of transfer learning. However, these universal features are still inferior to specialized networks. In the context of hyperspectral image (HSI) classification, the lack of labeled training samples due to high cost and the restriction to single-domain learning further complicates the problem. To overcome these challenges, we propose a solution that combines the problems of multi-domain learning (MDL) and few-shot learning (FSL) for HSI classification. Our goal is to train a highly shareable network with all domains in the low-shot training regime. We call our network the Multi-Domain Few-Shot (MDFS) network, which shares the majority of model parameters (specifically, convolution and dense layer parameters) across domains while keeping domain-specific batch-normalization layers separate to capture domain characteristics. To address the overfitting issue in few-shot models, we supplement the main classification task with an auxiliary self-supervised task. We test our proposed method on five benchmark HSI datasets and find that MDFS-Net consistently outperforms relevant baselines convincingly. Our approach offers a promising solution for HSI classification in remote sensing by enabling the design of a unified classification system that can work with multiple HSI sites (domains) and fewer labeled samples.


15 December 2023
Verified
Conference Paper
Open access
ABAvigyan Bhattacharya
Avigyan Bhattacharya
MSMainak Singha
Mainak Singha
AJAnkit Jha
Ankit Jha
Biplab BanerjeeBiplab Banerjee
Biplab Banerjee
We focus on domain and class generalization problems in analyzing optical remote sensing images, using the large-scale pre-trained vision-language model (VLM), CLIP. While contrastively trained VLMs show impressive zero-shot generalization performance, their effectiveness is limited when dealing with diverse domains during training and testing. Existing prompt learning techniques overlook the importance of incorporating domain and content information into the prompts, which results in a drop in performance while dealing with such multi-domain data. To address these challenges, we propose a solution that ensures domain-invariant prompt learning while enhancing the expressiveness of visual features. We observe that CLIP’s vision encoder struggles to identify contextual image information, particularly when image patches are jumbled up. This issue is especially severe in optical remote sensing images, where land-cover classes exhibit well-defined contextual appearances. 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. We keep the CLIP backbone frozen and introduce a small set of projectors for both the CLIP encoders to train C-SAW contrastively. Experimental results demonstrate the superiority of C-SAW across multiple remote sensing benchmarks and different generalization tasks.