Publications

Preprints

1. How (Mis)calibrated is Your Federated CLIP and What To Do About It?
   Mainak Singha, Masih Aminbeidokhti, Paolo Casari, Elisa Ricci, Subhankar Roy
   arXiv Preprint, 2025.
   [ arXiv ]   [ Code ]   [ BibTeX ]

   @article{singha2025mis,
     title={How (Mis) calibrated is Your Federated CLIP and What To Do About It?},
     author={Singha, Mainak and Aminbeidokhti, Masih and Casari, Paolo and Ricci, Elisa and Roy, Subhankar},
     journal={arXiv preprint arXiv:2512.04305},
     year={2025}
   }
   

Conferences

1. FedMVP: Federated Multi-modal Visual Prompt Tuning for Vision-Language Models
   Mainak Singha, Subhankar Roy, Sarthak Mehrotra, Ankit Jha, Moloud Abdar, Biplab Banerjee, Elisa Ricci
   International Conference on Computer Vision (ICCV), 2025.
   [ PDF ]   [ arXiv ]   [ Code ]   [ HTML ]   [ BibTeX ]

   @article{fedmvp,
     title={FedMVP: Federated Multi-modal Visual Prompt Tuning for Vision-Language Models},
     author={Singha, Mainak and Roy, Subhankar and Mehrotra, Sarthak and Jha, Ankit and Abdar, Moloud and Banerjee, Biplab and Ricci, Elisa},
     journal={Proceedings of the IEEE/CVF International Conference on Computer Vision},
     year={2025}
   }
   

2. OSLoPrompt: Bridging Low-Supervision Challenges and Open-Set Domain Generalization in CLIP
   Mohamad Hassan N C, Divyam Gupta, Mainak Singha, Sai Bhargav Rongali, Ankit Jha, Muhammad Haris Khan, Biplab Banerjee
   Computer Vision and Pattern Recognition Conference (CVPR), 2025.
   [ PDF ]   [ arXiv ]   [ Code ]   [ HTML ]   [ BibTeX ]

   @inproceedings{gupta2025osloprompt,
     title={OSLoPrompt: Bridging Low-Supervision Challenges and Open-Set Domain Generalization in CLIP},
     author={Gupta, Divyam and Singha, Mainak and Rongali, Sai Bhargav and Jha, Ankit and Khan, Muhammad Haris and Banerjee, Biplab and others},
     booktitle={Proceedings of the Computer Vision and Pattern Recognition Conference},
     pages={10110--10120},
     year={2025}
   }
   

3. Elevating All Zero-Shot Sketch-Based Image Retrieval Through Multimodal Prompt Learning
   Mainak Singha, Ankit Jha, Divyam Gupta, Pranav Singla, Biplab Banerjee
   European Conference on Computer Vision (ECCV), 2024.
   [ PDF ]   [ arXiv ]   [ Code ]   [ Project ]   [ HTML ]   [ BibTeX ]

   @inproceedings{singha2024elevating,
     title={Elevating all zero-shot sketch-based image retrieval through multimodal prompt learning},
     author={Singha, Mainak and Jha, Ankit and Gupta, Divyam and Singla, Pranav and Banerjee, Biplab},
     booktitle={European Conference on Computer Vision},
     pages={1--19},
     year={2024},
     organization={Springer}
   }
   

4. COSMo: CLIP Talks on Open-Set Multi-Target Domain Adaptation
   Munish Monga, Sachin Kumar Giroh, Ankit Jha, Mainak Singha, Biplab Banerjee, Jocelyn Chanussot
   British Machine Vision Conference (BMVC), 2024.
   [ PDF ]   [ arXiv ]   [ Code ]   [ HTML ]   [ BibTeX ]

   @article{monga2024cosmo,
     title={COSMo: CLIP Talks on Open-Set Multi-Target Domain Adaptation},
     author={Monga, Munish and Giroh, Sachin Kumar and Jha, Ankit and Singha, Mainak and Banerjee, Biplab and Chanussot, Jocelyn},
     journal={arXiv preprint arXiv:2409.00397},
     year={2024}
   }
   

5. Unknown Prompt, the only Lacuna: Unveiling CLIP’s Potential for Open Domain Generalization
   Mainak Singha, Ankit Jha, Shirsha Bose, Ashwin Nair, Moloud Abdar, Biplab Banerjee
   Computer Vision and Pattern Recognition Conference (CVPR), 2024.
   [ PDF ]   [ arXiv ]   [ Code ]   [ HTML ]   [ BibTeX ]

   @inproceedings{singha2024unknown,
     title={Unknown Prompt the only Lacuna: Unveiling CLIP's Potential for Open Domain Generalization},
     author={Singha, Mainak and Jha, Ankit and Bose, Shirsha and Nair, Ashwin and Abdar, Moloud and Banerjee, Biplab},
     booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
     pages={13309--13319},
     year={2024}
   }
   

6. CDAD-Net: Bridging Domain Gaps in Generalized Category Discovery
   Sai Bhargav Rongali, Sarthak Mehrotra, Ankit Jha, Mohamad Hassan N C, Shirsha Bose, Tanisha Gupta, Mainak Singha, Biplab Banerjee
   Computer Vision and Pattern Recognition Conference (CVPR) Workshops, 2024.
   [ PDF ]   [ arXiv ]   [ Code ]   [ HTML ]   [ BibTeX ]

   @inproceedings{rongali2024cdad,
     title={Cdad-net: Bridging domain gaps in generalized category discovery},
     author={Rongali, Sai Bhargav and Mehrotra, Sarthak and Jha, Ankit and Bose, Shirsha and Gupta, Tanisha and Singha, Mainak and Banerjee, Biplab and others},
     booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
     pages={2616--2626},
     year={2024}
   }
   

7. GraphVL: Graph-Enhanced Semantic Modeling via Vision-Language Models for Generalized Class Discovery
   Bhupendra Solanki, Ashwin R Nair, Mainak Singha, Souradeep Mukhopadhyay, Ankit Jha, Biplab Banerjee
   Indian Conference on Computer Vision Graphics and Image Processing (ICVGIP), 2024.
   [ PDF ]   [ arXiv ]   [ HTML ]   [ BibTeX ]

   @inproceedings{solanki2024graphvl,
     title={GraphVL: graph-enhanced semantic modeling via vision-language models for generalized class discovery},
     author={Solanki, Bhupendra and Nair, Ashwin R and Singha, Mainak and Mukhopadhyay, Souradeep and Jha, Ankit and Banerjee, Biplab},
     booktitle={Proceedings of the Fifteenth Indian Conference on Computer Vision Graphics and Image Processing},
     pages={1--10},
     year={2024}
   }
   

8. StyLIP: Multi-Scale Style-Conditioned Prompt Learning for CLIP-based Domain Generalization
   Shirsha Bose, Ankit Jha, Enrico Fini, Mainak Singha, Biplab Banerjee, Elisa Ricci
   Winter Conference on Applications of Computer Vision (WACV), 2024.
   [ PDF ]   [ arXiv ]   [ HTML ]   [ BibTeX ]

   @inproceedings{bose2024stylip,
     title={Stylip: Multi-scale style-conditioned prompt learning for clip-based domain generalization},
     author={Bose, Shirsha and Jha, Ankit and Fini, Enrico and Singha, Mainak and Ricci, Elisa and Banerjee, Biplab},
     booktitle={Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision},
     pages={5542--5552},
     year={2024}
   }
   

9. C-SAW: Self-Supervised Prompt Learning for Image Generalization in Remote Sensing [Best Paper Award]
   Avigyan Bhattacharya, Mainak Singha, Ankit Jha, Biplab Banerjee
   Indian Conference on Computer Vision Graphics and Image Processing (ICVGIP), 2023.
   [ PDF ]   [ arXiv ]   [ Code ]   [ HTML ]   [ BibTeX ]

   @inproceedings{bhattacharya2023c,
     title={C-SAW: self-supervised prompt learning for image generalization in remote sensing},
     author={Bhattacharya, Avigyan and Singha, Mainak and Jha, Ankit and Banerjee, Biplab},
     booktitle={Proceedings of the Fourteenth Indian Conference on Computer Vision, Graphics and Image Processing},
     pages={1--10},
     year={2023}
   }
   

10. GOPro: Generate and Optimize Prompts in CLIP using Self-Supervised Learning
    Mainak Singha, Ankit Jha, Biplab Banerjee
    British Machine Vision Conference (BMVC), 2023.
    [ PDF ]   [ arXiv ]   [ Code ]   [ HTML ]   [ BibTeX ]

    @article{singha2023gopro,
      title={Gopro: Generate and optimize prompts in clip using self-supervised learning},
      author={Singha, Mainak and Jha, Ankit and Banerjee, Biplab},
      journal={arXiv preprint arXiv:2308.11605},
      year={2023}
    }
    

11. AD-CLIP: Adapting Domains in Prompt Space Using CLIP
    Mainak Singha, Harsh Pal, Ankit Jha, Biplab Banerjee
    International Conference on Computer Vision (ICCV) Workshops, 2023.
    [ PDF ]   [ arXiv ]   [ Code ]   [ HTML ]   [ BibTeX ]

    @inproceedings{singha2023ad,
      title={Ad-clip: Adapting domains in prompt space using clip},
      author={Singha, Mainak and Pal, Harsh and Jha, Ankit and Banerjee, Biplab},
      booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
      pages={4355--4364},
      year={2023}
    }
    

12. HAVE-Net: Hallucinated Audio-Visual Embeddings for Few-Shot Classification with Unimodal Cues [Best Paper Award]
    Ankit Jha, Debabrata Pal, Mainak Singha, Naman Agarwal, Biplab Banerjee
    European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML-PKDD) Workshops, 2023.
    [ PDF ]   [ arXiv ]   [ HTML ]   [ BibTeX ]

    @inproceedings{jha2023have,
      title={HAVE-Net: Hallucinated Audio-Visual Embeddings for Few-Shot Classification with Unimodal Cues},
      author={Jha, Ankit and Pal, Debabrata and Singha, Mainak and Agarwal, Naman and Banerjee, Biplab},
      booktitle={Joint European Conference on Machine Learning and Knowledge Discovery in Databases},
      pages={390--398},
      year={2023},
      organization={Springer}
    }
    

13. APPLeNet: Visual Attention Parameterized Prompt Learning for Few-Shot Remote Sensing Image Generalization Using CLIP
    Mainak Singha, Ankit Jha, Bhupendra Solanki, Shirsha Bose, Biplab Banerjee
    Computer Vision and Pattern Recognition Conference (CVPR) Workshops, 2023.
    [ PDF ]   [ arXiv ]   [ Code ]   [ HTML ]   [ BibTeX ]

    @inproceedings{singha2023applenet,
      title={Applenet: Visual attention parameterized prompt learning for few-shot remote sensing image generalization using clip},
      author={Singha, Mainak and Jha, Ankit and Solanki, Bhupendra and Bose, Shirsha and Banerjee, Biplab},
      booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
      pages={2024--2034},
      year={2023}
    }
    

Journals

1. Meta-Learning to Teach Semantic Prompts for Open Domain Generalization in Vision-Language Models
   Shirsha Bose, Mainak Singha, Ankit Jha, Souradeep Mukhopadhyay, Biplab Banerjee
   Transactions on Machine Learning Research (TMLR), 2025.
   [ PDF ]   [ HTML ]   [ BibTeX ]

   @article{bose2025meta,
     title={Meta-Learning to Teach Semantic Prompts for Open Domain Generalization in Vision-Language Models},
     author={Bose, Shirsha and Singha, Mainak and Jha, Ankit and Mukhopadhyay, Souradeep and Banerjee, Biplab},
     journal={Transactions on Machine Learning Research},
     year={2025}
   }
   

2. RS³Lip: Consistency for Remote Sensing Image Classification on Part Embeddings using Self-Supervised Learning and CLIP
   Ankit Jha, Mainak Singha, Avigyan Bhattacharya, Biplab Banerjee
   Computer Vision and Image Understanding (CVIU), 2025.
   [ PDF ]   [ HTML ]   [ BibTeX ]

   @article{jha2025rs3lip,
     title={RS3Lip: Consistency for remote sensing image classification on part embeddings using self-supervised learning and CLIP},
     author={Jha, Ankit and Singha, Mainak and Bhattacharya, Avigyan and Banerjee, Biplab},
     journal={Computer Vision and Image Understanding},
     volume={251},
     pages={104254},
     year={2025},
     publisher={Elsevier}
   }
   

3. Towards Molecular Structure Discovery from Cryo-ET Density Volumes via Modelling Auxiliary Semantic Prototypes
   Ashwin Nair, Xingjian Li, Bhupendra Solanki, Souradeep Mukhopadhyay, Ankit Jha, Mostofa Rafid Uddin, Mainak Singha, Biplab Banerjee, Min Xu
   Briefings in Bioinformatics, 2024.
   [ PDF ]   [ HTML ]   [ BibTeX ]

   @article{nair2024towards,
     title={Towards molecular structure discovery from cryo-ET density volumes via modelling auxiliary semantic prototypes},
     author={Nair, Ashwin and Li, Xingjian and Solanki, Bhupendra and Mukhopadhyay, Souradeep and Jha, Ankit and Rafid\_Uddin, Mostofa and Singha, Mainak and Banerjee, Biplab and Xu, Min},
     journal={Briefings in Bioinformatics},
     volume={26},
     number={1},
     year={2024},
     publisher={Oxford University Press}
   }