Goirik Chakrabarty

TCS Pre-Doctoral Researcher

goirik.jpeg

Hi there!👋 My name is Goirik Chakrabarty, and I am interested in Lifelong Learning and Multimodal Learning. From my experience with computer vision and continual learning and my current research project in vision-language modelsđŸ€–, I find it a critical field for real-world application. I aim to apply the principles of robustness and reliability that I have learnt in continual learning to the use of foundation models such as StableDiffusion and CLIP.

I am currently working as a Pre-Doctoral Researcher at TCS Research under Ramya Hebbalaguppe in collaboration with Prathosh A.P. (IISc Bangalore)

Prior to this, I completed my MS Thesis titled,”Continual Domain Incremental Learning during Test-time” under the supervision of Soma Biswas (IISc Bangalore) and Leelavati Narlikar (IISER Pune).

I am actively looking for PhD opportunities related to Robust, Reliable and Explainable Machine Learning! Feel free to contact me 😄

selected publications

  1. WACV
    pSTarC: Pseudo Source Guided Target Clustering for Fully Test-Time Adaptation
    Manogna Sreenivas, Goirik Chakrabarty, and Soma Biswas
    In Winter Conference on Applications of Computer Vision, 2024
  2. TMLR
    SANTA: Source Anchoring Network and Target Alignment for Continual Test Time Adaptation
    Goirik Chakrabarty, Manogna Sreenivas, and Soma Biswas
    In Transactions on Machine Learning Research, 2023
  3. ICCVW
    A Simple Signal for Domain Shift
    Goirik Chakrabarty, Manogna Sreenivas, and Soma Biswas
    In ICCV Workshops, 2023