Complete list of publications   *equal contribution
  • Jogendra Nath Kundu*, Suvaansh Bhambri*, Akshay Kulkarni*, Hiran Sarkar, Varun Jampani, and R. Venkatesh Babu,  Subsidiary Prototype Alignment for Universal Domain Adaptation, NeurIPS 2022 [OpenReview] [arXiv] [Project Page]
  • Jogendra Nath Kundu*, Suvaansh Bhambri*, Akshay Kulkarni*, Hiran Sarkar, Varun Jampani, and R. Venkatesh Babu,  Concurrent Subsidiary Supervision for Unsupervised Source-Free Domain Adaptation, ECCV 2022 [ECVA PDF] [arXiv] [Project Page]
  • Jogendra Nath Kundu*, Akshay Kulkarni*, S. Bhambri*, Deepesh Mehta, Shreyas Kulkarni, V. Jampani, and R. V. Babu,  Balancing Discriminability and Transferability for Source-Free Domain Adaptation, ICML 2022 [PMLR Landing Page] [arXiv] [Project Page]
  • Jogendra Nath Kundu*, Akshay Kulkarni*, S. Bhambri*, Varun Jampani, and R. Venkatesh Babu, Amplitude Spectrum Transformation for Open Compound Domain Adaptive Semantic Segmentation, AAAI 2022 [AAAI Landing Page] [arXiv] [Project Page] [Poster]
  • Jogendra Nath Kundu*, Akshay Kulkarni*, Amit Kumar Singh, Varun Jampani, and R. Venkatesh Babu, Generalize then Adapt: Source-Free Domain Adaptive Semantic Segmentation, ICCV 2021 [CVF Landing Page] [arXiv] [Project Page] [Poster] [IEEEXplore]
  • Rishika Bhagwatkar, Khurshed Fitter, Saketh Bachu, Akshay Kulkarni, Shital Chiddarwar, Paying Attention to Video Generation, NeurIPS 2020 Workshop on Pre-registration in Machine Learning, PMLR 148:139-154 [PMLR Landing Page] [PDF]
  • Aniket Gujarathi, Akshay Kulkarni, Unmesh Patil, et al., Design and Development of Autonomous Delivery Robot, 2021, Arxiv:2103.09229 [cs.RO] [Bachelor's Thesis] [arXiv] [Code]
  • Akshay Kulkarni*, Navid Panchi*, Sharath Chandra Raparthy, Shital Chiddarwar, Data Efficient Stagewise Knowledge Distillation, 2019, Arxiv:1911.06786 [cs.LG] [arXiv] [Code]
  • Unmesh Patil, Aniket Gujarathi, Akshay Kulkarni, et al., Deep Learning based Stair Detection and Statistical Image Filtering for Autonomous Stair Climbing, IEEE International Conference on Robotic Computing (IRC), 2019 [IEEEXplore] [Code]