Ajinkya Tejankar

PhD student at UC Davis.

my-website-pic.jpg

I am a 3rd year PhD student at University of California, Davis. My advisor is Dr. Hamed Pirsiavash.

Research: I primarily work on self-supervised learning for images. My focus thus far has been improving the quality of features learnt by self-supervised models. This has involved using knowledge distillation for improving smaller models and improving the loss functions for better semantic level grouping. Recently, I have become interested in analyzing the failure modes of these methods. Specifically, how changing the input dataset affects the representations of the final model? I am also interesting in vision-language pre-training.

Previously: I obtained my MS in Computer Science from UMBC in 2020. I interned at Meta AI in summer 2021, 2022 and at Matroid in summer 2020. Even before that I was a Software Engineer at Tavisca from 2014 to 2017.

Publications

(*) denotes shared first authorship

  1. CVPR
    Defending Against Patch-based Backdoor Attacks on Self-Supervised Learning
    Ajinkya Tejankar, Maziar Sanjabi , Qifan Wang , Sinong Wang , Hamed Firooz , Hamed Pirsiavash , and Liang Tan
    In Conference on Computer Vision and Pattern Recognition (CVPR) Jun 2023
  2. ECCV
    Constrained Mean Shift Using Distant Yet Related Neighbors for Representation Learning
    KL Navaneet* , Soroush Abbasi Koohpayegani* ,  Ajinkya Tejankar*, Kossar Pourahmadi , Akshayvarun Subramanya , and Hamed Pirsiavash
    In European Conference on Computer Vision (ECCV) Jun 2022
  3. CVPROral
    Backdoor Attacks on Self-supervised Learning
    Aniruddha Saha ,  Ajinkya Tejankar, Soroush Abbasi Koohpayegani , and Hamed Pirsiavash
    In Conference on Computer Vision and Pattern Recognition (CVPR) Jun 2022
  4. NeurIPS W.
    Can we train vision and language zero-shot classification models without syntax?
    Ajinkya Tejankar, Bichen Wu , Saining Xie , Madian Khabsa , Hamed Pirsiavash , and Hamed Firooz
    In NeurIPS SSL Theory and Practice Workshop Dec 2022
  5. BMVC
    SimReg: Regression as a Simple Yet Effective Tool for Self-supervised Knowledge Distillation
    KL Navaneet , Soroush Abbasi Koohpayegani ,  Ajinkya Tejankar, and Hamed Pirsiavash
    In British Machine Vision Conference (BMVC) Nov 2021
  6. ICCVOral
    Mean Shift for Self-Supervised Learning
    Soroush Abbasi Koohpayegani* ,  Ajinkya Tejankar*, and Hamed Pirsiavash
    In International Conference on Computer Vision (ICCV) Oct 2021
  7. ICCV
    ISD: Self-Supervised Learning by Iterative Similarity Distillation
    Ajinkya Tejankar*, Soroush Abbasi Koohpayegani* , Vipin Pillai , Paolo Favaro , and Hamed Pirsiavash
    In International Conference on Computer Vision (ICCV) Oct 2021
  8. NeurIPS
    CompRess: Self-Supervised Learning by Compressing Representations
    Soroush Abbasi Koohpayegani* ,  Ajinkya Tejankar*, and Hamed Pirsiavash
    In Advances in Neural Information Processing Systems (NeurIPS) Dec 2020