Tempe, AZ
Joined July 2017
- Tweets9
- Following144
- Followers31
- Likes12
Rakshith Subramanyam retweeted
Need to adapt classifiers to novel target domains but don't have enough data? We are excited to present SiSTA, which adapts generative models with only one target sample and produces target-aware augmentations!. Poster#104@10:30 today #ICML2023 #icml w/ amazing co-authors. A 🧵
Venturing into single-shot domain adaptation? Meet SiSTA, our solution for large distribution shifts using a single-shot target! 🎯
🌐 Project: rakshith-2905.github.io/SiST…
Join us: ⏱️ Session: 27 Jul, 10:30 a.m. HST (Poster #104)
In collaboration with @kowshik0808 @pturaga1 @jjayram7
Rakshith Subramanyam retweeted
Interested in adapting high quality, pretrained models for safe & effective generalization on downstream tasks? Check out our new paper where we take a closer at model adaptation using feature distortion & simplicity bias! arxiv.org/abs/2303.13500 #ICLR2023🧵
Rakshith Subramanyam retweeted
Are large-scale generative models (StyleGAN-XL) useful for data constrained domain adaptation? Our #ICML2023 paper introduces SiSTA, a new data augmentation method that works even with one shot!! Preprint & codes coming out soon. Stay tuned. @kowshik0808 @rakshith_subra @pturaga1
Rakshith Subramanyam retweeted
🇮🇳 🇺🇸 His Excellency @SandhuTaranjitS, India's Ambassador to the United States, recently visited the Luminosity Lab to meet the students and explore the Rodel, our cutting-edge simulation designed to assist policymakers in making informed decisions about Arizona and beyond. – at Phoenix, AZ
Rakshith Subramanyam retweeted
Codes for our #Neurips2022 paper on Delta-UQ are officially out now! If you are looking to quickly integrate an epistemic uncertainty estimator to your deep model, please check this out! @LLNL
Repo: github.com/LLNL/DeltaUQ
Paper: arxiv.org/pdf/2207.07235.pdf
Rakshith Subramanyam retweeted
2. Interested in few-shot learners that generalize across domains or to even unseen datasets? Check out CAML - it uses contrastively trained knowledge graph bridges for meta learning. Here is our paper led by @rakshith_subra
arxiv.org/abs/2207.12346
Jan 5 1815--1915 in Session 6B
Rakshith Subramanyam retweeted
Come check out our work this Saturday at the PODs workshop at #ICML! We look at adapting pretrained models for both safety and generalization. :)
When you want to ensure improved accuracy as well as model safety, do you train a linear probe or fine-tune pre-trained models end-to-end? Check out our poster at the PODS@ICML workshop to learn about the best approach! @puja_computes @danaikoutra
3/9
Excited to present our work on repurposing pre-trained StyleGANs to solve inverse problems for Out-Of-Distribution images at #ICML2022, #GANinversion. Check our paper SPHInX proceedings.mlr.press/v162/s…
This work is in collaboration with @VivekSivaraman1 and @jjayaram7
