Gowthami SomepalliDiffusion mini-summaries #2: An Image is Worth One Word: Personalizing Text-to-Image Generation…Textual Inversion: Learn the word for a given subject by optimizing the language encoder which enables us to generate new images of the…Jan 10, 2023Jan 10, 2023
Gowthami SomepalliDiffusion model mini-summaries #1 — DreamBooth: Fine Tuning Text-to-Image Diffusion Models for…DreamBooth: Assign a rare sequence of tokens as the subject’s identifier and fine-tune the diffusion model on the small set of images with…Jan 10, 2023Jan 10, 2023
Gowthami SomepalliUniversal Adversarial Training — Paper SummaryPaper: Universal Adversarial Training Link: https://ojs.aaai.org/index.php/AAAI/article/view/6017/5873 Authors: Ali Shafahi, Mahyar Najibi…Mar 7, 2022Mar 7, 2022
Gowthami SomepalliWhen Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations —…Paper: When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations Link…Feb 21, 20221Feb 21, 20221
Gowthami SomepalliDeep Learning Through the Lens of Example Difficulty — Paper SummaryLink: https://openreview.net/forum?id=fmgYOUahK9 Authors: Robert John Nicholas Baldock, Hartmut Maennel, Behnam Neyshabur Tags: Deep…Feb 13, 2022Feb 13, 2022
Gowthami SomepalliWhy Do Better Loss Functions Lead to Less Transferable Features? — Paper SummaryPaper: Why Do Better Loss Functions Lead to Less Transferable Features? Link: https://openreview.net/forum?id=8twKpG5s8Qh Authors: Simon…Feb 7, 20222Feb 7, 20222
Gowthami SomepalliSLIP: Self-supervision meets Language-Image Pre-training — Paper SummaryPaper: SLIP: Self-supervision meets Language-Image Pre-training Link: https://arxiv.org/abs/2112.12750 Authors: Norman Mu, Alexander…Jan 3, 2022Jan 3, 2022
Gowthami SomepalliSuggest papers or topics to cover!Hi there, If you have a specific topic or paper in mind, please suggest in the following Typeform.Dec 19, 2021Dec 19, 2021
Gowthami SomepalliMLP-Mixer: An all-MLP Architecture for Vision — Paper SummaryPaper: MLP-Mixer: An all-MLP Architecture for Vision Link: https://arxiv.org/abs/2105.01601 Authors: Ilya Tolstikhin, Neil Houlsby…Aug 31, 2021Aug 31, 2021