Get our free extension to see links to code for papers anywhere online!

Chrome logo  Add to Chrome

Firefox logo Add to Firefox
Picture for Gowthami Somepalli

Gowthami Somepalli
Alert button

Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Models


Dec 12, 2022
Gowthami Somepalli, Vasu Singla, Micah Goldblum, Jonas Geiping, Tom Goldstein

Add code
Alert button

Figure 1 for Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Models
Figure 2 for Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Models
Figure 3 for Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Models
Figure 4 for Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Models
* Updated draft with the following changes (1) Clarified the LAION Aesthetics versions everywhere (2) Correction on which LAION Aesthetics version SD - 1.4 is finetuned on and updated figure 12 based on this (3) A section on possible causes of replication 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

How Much Data Are Augmentations Worth? An Investigation into Scaling Laws, Invariance, and Implicit Regularization


Oct 12, 2022
Jonas Geiping, Micah Goldblum, Gowthami Somepalli, Ravid Shwartz-Ziv, Tom Goldstein, Andrew Gordon Wilson

Add code
Alert button

Figure 1 for How Much Data Are Augmentations Worth? An Investigation into Scaling Laws, Invariance, and Implicit Regularization
Figure 2 for How Much Data Are Augmentations Worth? An Investigation into Scaling Laws, Invariance, and Implicit Regularization
Figure 3 for How Much Data Are Augmentations Worth? An Investigation into Scaling Laws, Invariance, and Implicit Regularization
Figure 4 for How Much Data Are Augmentations Worth? An Investigation into Scaling Laws, Invariance, and Implicit Regularization
* 27 pages, 20 figures. Code at https://github.com/JonasGeiping/dataaugs 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Can Neural Nets Learn the Same Model Twice? Investigating Reproducibility and Double Descent from the Decision Boundary Perspective


Mar 15, 2022
Gowthami Somepalli, Liam Fowl, Arpit Bansal, Ping Yeh-Chiang, Yehuda Dar, Richard Baraniuk, Micah Goldblum, Tom Goldstein

Add code
Alert button

Figure 1 for Can Neural Nets Learn the Same Model Twice? Investigating Reproducibility and Double Descent from the Decision Boundary Perspective
Figure 2 for Can Neural Nets Learn the Same Model Twice? Investigating Reproducibility and Double Descent from the Decision Boundary Perspective
Figure 3 for Can Neural Nets Learn the Same Model Twice? Investigating Reproducibility and Double Descent from the Decision Boundary Perspective
Figure 4 for Can Neural Nets Learn the Same Model Twice? Investigating Reproducibility and Double Descent from the Decision Boundary Perspective
* To appear in CVPR 2022 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

PatchGame: Learning to Signal Mid-level Patches in Referential Games


Nov 02, 2021
Kamal Gupta, Gowthami Somepalli, Anubhav Gupta, Vinoj Jayasundara, Matthias Zwicker, Abhinav Shrivastava

Add code
Alert button

Figure 1 for PatchGame: Learning to Signal Mid-level Patches in Referential Games
Figure 2 for PatchGame: Learning to Signal Mid-level Patches in Referential Games
Figure 3 for PatchGame: Learning to Signal Mid-level Patches in Referential Games
Figure 4 for PatchGame: Learning to Signal Mid-level Patches in Referential Games
* To appear at NeurIPS 2021 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

SAINT: Improved Neural Networks for Tabular Data via Row Attention and Contrastive Pre-Training


Jun 02, 2021
Gowthami Somepalli, Micah Goldblum, Avi Schwarzschild, C. Bayan Bruss, Tom Goldstein

Add code
Alert button

Figure 1 for SAINT: Improved Neural Networks for Tabular Data via Row Attention and Contrastive Pre-Training
Figure 2 for SAINT: Improved Neural Networks for Tabular Data via Row Attention and Contrastive Pre-Training
Figure 3 for SAINT: Improved Neural Networks for Tabular Data via Row Attention and Contrastive Pre-Training
Figure 4 for SAINT: Improved Neural Networks for Tabular Data via Row Attention and Contrastive Pre-Training

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

What Doesn't Kill You Makes You Robust(er): Adversarial Training against Poisons and Backdoors


Feb 26, 2021
Jonas Geiping, Liam Fowl, Gowthami Somepalli, Micah Goldblum, Michael Moeller, Tom Goldstein

Add code
Alert button

* 17 pages, 14 figures 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email