Julia Grabinski
@juliagrabinski.bsky.social
Postdoc at Visual Inference Lab, TU Darmstadt
Update: thanks @iclr-conf.bsky.social for finding this creative and well working solution ☺️
April 24, 2025 at 2:48 AM
Update: thanks @iclr-conf.bsky.social for finding this creative and well working solution ☺️
🗓️ Thu, Apr 24, 10:00–12:30
📍 Hall 3 + 2B, Poster #74
🧠 Paper: openreview.net/pdf?id=xRy1Y...
💻 Code: github.com/GeJulia/NIFF
Are you around? Come say hi! 😊
📍 Hall 3 + 2B, Poster #74
🧠 Paper: openreview.net/pdf?id=xRy1Y...
💻 Code: github.com/GeJulia/NIFF
Are you around? Come say hi! 😊
GitHub - GeJulia/NIFF
Contribute to GeJulia/NIFF development by creating an account on GitHub.
github.com
April 21, 2025 at 6:45 AM
🗓️ Thu, Apr 24, 10:00–12:30
📍 Hall 3 + 2B, Poster #74
🧠 Paper: openreview.net/pdf?id=xRy1Y...
💻 Code: github.com/GeJulia/NIFF
Are you around? Come say hi! 😊
📍 Hall 3 + 2B, Poster #74
🧠 Paper: openreview.net/pdf?id=xRy1Y...
💻 Code: github.com/GeJulia/NIFF
Are you around? Come say hi! 😊
Really cool video! Maybe our work on aliasing artifacts and robustness link.springer.com/article/10.1... within vision models and how to fix them to link.springer.com/chapter/10.1... might be interesting for you 😊
FrequencyLowCut Pooling - Plug and Play Against Catastrophic Overfitting
Over the last years, Convolutional Neural Networks (CNNs) have been the dominating neural architecture in a wide range of computer vision tasks. From an image and signal processing point of view, this...
link.springer.com
March 1, 2025 at 8:06 AM
Really cool video! Maybe our work on aliasing artifacts and robustness link.springer.com/article/10.1... within vision models and how to fix them to link.springer.com/chapter/10.1... might be interesting for you 😊
Reposted by Julia Grabinski
3. our TMLR Featured Certification "As large as it gets – Studying Infinitely Large Convolutions via Neural Implicit Frequency Filters" - openreview.net/forum?id=xRy... joint work with @juliagrabinski.bsky.social @janiskeuper.bsky.social and @margretkeuper.bsky.social
January 25, 2025 at 3:25 PM
3. our TMLR Featured Certification "As large as it gets – Studying Infinitely Large Convolutions via Neural Implicit Frequency Filters" - openreview.net/forum?id=xRy... joint work with @juliagrabinski.bsky.social @janiskeuper.bsky.social and @margretkeuper.bsky.social