MULTIMODAL AI

→ View original post on X — @animaanandkumar

Robust Vision Transformer Architecture Wins Semantic Segmentation Challenge

By

@animaanandkumar

–

31 December 2022 22h51

We also developed robust vision transformer architecture, fully attention networks (FAN), with channel-based attention for robustness. We won the Semantic Segmentation Tracking of Robust Vision Challenge at ECCV. https://
arxiv.org/abs/2210.12852

→ View original post on X — @thegautamkamath

Vision Transformer Citations: Identifying False Positives in Scholar Data

By

@thegautamkamath

–

31 December 2022 15h34

I feel like this might be picking up some false positives. Scholar also says that the vision transformer paper (
https://
arxiv.org/abs/2010.11929) only has about 10k citations total. There must be some way to see how many are from 2022…

OpenAI Whisper Speech Recognition Model Added to Hugging Face

By

–

31 December 2022 13h22

In October, Whisper, a state-of-the-art audio model from @OpenAI for speech recognition was added to the library. https://
huggingface.co/docs/transform
ers/model_doc/whisper
…

LayoutLM v3 Multimodal Model Added for Document Analysis

By

–

31 December 2022 13h22

LayoutLM v3 (also from @MSFTResearch
) was added to the library in June. It is a multimodal model combining vision and text for document analysis.

Doubling AI Model Architectures: New Audio, Vision and Multimodal Models

By

–

31 December 2022 13h22

We doubled the number of architectures (89 to 167) with new models in audio, text, vision, multiple modalities or even time seriesand protein folding Here are a few highlights in the most used of those new models

Swin Transformer Vision Model for Image Classification Detection

By

–

31 December 2022 13h22

Swin Transformer is a vision model from @MSFTResearch added back in January, which can be used as backbone for a variety of tasks such as image classification, object detection or semantic segmentation. https://
huggingface.co/docs/transform
ers/model_doc/swin
…