273 citations · 1.5k across the 75 of their papers we have counts for
5 papers · 1 filter
Multiple View Performers for Shape Completion
David Watkins, Peter Allen, Krzysztof Choromanski +2
We propose the Multiple View Performer (MVP) - a new architecture for 3D shape completion from a series of temporally sequential views. MVP accomplishes this task by using linear-a…
Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language
Andy Zeng, Maria Attarian, Brian Ichter +10
Large pretrained (e.g., "foundation") models exhibit distinct capabilities depending on the domain of data they are trained on. While these domains are generic, they may only barel…
PolyViT: Co-training Vision Transformers on Images, Videos and Audio
Valerii Likhosherstov, Anurag Arnab, Krzysztof Choromanski +4
Can we train a single transformer model capable of processing multiple modalities and datasets, whilst sharing almost all of its learnable parameters? We present PolyViT, a model t…
Explaining How a Deep Neural Network Trained with End-to-End Learning Steers a Car
Mariusz Bojarski, Philip Yeres, Anna Choromanska +4
As part of a complete software stack for autonomous driving, NVIDIA has created a neural-network-based system, known as PilotNet, which outputs steering angles given images of the…
VisualBackProp: efficient visualization of CNNs
Mariusz Bojarski, Anna Choromanska, Krzysztof Choromanski +4
This paper proposes a new method, that we call VisualBackProp, for visualizing which sets of pixels of the input image contribute most to the predictions made by the convolutional…