Filters








7 Hits in 7.4 sec

Reconstruct, Rasterize and Backprop: Dense shape and pose estimation from a single image [article]

Aniket Pokale, Aditya Aggarwal, K. Madhava Krishna
2020 arXiv   pre-print
This paper presents a new system to obtain dense object reconstructions along with 6-DoF poses from a single image.  ...  We demonstrate that our approach---dubbed reconstruct, rasterize and backprop (RRB) achieves significantly lower pose estimation errors compared to prior art, and is able to recover dense object shapes  ...  Acknowledgment The authors acknowledge the support and funding from Kohli Center for Intelligent Systems (KCIS), IIIT Hyderabad for this work.  ... 
arXiv:2004.12232v1 fatcat:7p2ln75xfzcxbapf2ztksua6ge

Distilling Model Knowledge [article]

George Papamakarios
2015 arXiv   pre-print
We present a general framework for knowledge distillation, whereby a convenient model of our choosing learns how to mimic a complex model, by observing the latter's behaviour and being penalized whenever  ...  In this thesis, we study knowledge distillation, the idea of extracting the knowledge contained in a complex model and injecting it into a more convenient model.  ...  learning (and beyond!).  ... 
arXiv:1510.02437v1 fatcat:c32papt6hngcre4wkl3nygac7a

Physics-based Deep Learning [article]

Nils Thuerey and Philipp Holl and Maximilian Mueller and Patrick Schnell and Felix Trost and Kiwon Um
2022 arXiv   pre-print
This digital book contains a practical and comprehensive introduction of everything related to deep learning in the context of physical simulations.  ...  Beyond standard supervised learning from data, we'll look at physical loss constraints, more tightly coupled learning algorithms with differentiable simulations, as well as reinforcement learning and uncertainty  ...  As inputs we have the Reynolds number Re ∈ R, the angle of attack 𝛼 ∈ R, and the airfoil shape s encoded as a rasterized grid with 128 2 .  ... 
arXiv:2109.05237v3 fatcat:pz7ot63dlbdkriihkwloefk3im

2022 Roadmap on Neuromorphic Computing and Engineering [article]

Dennis V. Christensen, Regina Dittmann, Bernabé Linares-Barranco, Abu Sebastian, Manuel Le Gallo, Andrea Redaelli, Stefan Slesazeck, Thomas Mikolajick, Sabina Spiga, Stephan Menzel, Ilia Valov, Gianluca Milano (+47 others)
2022 arXiv   pre-print
Among their potential future applications, an important niche is moving the control from data centers to edge devices.  ...  The aim of this Roadmap is to present a snapshot of the present state of neuromorphic technology and provide an opinion on the challenges and opportunities that the future holds in the major areas of neuromorphic  ...  Acknowledgements Roadmap on Neuromorphic Computing and Engineering This work was partially based on results obtained from a project, JPNP16007, commissioned by the New Energy and Industrial Technology  ... 
arXiv:2105.05956v3 fatcat:pqir5infojfpvdzdwgmwdhsdi4

Putting more neural in artificial neural networks [article]

Callie Federer
2021
State-of-the-art algorithms in object recognition still suffer from interpreting images in a way that is not human-like, leading to unexpected and potentially catastrophic errors.  ...  In this thesis, we work towards understanding how can we use AI algorithms as a model of the brain, and how can the brain influence how we design AI algorithms?  ...  ACKNOWLEDGEMENTS This dissertation would not be possible without a significant amount of support from colleagues, friends and family.  ... 
doi:10.25677/byv1-e934 fatcat:4yhtnbzg2vaslh6vkiy2uepszu

Event-Based Vision Processing in Deep Neural Networks

Bodo Rückauer
2020
The algorithm is shown to produce equivalent accuracy results at reduced computational cost on a range of vision tasks including human pose estimation and object detection in static and dynamic scenes.  ...  The algorithm is shown to produce equivalent accuracy results at reduced computational cost on a range of vision tasks including human pose estimation and object detection in static and dynamic scenes.  ...  . † On a subset of 2570 samples, using single-scale images of size 224x224. † † On a subset of 1382 samples, using single-scale images of size 299x299. ‡ On a subset of 3072 samples.  ... 
doi:10.5167/uzh-200987 fatcat:y2clxptcabh2bklipriywhtx4i

2022 roadmap on neuromorphic computing and engineering

Dennis Valbjørn Christensen, Regina Dittmann, Bernabé Linares-Barranco, Abu Sebastian, Manuel Le Gallo, Andrea Redaelli, Stefan Slesazeck, Thomas Mikolajick, Sabina Spiga, Stephan Menzel, Ilia Valov, Gianluca Milano (+12 others)
2022
Among their potential future applications, an important niche is moving the control from data centers to edge devices.  ...  The aim of this roadmap is to present a snapshot of the present state of neuromorphic technology and provide an opinion on the challenges and opportunities that the future holds in the major areas of neuromorphic  ...  Acknowledgements This research/project was supported by the Human Brain Project (Grant Agreement Number 785907) of the European Union and a Grant from Intel.  ... 
doi:10.3929/ethz-b-000529282 fatcat:x5s5lalqqbbn7fb6gmpqmbqkxu