Pretraining boosts out-of-domain robustness for pose estimation
Graph Chatbot
Chat with Graph Search
Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.
DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.
The dense interconnections that characterize neural networks are most readily implemented using optical signal processing. Optoelectronic 'neurons' fabricated from semiconducting materials can be connected by holographic images recorded in photorefractive ...
We pursue a time-domain feedback analysis of adaptive schemes with nonlinear update relations. We consider commonly used algorithms in blind equalization and neural network training and study their performance in a purely deterministic framework. The deriv ...
The applicability of neural networks to a typical biochemical engineering problem was investigated. The data treatment required for a novel technique for measuring the mean bubble size and the specific interfacial area in aerobic bioreactors was chosen as ...
Neural networks are highly effective tools for pose estimation. However, robustness to outof-domain data remains a challenge, especially for small training sets that are common for real world applications. Here, we probe the generalization ability with thr ...
We describe an evolutionary vision system capable of autonomously scanning through an image while zooming in and out and changing filtering strategy in order to perform shape discrimination. The system consists of a small artificial retina controlled by an ...
The default multilayer neural network topology is a fully interlayer connected one. This simplistic choice facilitates the design but it limits the performance of the resulting neural networks. The best-known methods for obtaining partially connected neura ...
The applicability of neural networks to a typical biochem. engineering problem was investigated. The data treatment required for a novel technique for measuring the mean bubble size and the sp. interfacial area in aerobic bioreactors was chosen as an appro ...
We propose a recurrent neural-network for real-time reconstruction of acoustic camera spherical maps. The network, dubbed DeepWave, is both physically and algorithmically motivated: its recurrent architecture mimics iterative solvers from convex optimisati ...
