Corpus ID: 231924770

Naturalizing Neuromorphic Vision Event Streams Using GANs

  title={Naturalizing Neuromorphic Vision Event Streams Using GANs},
  author={Dennis E. Robey and Wesley Joo-Chen Thio and Herbert H. C. Iu and Jason Kamran Eshraghian},
Dynamic vision sensors are able to operate at high temporal resolutions within resource constrained environments, though at the expense of capturing static content. The sparse nature of event streams enables efficient downstream processing tasks as they are suited for power-efficient spiking neural networks. One of the challenges associated with neuromorphic vision is the lack of interpretability of event streams. While most application use-cases do not intend for the event stream to be… Expand

Figures from this paper

Learning to Time-Decode in Spiking Neural Networks Through the Information Bottleneck
A novel end-to-end learning rule is introduced that optimizes a directed information bottleneck training criterion via surrogate gradients and demonstrates the applicability of the technique in an experimental settings on various tasks, including real-life datasets. Expand


Converting Static Image Datasets to Spiking Neuromorphic Datasets Using Saccades
This work proposes a method for converting existing Computer Vision static image datasets into Neuromorphic Vision datasets using an actuated pan-tilt camera platform, and presents conversion of two popular image datasets which have played important roles in the development of Computer Vision. Expand
Nonlinear retinal response modeling for future neuromorphic instrumentation
A biologically plausible cellular network retina simulator, where light stimuli are accepted at the front-end array of photoreceptor cells, and pass through a system of nonlinear integral equations derived from experimental voltage- and current-clamp data used to calculate the response of each sequential retina cell. Expand
CIFAR10-DVS: An Event-Stream Dataset for Object Classification
This work provides a large event-stream dataset and an initial benchmark for comparison, which may boost algorithm developments in even-driven pattern recognition and object classification, based on state-of-the-art classification algorithms. Expand
Going Deeper in Spiking Neural Networks: VGG and Residual Architectures
A novel algorithmic technique is proposed for generating an SNN with a deep architecture with significantly better accuracy than the state-of-the-art, and its effectiveness on complex visual recognition problems such as CIFAR-10 and ImageNet is demonstrated. Expand
Neuromorphic Vision Hybrid RRAM-CMOS Architecture
The signal flow path of photocurrent throughout a retina in a scalable 180-nm CMOS technology is synthesized and the resulting image matches biologically verified results within an error margin of 6% and exhibits the following features of the retina: lateral inhibition, asynchronous adaptation, and a low-dynamic-range integration active pixel sensor to perceive a high-d dynamic-range scene. Expand
A Dynamic Vision Sensor With 1% Temporal Contrast Sensitivity and In-Pixel Asynchronous Delta Modulator for Event Encoding
Improvements to a dynamic vision sensor with improved TC sensitivity and event encoding can facilitate the application of DVSs in areas like optical neuroimaging which is demonstrated in a simulated experiment. Expand
A 240 × 180 130 dB 3 µs Latency Global Shutter Spatiotemporal Vision Sensor
This paper presents a dynamic and active pixel vision sensor (DAVIS) which addresses this deficiency by outputting asynchronous DVS events and synchronous global shutter frames concurrently. Expand
Very Deep Convolutional Networks for Large-Scale Image Recognition
This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers. Expand
A Real-Time Retinomorphic Simulator Using a Conductance-Based Discrete Neuronal Network
An optimized conductance-based retina microcircuit simulator which transforms light stimuli into a series of graded and spiking action potentials through photo transduction, and successfully achieves a biologically real-time simulator. Expand
Formulation and Implementation of Nonlinear Integral Equations to Model Neural Dynamics Within the Vertebrate Retina
This research presents a novel approach that requires the effective integration of different dynamical time scales within a unified framework of neural responses, where the rod, cone, amacrine, bipolar, and ganglion cells correspond to the implemented pathways. Expand