Recursos de colección

Caltech Authors (143.226 recursos)

Repository of works by Caltech published authors.

Group = Computation & Neural Systems Technical Reports

Mostrando recursos 1 - 6 de 6

  1. Analog VLSI Phototransduction by continuous-time, adaptive, logarithmic photoreceptor circuits

    Delbrück, T.; Mead, C. A.
    Over the last few years, we and others have built a number of interesting neuromorphic analog vision chips that do focal-plane time-domain computation. These chips do local, continuous-time, spatiotemporal processing that takes place before any sampling or long-range communication, for example, motion processing, change detection, neuromorphic retinal preprocessing, stereo image matching, and synthesis of auditory images from visual scenes. This processing requires photoreceptor circuits that transduce from light falling on the chip to an electrical signal. If we want to build analog vision chips that do high-quality focal plane processing, then we need good photoreceptors. It's not enough to just demonstrate a concept; ultimate usefulness will be determined...

  2. Refractory Neuron Circuits

    Sarpeshkar, Rahul; Watts, Lloyd; Mead, Carver
    Neural networks typically use an abstraction of the behaviour of a biological neuron, in which the continuously varying mean firing rate of the neuron is presumed to carry information about the neuron's time-varying state of excitation. However, the detailed timing of action potentials is known to be important in many biological systems. To build electronic models of such systems, one must have well-characterized neuron circuits that capture the essential behaviour of real neurons in biological systems. In this paper, we describe two simple and compact circuits that fire narrow action potentials with controllable thresholds, pulse widths, and refractory periods. Both circuits are well suited as high-level abstractions...

  3. Crowdclustering

    Gomes, Ryan; Welinder, Peter; Krause, Andreas; Perona, Pietro
    Is it possible to crowdsource categorization? Amongst the challenges: (a) each worker has only a partial view of the data, (b) different workers may have different clustering criteria and may produce different numbers of categories, (c) the underlying category structure may be hierarchical. We propose a Bayesian model of how workers may approach clustering and show how one may infer clusters / categories, as well as worker parameters, using this model. Our experiments, carried out on large collections of images, suggest that Bayesian crowdclustering works well and may be superior to single-expert annotations.

  4. The Caltech-UCSD Birds-200-2011 Dataset

    Wah, Catherine; Branson, Steve; Welinder, Peter; Perona, Pietro; Belongie, Serge
    CUB-200-2011 is an extended version of CUB-200 [7], a challenging dataset of 200 bird species. The extended version roughly doubles the number of images per category and adds new part localization annotations. All images are annotated with bounding boxes, part locations, and at- tribute labels. Images and annotations were filtered by mul- tiple users of Mechanical Turk. We introduce benchmarks and baseline experiments for multi-class categorization and part localization.

  5. Caltech-UCSD Birds 200

    Welinder, Peter; Branson, Steve; Mita, Takeshi; Wah, Catherine; Schroff, Florian; Belongie, Serge; Perona, Pietro
    Caltech-UCSD Birds 200 (CUB-200) is a challenging image dataset annotated with 200 bird species. It was created to enable the study of subordinate categorization, which is not possible with other popular datasets that focus on basic level categories (such as PASCAL VOC, Caltech-101, etc). The images were downloaded from the website Flickr and filtered by workers on Amazon Mechanical Turk. Each image is annotated with a bounding box, a rough bird segmentation, and a set of attribute labels.

  6. Crowdclustering

    Gomes, Ryan; Welinder, Peter; Krause, Andreas; Perona, Pietro
    Is it possible to crowdsource categorization? Amongst the challenges: (a) each worker has only a partial view of the data, (b) different workers may have different clustering criteria and may produce different numbers of categories, (c) the underlying category structure may be hierarchical. We propose a Bayesian model of how workers may approach clustering and show how one may infer clusters / categories, as well as worker parameters, using this model. Our experiments, carried out on large collections of images, suggest that Bayesian crowdclustering works well and may be superior to single-expert annotations.

Aviso de cookies: Usamos cookies propias y de terceros para mejorar nuestros servicios, para análisis estadístico y para mostrarle publicidad. Si continua navegando consideramos que acepta su uso en los términos establecidos en la Política de cookies.