Transcription of Learning Deep Features for Discriminative Localization
{{id}} {{{paragraph}}}
Example: stock market
Learning Deep Features for Discriminative Localization
Learning Deep Features for Discriminative LocalizationBolei Zhou, Aditya Khosla, Agata Lapedriza, Aude Oliva, Antonio TorralbaComputer Science and Artificial Intelligence Laboratory, this work, we revisit the global average pooling layerproposed in [13], and shed light on how it explicitly enablesthe convolutional neural network to have remarkable local-ization ability despite being trained on image-level this technique was previously proposed as a meansfor regularizing training, we find that it actually builds ageneric localizable deep representation that can be appliedto a variety of tasks. Despite the apparent simplicity ofglobal average pooling, we are able to achieve top-5error for object Localization on ILSVRC 2014, which is re-markably close to the top-5 error achieved by a fullysupervised CNN approach. We demonstrate that our net-work is able to localize the Discriminative image regions ona variety of tasks despite not being trained for IntroductionRecent work by Zhouet al[33] has shown that the con-volutional units of various layers of convolutional neuralnetworks (CNNs) actually behave as object detectors de-spite no supervision on the location of the object was pro-vided.
the visual encoding of CNNs by inverting deep features at different layers. While these approaches can invert the fully-connected layers, they only show what information is being preserved in the deep features without highlight-ing the relative importance of this information. Unlike [14] and [4], our approach can highlight exactly which regions
Loading..
Tags:
Information
Domain:
Source:
Link to this page:
Please notify us if you found a problem with this document: