recentpopularlog in


« earlier   
Approximating CNNs with Bag-of-local-Features models works surprisingly well on ImageNet | OpenReview
"Deep Neural Networks (DNNs) excel on many complex perceptual tasks but it has proven notoriously difficult to understand how they reach their decisions. We here introduce a high-performance DNN architecture on ImageNet whose decisions are considerably easier to explain. Our model, a simple variant of the ResNet-50 architecture called BagNet, classifies an image based on the occurrences of small local image features without taking into account their spatial ordering. This strategy is closely related to the bag-of-feature (BoF) models popular before the onset of deep learning and reaches a surprisingly high accuracy on ImageNet (87.6% top-5 for 32 x 32 px features and Alexnet performance for 16 x16 px features). The constraint on local features makes it straight-forward to analyse how exactly each part of the image influences the classification. Furthermore, the BagNets behave similar to state-of-the art deep neural networks such as VGG-16, ResNet-152 or DenseNet-169 in terms of feature sensitivity, error distribution and interactions between image parts. This suggests that the improvements of DNNs over previous bag-of-feature classifiers in the last few years is mostly achieved by better fine-tuning rather than by qualitatively different decision strategies."
deep-learning  convnet  computer-vision  bagnet  imagenet 
15 days ago by arsyed
The top three state of the art network architectures for are produced by , now i…
deeplearning  AI  AutoML  ImageNet  from twitter_favs
november 2018 by aratob
Prepare the ImageNet dataset — gluoncv 0.3.0 documentation
includes instructions for other datasets, too, namely COCO, ADE20K, PASCAL VOC
imagenet  advice 
september 2018 by wpenman

Copy this bookmark:

to read