02/02/2021

Anytime Inference with Distilled Hierarchical Neural Ensembles

Adria Ruiz, Jakob Verbeek

Keywords:

Abstract Paper Similar Papers

Abstract: Inference in deep neural networks can be computationally expensive, and networks capable of anytime inference are important in scenarios where the amount of compute or input data varies over time. In such networks the inference process can interrupted to provide a result faster, or continued to obtain a more accurate result. We propose Hierarchical Neural Ensembles (HNE), a novel framework to embed an ensemble of multiple networks in a hierarchical tree structure, sharing intermediate layers. In HNE we control the complexity of inference on-the-fly by evaluating more or less models in the ensemble. Our second contribution is a novel hierarchical distillation method to boost the predictions of small ensembles. This approach leverages the nested structure of our ensembles, to optimally allocate accuracy and diversity across the individual models. Our experiments show that, compared to previous anytime inference models, HNE provides state-of-the-art accuracy-computation trade-offs on the CIFAR-10/100 and ImageNet datasets.

The video of this talk cannot be embedded. You can watch it here:
https://slideslive.com/38949210
(Link will open in new window)
 0
 0
 0
 0
  Share    
This is an embedded video. Talk and the respective paper are published at AAAI 2021 virtual conference. If you are one of the authors of the paper and want to manage your upload, see the question "My papertalk has been externally embedded..." in the FAQ section.

Comments

Post Comment
no comments yet
code of conduct: tbd Characters remaining: 140

Similar Papers

 0
 0
 0
 0
 15:02 
 0
 0
 0
 0
 3:20 
 0
 0
 0
 1
 5:39 
 0
 0
 0
 0
 3:17 
 0
 0
 0
 0
 3:23 
 0
 0
 0
 0
 5:02 
 0
 0
 0
 0
 5:25 
 0
 0
 0
 0
 5:05 
 0
 0
 0
 0
 3:02 
 0
 0
 0
 0
 15:02 
 0
 0
 0
 0
 6:40 
 0
 0
 0
 0
 8:31 
 0
 0
 0
 0
 4:52 
 0
 0
 0
 0
 3:25 
 0
 0
 0
 0
 3:19 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 12:58 
 0
 0
 0
 0
 13:52 
 0
 0
 0
 0
 4:53 
 0
 0
 0
 0
 5:07 
 1
 0
 0
 1
 3:10 
 0
 0
 0
 0
 2:46 
 0
 0
 0
 0
 3:21 
 0
 0
 0
 0
 3:05 
 0
 0
 0
 0
 8:07 
 0
 0
 0
 0
 4:52 
 0
 0
 0
 0
 5:05 
 0
 0
 0
 0
 4:25 
 0
 0
 0
 1
 5:06 
 0
 0
 0
 0
 3:13 
 0
 0
 0
 0
 4:07 
 0
 0
 0
 0
 14:02 
 0
 0
 0
 0
 13:42 
 0
 0
 0
 0
 18:14 
 0
 0
 0
 0
 6:05 
 0
 0
 0
 0
 15:01 
 0
 0
 0
 0
 9:50 
 0
 0
 0
 0
 9:47 
 0
 0
 0
 0
 19:14 
 0
 0
 0
 0
 14:59