Angular Visual Hardness

12/04/2019
by   Beidi Chen, et al.
66

Although convolutional neural networks (CNNs) are inspired by the mechanisms behind human visual systems, they diverge on many measures such as ambiguity or hardness. In this paper, we make a surprising discovery: there exists a (nearly) universal score function for CNNs whose correlation is statistically significant than the widely used model confidence with human visual hardness. We term this function as angular visual hardness (AVH) which is given by the normalized angular distance between a feature embedding and the classifier weights of the corresponding target category in a CNN. We conduct an in-depth scientific study. We observe that CNN models with the highest accuracy also have the best AVH scores. This agrees with an earlier finding that state-of-art models tend to improve on the classification of harder training examples. We find that AVH displays interesting dynamics during training: it quickly reaches a plateau even though the training loss keeps improving. This suggests the need for designing better loss functions that can target harder examples more effectively. Finally, we empirically show significant improvement in performance by using AVH as a measure of hardness in self-training methods for domain adaptation.

READ FULL TEXT

page 9

page 11

page 12

page 13

page 15

page 18

page 22

page 24

research
02/09/2016

The Role of Typicality in Object Classification: Improving The Generalization Capacity of Convolutional Neural Networks

Deep artificial neural networks have made remarkable progress in differe...
research
06/10/2019

Automatic Segmentation of Vestibular Schwannoma from T2-Weighted MRI by Deep Spatial Attention with Hardness-Weighted Loss

Automatic segmentation of vestibular schwannoma (VS) tumors from magneti...
research
11/11/2022

Hardness-guided domain adaptation to recognise biomedical named entities under low-resource scenarios

Domain adaptation is an effective solution to data scarcity in low-resou...
research
12/29/2018

Support Vector Guided Softmax Loss for Face Recognition

Face recognition has witnessed significant progresses due to the advance...
research
07/24/2018

Self-Paced Learning with Adaptive Deep Visual Embeddings

Selecting the most appropriate data examples to present a deep neural ne...
research
11/08/2017

Deep Hyperspherical Learning

Convolution as inner product has been the founding basis of convolutiona...
research
06/15/2021

Canonical Face Embeddings

We present evidence that many common convolutional neural networks (CNNs...

Please sign up or login with your details

Forgot password? Click here to reset