Training Interpretable Convolutional Neural Networks by Differentiating Class-specific Filters

• URL: http://arxiv.org/abs/2007.08194v3
• Date: Thu, 1 Jul 2021 10:40:06 GMT
• Title: Training Interpretable Convolutional Neural Networks by Differentiating Class-specific Filters
• Authors: Haoyu Liang, Zhihao Ouyang, Yuyuan Zeng, Hang Su, Zihao He, Shu-Tao Xia, Jun Zhu, Bo Zhang
• Abstract summary: Convolutional neural networks (CNNs) have been successfully used in a range of tasks. CNNs are often viewed as "black-box" and lack of interpretability. We propose a novel strategy to train interpretable CNNs by encouraging class-specific filters.
• Score: 64.46270549587004
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Convolutional neural networks (CNNs) have been successfully used in a range of tasks. However, CNNs are often viewed as "black-box" and lack of interpretability. One main reason is due to the filter-class entanglement -- an intricate many-to-many correspondence between filters and classes. Most existing works attempt post-hoc interpretation on a pre-trained model, while neglecting to reduce the entanglement underlying the model. In contrast, we focus on alleviating filter-class entanglement during training. Inspired by cellular differentiation, we propose a novel strategy to train interpretable CNNs by encouraging class-specific filters, among which each filter responds to only one (or few) class. Concretely, we design a learnable sparse Class-Specific Gate (CSG) structure to assign each filter with one (or few) class in a flexible way. The gate allows a filter's activation to pass only when the input samples come from the specific class. Extensive experiments demonstrate the fabulous performance of our method in generating a sparse and highly class-related representation of the input, which leads to stronger interpretability. Moreover, comparing with the standard training strategy, our model displays benefits in applications like object localization and adversarial sample detection. Code link: https://github.com/hyliang96/CSGCNN.

Related papers

• PICNN: A Pathway towards Interpretable Convolutional Neural Networks [12.31424771480963]
  We introduce a novel pathway to alleviate the entanglement between filters and image classes. We use the Bernoulli sampling to generate the filter-cluster assignment matrix from a learnable filter-class correspondence matrix. We evaluate the effectiveness of our method on ten widely used network architectures.
  arXiv  Detail & Related papers  (2023-12-19T11:36:03Z)
• The Power of Linear Combinations: Learning with Random Convolutions [2.0305676256390934]
  Modern CNNs can achieve high test accuracies without ever updating randomly (spatial) convolution filters. These combinations of random filters can implicitly regularize the resulting operations. Although we only observe relatively small gains from learning $3times 3$ convolutions, the learning gains increase proportionally with kernel size.
  arXiv  Detail & Related papers  (2023-01-26T19:17:10Z)
• Gabor is Enough: Interpretable Deep Denoising with a Gabor Synthesis Dictionary Prior [6.297103076360578]
  Gabor-like filters have been observed in the early layers of CNN classifiers and throughout low-level image processing networks. In this work, we take this observation to the extreme and explicitly constrain the filters of a natural-image denoising CNN to be learned 2D real Gabor filters. We find that the proposed network (GDLNet) can achieve near state-of-the-art denoising performance amongst popular fully convolutional neural networks.
  arXiv  Detail & Related papers  (2022-04-23T22:21:54Z)
• CNN Filter DB: An Empirical Investigation of Trained Convolutional Filters [2.0305676256390934]
  We show that model pre-training can succeed on arbitrary datasets if they meet size and variance conditions. We show that many pre-trained models contain degenerated filters which make them less robust and less suitable for fine-tuning on target applications.
  arXiv  Detail & Related papers  (2022-03-29T08:25:42Z)
• Learning Versatile Convolution Filters for Efficient Visual Recognition [125.34595948003745]
  This paper introduces versatile filters to construct efficient convolutional neural networks. We conduct theoretical analysis on network complexity and an efficient convolution scheme is introduced. Experimental results on benchmark datasets and neural networks demonstrate that our versatile filters are able to achieve comparable accuracy as that of original filters.
  arXiv  Detail & Related papers  (2021-09-20T06:07:14Z)
• Graph Neural Networks with Adaptive Frequency Response Filter [55.626174910206046]
  We develop a graph neural network framework AdaGNN with a well-smooth adaptive frequency response filter. We empirically validate the effectiveness of the proposed framework on various benchmark datasets.
  arXiv  Detail & Related papers  (2021-04-26T19:31:21Z)
• Filter Grafting for Deep Neural Networks: Reason, Method, and Cultivation [86.91324735966766]
  Filter is the key component in modern convolutional neural networks (CNNs) In this paper, we introduce filter grafting (textbfMethod) to achieve this goal. We develop a novel criterion to measure the information of filters and an adaptive weighting strategy to balance the grafted information among networks.
  arXiv  Detail & Related papers  (2020-04-26T08:36:26Z)
• Filter Grafting for Deep Neural Networks [71.39169475500324]
  Filter grafting aims to improve the representation capability of Deep Neural Networks (DNNs) We develop an entropy-based criterion to measure the information of filters and an adaptive weighting strategy for balancing the grafted information among networks. For example, the grafted MobileNetV2 outperforms the non-grafted MobileNetV2 by about 7 percent on CIFAR-100 dataset.
  arXiv  Detail & Related papers  (2020-01-15T03:18:57Z)
• FrequentNet: A Novel Interpretable Deep Learning Model for Image Classification [1.7205106391379026]
  This paper has proposed a new baseline deep learning model of more benefits for image classification. We are inspired by a method called "PCANet" in "PCANet: A Simple Deep Learning Baseline for Image Classification?"
  arXiv  Detail & Related papers  (2020-01-04T04:31:32Z)
• Approximation and Non-parametric Estimation of ResNet-type Convolutional Neural Networks [52.972605601174955]
  We show a ResNet-type CNN can attain the minimax optimal error rates in important function classes. We derive approximation and estimation error rates of the aformentioned type of CNNs for the Barron and H"older classes.
  arXiv  Detail & Related papers  (2019-03-24T19:42:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.