MDM:Visual Explanations for Neural Networks via Multiple Dynamic Mask
- URL: http://arxiv.org/abs/2207.08046v1
- Date: Sun, 17 Jul 2022 00:25:16 GMT
- Title: MDM:Visual Explanations for Neural Networks via Multiple Dynamic Mask
- Authors: Yitao Peng, Longzhen Yang, Yihang Liu, Lianghua He
- Abstract summary: We propose an algorithm Multiple Dynamic Mask(MDM), which is a general saliency graph query method with interpretability of the inference process.
For the MDM saliency map search algorithm, we experimentally compared the performance indicators of various saliency map search methods and the MDM with ResNet and DenseNet as the trained neural networks.
- Score: 5.333582981327497
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: The active region lookup of a neural network tells us which regions the
neural network focuses on when making a decision, which gives us a basis for
interpretability when the neural network makes a classification decision. We
propose an algorithm Multiple Dynamic Mask(MDM), which is a general saliency
graph query method with interpretability of the inference process. Its proposal
is based on an assumption: when a picture is input to a neural network that has
been trained, the activation features related to classification will affect the
classification results of the neural network, and the features unrelated to
classification will hardly affect the classification results of the network.
MDM: A learning-based end-to-end algorithm for finding regions of interest for
neural network classification. It has the following advantages: 1. It has the
interpretability of the reasoning process. 2. It is universal, it can be used
for any neural network and does not depend on the internal structure of the
neural network. 3. The search performance is better. Because the algorithm is
based on learning to generate masks and has the ability to adapt to different
data and networks, the performance is better than the method proposed in the
previous paper. For the MDM saliency map search algorithm, we experimentally
compared the performance indicators of various saliency map search methods and
the MDM with ResNet and DenseNet as the trained neural networks. The search
effect performance of the MDM reached the state of the art. We applied the MDM
to the interpretable neural network ProtoPNet and XProtoNet, which improved the
interpretability of the model and the prototype search performance. We
visualize the performance of convolutional neural architecture and Transformer
architecture on saliency map search.
Related papers
- Graph Neural Networks for Learning Equivariant Representations of Neural Networks [55.04145324152541]
We propose to represent neural networks as computational graphs of parameters.
Our approach enables a single model to encode neural computational graphs with diverse architectures.
We showcase the effectiveness of our method on a wide range of tasks, including classification and editing of implicit neural representations.
arXiv Detail & Related papers (2024-03-18T18:01:01Z) - Sparse Multitask Learning for Efficient Neural Representation of Motor
Imagery and Execution [30.186917337606477]
We introduce a sparse multitask learning framework for motor imagery (MI) and motor execution (ME) tasks.
Given a dual-task CNN model for MI-ME classification, we apply a saliency-based sparsification approach to prune superfluous connections.
Our results indicate that this tailored sparsity can mitigate the overfitting problem and improve the test performance with small amount of data.
arXiv Detail & Related papers (2023-12-10T09:06:16Z) - SA-CNN: Application to text categorization issues using simulated
annealing-based convolutional neural network optimization [0.0]
Convolutional neural networks (CNNs) are a representative class of deep learning algorithms.
We introduce SA-CNN neural networks for text classification tasks based on Text-CNN neural networks.
arXiv Detail & Related papers (2023-03-13T14:27:34Z) - DProtoNet: Decoupling the inference module and the explanation module
enables neural networks to have better accuracy and interpretability [5.333582981327497]
In the previous method, by modifying the architecture of the neural network, the network simulates the human reasoning process.
We propose DProtoNet (Decoupling Prototypical network), it stores the decision basis of the neural network by using feature masks.
It decouples the neural network inference module from the interpretation module, and removes the specific architectural limitations of the interpretable network.
arXiv Detail & Related papers (2022-10-15T17:05:55Z) - Increasing the Accuracy of a Neural Network Using Frequency Selective
Mesh-to-Grid Resampling [4.211128681972148]
We propose the use of keypoint frequency selective mesh-to-grid resampling (FSMR) for the processing of input data for neural networks.
We show that depending on the network architecture and classification task the application of FSMR during training aids learning process.
The classification accuracy can be increased by up to 4.31 percentage points for ResNet50 and the Oxflower17 dataset.
arXiv Detail & Related papers (2022-09-28T21:34:47Z) - Adaptive Convolutional Dictionary Network for CT Metal Artifact
Reduction [62.691996239590125]
We propose an adaptive convolutional dictionary network (ACDNet) for metal artifact reduction.
Our ACDNet can automatically learn the prior for artifact-free CT images via training data and adaptively adjust the representation kernels for each input CT image.
Our method inherits the clear interpretability of model-based methods and maintains the powerful representation ability of learning-based methods.
arXiv Detail & Related papers (2022-05-16T06:49:36Z) - Data-driven emergence of convolutional structure in neural networks [83.4920717252233]
We show how fully-connected neural networks solving a discrimination task can learn a convolutional structure directly from their inputs.
By carefully designing data models, we show that the emergence of this pattern is triggered by the non-Gaussian, higher-order local structure of the inputs.
arXiv Detail & Related papers (2022-02-01T17:11:13Z) - Neural networks with linear threshold activations: structure and
algorithms [1.795561427808824]
We show that 2 hidden layers are necessary and sufficient to represent any function representable in the class.
We also give precise bounds on the sizes of the neural networks required to represent any function in the class.
We propose a new class of neural networks that we call shortcut linear threshold networks.
arXiv Detail & Related papers (2021-11-15T22:33:52Z) - Why Lottery Ticket Wins? A Theoretical Perspective of Sample Complexity
on Pruned Neural Networks [79.74580058178594]
We analyze the performance of training a pruned neural network by analyzing the geometric structure of the objective function.
We show that the convex region near a desirable model with guaranteed generalization enlarges as the neural network model is pruned.
arXiv Detail & Related papers (2021-10-12T01:11:07Z) - Learning Structures for Deep Neural Networks [99.8331363309895]
We propose to adopt the efficient coding principle, rooted in information theory and developed in computational neuroscience.
We show that sparse coding can effectively maximize the entropy of the output signals.
Our experiments on a public image classification dataset demonstrate that using the structure learned from scratch by our proposed algorithm, one can achieve a classification accuracy comparable to the best expert-designed structure.
arXiv Detail & Related papers (2021-05-27T12:27:24Z) - Joint Learning of Neural Transfer and Architecture Adaptation for Image
Recognition [77.95361323613147]
Current state-of-the-art visual recognition systems rely on pretraining a neural network on a large-scale dataset and finetuning the network weights on a smaller dataset.
In this work, we prove that dynamically adapting network architectures tailored for each domain task along with weight finetuning benefits in both efficiency and effectiveness.
Our method can be easily generalized to an unsupervised paradigm by replacing supernet training with self-supervised learning in the source domain tasks and performing linear evaluation in the downstream tasks.
arXiv Detail & Related papers (2021-03-31T08:15:17Z)
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.