Towards interpreting computer vision based on transformation invariant
optimization
- URL: http://arxiv.org/abs/2106.09982v1
- Date: Fri, 18 Jun 2021 08:04:10 GMT
- Title: Towards interpreting computer vision based on transformation invariant
optimization
- Authors: Chen Li, Jinzhe Jiang, Xin Zhang, Tonghuan Zhang, Yaqian Zhao,
Dongdong Jiang and RenGang Li
- Abstract summary: In this work, visualized images that can activate the neural network to the target classes are generated by back-propagation method.
We show some cases that such method can help us to gain insight into neural networks.
- Score: 10.820985444099536
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Interpreting how does deep neural networks (DNNs) make predictions is a vital
field in artificial intelligence, which hinders wide applications of DNNs.
Visualization of learned representations helps we humans understand the vision
of DNNs. In this work, visualized images that can activate the neural network
to the target classes are generated by back-propagation method. Here, rotation
and scaling operations are applied to introduce the transformation invariance
in the image generating process, which we find a significant improvement on
visualization effect. Finally, we show some cases that such method can help us
to gain insight into neural networks.
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) - Manipulating Feature Visualizations with Gradient Slingshots [54.31109240020007]
We introduce a novel method for manipulating Feature Visualization (FV) without significantly impacting the model's decision-making process.
We evaluate the effectiveness of our method on several neural network models and demonstrate its capabilities to hide the functionality of arbitrarily chosen neurons.
arXiv Detail & Related papers (2024-01-11T18:57:17Z) - Unleashing the Power of Depth and Pose Estimation Neural Networks by
Designing Compatible Endoscopic Images [12.412060445862842]
We conduct a detail analysis of the properties of endoscopic images and improve the compatibility of images and neural networks.
First, we introcude the Mask Image Modelling (MIM) module, which inputs partial image information instead of complete image information.
Second, we propose a lightweight neural network to enhance the endoscopic images, to explicitly improve the compatibility between images and neural networks.
arXiv Detail & Related papers (2023-09-14T02:19:38Z) - SO(2) and O(2) Equivariance in Image Recognition with
Bessel-Convolutional Neural Networks [63.24965775030674]
This work presents the development of Bessel-convolutional neural networks (B-CNNs)
B-CNNs exploit a particular decomposition based on Bessel functions to modify the key operation between images and filters.
Study is carried out to assess the performances of B-CNNs compared to other methods.
arXiv Detail & Related papers (2023-04-18T18:06:35Z) - Adapting Brain-Like Neural Networks for Modeling Cortical Visual
Prostheses [68.96380145211093]
Cortical prostheses are devices implanted in the visual cortex that attempt to restore lost vision by electrically stimulating neurons.
Currently, the vision provided by these devices is limited, and accurately predicting the visual percepts resulting from stimulation is an open challenge.
We propose to address this challenge by utilizing 'brain-like' convolutional neural networks (CNNs), which have emerged as promising models of the visual system.
arXiv Detail & Related papers (2022-09-27T17:33:19Z) - Perception Visualization: Seeing Through the Eyes of a DNN [5.9557391359320375]
We develop a new form of explanation that is radically different in nature from current explanation methods, such as Grad-CAM.
Perception visualization provides a visual representation of what the DNN perceives in the input image by depicting what visual patterns the latent representation corresponds to.
Results of our user study demonstrate that humans can better understand and predict the system's decisions when perception visualizations are available.
arXiv Detail & Related papers (2022-04-21T07:18:55Z) - Visualizing Deep Neural Networks with Topographic Activation Maps [1.1470070927586014]
We introduce and compare methods to obtain a topographic layout of neurons in a Deep Neural Network layer.
We demonstrate how to use topographic activation maps to identify errors or encoded biases and to visualize training processes.
arXiv Detail & Related papers (2022-04-07T15:56:44Z) - 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) - Curriculum By Smoothing [52.08553521577014]
Convolutional Neural Networks (CNNs) have shown impressive performance in computer vision tasks such as image classification, detection, and segmentation.
We propose an elegant curriculum based scheme that smoothes the feature embedding of a CNN using anti-aliasing or low-pass filters.
As the amount of information in the feature maps increases during training, the network is able to progressively learn better representations of the data.
arXiv Detail & Related papers (2020-03-03T07:27:44Z)
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.