paper-with-me

Papers

Inverting the Feature Visualization Process for Feedforward Neural Networks

2020-07-21 · Christian Reinbold, Rüdiger Westermann

This work sheds light on the invertibility of feature visualization in neural networks. Since the input that is generated by feature visualization using activation maximization does, in general, not yield the feature objective it was optimized for, we investigate optimizing for the feature objective that yields this input. Given the objective function used in activation maximization that measures how closely a given input resembles the feature objective, we exploit that the gradient of this function w.r.t. inputs is---up to a scaling factor---linear in the objective. This observation is used to find the optimal feature objective via computing a closed form solution that minimizes the gradient. By means of Inverse Feature Visualization, we intend to provide an alternative view on a networks sensitivity to certain inputs that considers feature objectives rather than activations.

📄 PDF Abstract BibTeX arXiv:2007.10757

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Visualization, Discriminability and Applications of Interpretable Saak Features

2019-02-25 · Abinaya Manimaran, Thiyagarajan Ramanathan, Suya You, C-C Jay Kuo

In this work, we study the power of Saak features as an effort towards interpretable deep learning. Being inspired by the operations of convolutional layers of convolutional neural networks, multi-stage Saak transform wa…

General Classificationimage-classificationImage Classification

Physics-guided neural networks for feedforward control: From consistent identification to feedforward controller design

2022-04-01 · Max Bolderman, Mircea Lazar, Hans Butler

Model-based feedforward control improves tracking performance of motion systems, provided that the model describing the inverse dynamics is of sufficient accuracy. Model sets, such as neural networks (NNs) and physics-gu…

Visualizing Object Detection Features

2015-02-19 · Carl Vondrick, Aditya Khosla, Hamed Pirsiavash, Tomasz Malisiewicz 외

We introduce algorithms to visualize feature spaces used by object detectors. Our method works by inverting a visual feature back to multiple natural images. We found that these visualizations allow us to analyze object …

Objectobject-detectionObject Detection

GANSlider: How Users Control Generative Models for Images using Multiple Sliders with and without Feedforward Information

2022-02-02 · Hai Dang, Lukas Mecke, Daniel Buschek

We investigate how multiple sliders with and without feedforward visualizations influence users' control of generative models. In an online study (N=138), we collected a dataset of people interacting with a generative ad…

Generative Adversarial NetworkImage Reconstruction

Inverting and Visualizing Features for Object Detection

2012-12-11 · Carl Vondrick, Aditya Khosla, Tomasz Malisiewicz, Antonio Torralba

We introduce algorithms to visualize feature spaces used by object detectors. The tools in this paper allow a human to put on `HOG goggles' and perceive the visual world as a HOG based object detector sees it. We found t…

Objectobject-detectionObject Detection