paper-with-me

홈 › Papers

Understanding trained CNNs by indexing neuron selectivity

2017-02-01 · Ivet Rafegas, Maria Vanrell, Luis A. Alexandre, Guillem Arias

The impressive performance of Convolutional Neural Networks (CNNs) when solving different vision problems is shadowed by their black-box nature and our consequent lack of understanding of the representations they build and how these representations are organized. To help understanding these issues, we propose to describe the activity of individual neurons by their Neuron Feature visualization and quantify their inherent selectivity with two specific properties. We explore selectivity indexes for: an image feature (color); and an image label (class membership). Our contribution is a framework to seek or classify neurons by indexing on these selectivity properties. It helps to find color selective neurons, such as a red-mushroom neuron in layer Conv4 or class selective neurons such as dog-face neurons in layer Conv5 in VGG-M, and establishes a methodology to derive other selectivity properties. Indexing on neuron selectivity can statistically draw how features and classes are represented through layers in a moment when the size of trained nets is growing and automatic tools to index neurons can be helpful.

📄 PDF Abstract BibTeX arXiv:1702.00382

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Understanding the functional and structural differences across excitatory and inhibitory neurons

2019-09-25 · Sun Minni, Li Ji-An, Theodore Moskovitz, Grace Lindsay 외

One of the most fundamental organizational principles of the brain is the separation of excitatory (E) and inhibitory (I) neurons. In addition to their opposing effects on post-synaptic neurons, E and I cells tend to dif…

On the Capability of CNNs to Generalize to Unseen Category-Viewpoint Combinations

2021-01-01 · Spandan Madan, Timothy Henry, Jamell Arthur Dozier, Helen Ho 외

Object recognition and viewpoint estimation lie at the heart of visual understanding. Recent works suggest that convolutional neural networks (CNNs) fail to generalize to category-viewpoint combinations not seen during t…

Object RecognitionViewpoint Estimation

Complexity and Diversity in Sparse Code Priors Improve Receptive Field Characterization of Macaque V1 Neurons

2019-11-19 · Ziniu Wu, Harold Rockwell, Yimeng Zhang, Shiming Tang 외

System identification techniques -- projection pursuit regression models (PPRs) and convolutional neural networks (CNNs) -- provide state-of-the-art performance in predicting visual cortical neurons' responses to arbitra…

Diversity

Revisiting the Importance of Individual Units in CNNs via Ablation

2018-06-07 · Bolei Zhou, Yiyou Sun, David Bau, Antonio Torralba

We revisit the importance of the individual units in Convolutional Neural Networks (CNNs) for visual recognition. By conducting unit ablation experiments on CNNs trained on large scale image datasets, we demonstrate that…

General Classification

Understanding Neural Networks and Individual Neuron Importance via Information-Ordered Cumulative Ablation

2018-04-18 · Rana Ali Amjad, Kairen Liu, Bernhard C. Geiger

In this work, we investigate the use of three information-theoretic quantities -- entropy, mutual information with the class variable, and a class selectivity measure based on Kullback-Leibler divergence -- to understand…

ClassificationGeneral Classification