paper-with-me

Papers

What do CNN neurons learn: Visualization & Clustering

2020-10-18 · Haoyue Dai

In recent years convolutional neural networks (CNN) have shown striking progress in various tasks. However, despite the high performance, the training and prediction process remains to be a black box, leaving it a mystery to extract what neurons learn in CNN. In this paper, we address the problem of interpreting a CNN from the aspects of the input image's focus and preference, and the neurons' domination, activation and contribution to a concrete final prediction. Specifically, we use two techniques - visualization and clustering - to tackle the problems above. Visualization means the method of gradient descent on image pixel, and in clustering section two algorithms are proposed to cluster respectively over image categories and network neurons. Experiments and quantitative analyses have demonstrated the effectiveness of the two methods in explaining the question: what do neurons learn.

📄 PDF Abstract BibTeX arXiv:2010.11725

Code (0)

등록된 구현이 없습니다.

Tasks

Clustering

Similar Papers 제목 키워드 기반

Vision Transformer Visualization: What Neurons Tell and How Neurons Behave?

2022-10-14 · Van-Anh Nguyen, Khanh Pham Dinh, Long Tung Vuong, Thanh-Toan Do 외

Recently vision transformers (ViT) have been applied successfully for various tasks in computer vision. However, important questions such as why they work or how they behave still remain largely unknown. In this paper, w…

Feature Visualization

2020-01-10 · Distill 2020 1 · Chris Olah, Alexander Mordvintsev, Ludwig Schubert

There is a growing sense that neural networks need to be interpretable to humans. The field of neural network interpretability has formed in response to these concerns. As it matures, two major threads of research have b…

VITAL: More Understandable Feature Visualization through Distribution Alignment and Relevant Information Flow

2025-03-28 · Ada Gorgun, Bernt Schiele, Jonas Fischer

Neural networks are widely adopted to solve complex and challenging tasks. Especially in high-stakes decision-making, understanding their reasoning process is crucial, yet proves challenging for modern deep networks. Fea…

Decision Making

AMSOM: Adaptive Moving Self-organizing Map for Clustering and Visualization

2016-05-19 · Gerasimos Spanakis, Gerhard Weiss

Self-Organizing Map (SOM) is a neural network model which is used to obtain a topology-preserving mapping from the (usually high dimensional) input/feature space to an output/map space of fewer dimensions (usually two or…

Clustering

PCACE: A Statistical Approach to Ranking Neurons for CNN Interpretability

2021-12-31 · Sílvia Casacuberta, Esra Suel, Seth Flaxman

In this paper we introduce a new problem within the growing literature of interpretability for convolution neural networks (CNNs). While previous work has focused on the question of how to visually interpret CNNs, we ask…

Air Pollution Prediction