paper-with-me

홈 › Papers

A Game-Theoretic Taxonomy of Visual Concepts in DNNs

2021-06-21 · Xu Cheng, Chuntung Chu, Yi Zheng, Jie Ren, Quanshi Zhang

In this paper, we rethink how a DNN encodes visual concepts of different complexities from a new perspective, i.e. the game-theoretic multi-order interactions between pixels in an image. Beyond the categorical taxonomy of objects and the cognitive taxonomy of textures and shapes, we provide a new taxonomy of visual concepts, which helps us interpret the encoding of shapes and textures, in terms of concept complexities. In this way, based on multi-order interactions, we find three distinctive signal-processing behaviors of DNNs encoding textures. Besides, we also discover the flexibility for a DNN to encode shapes is lower than the flexibility of encoding textures. Furthermore, we analyze how DNNs encode outlier samples, and explore the impacts of network architectures on interactions. Additionally, we clarify the crucial role of the multi-order interactions in real-world applications. The code will be released when the paper is accepted.

📄 PDF Abstract BibTeX arXiv:2106.10938

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

A taxonomy of strategic human interactions in traffic conflicts

2021-09-27 · Atrisha Sarkar, Kate Larson, Krzysztof Czarnecki

In order to enable autonomous vehicles (AV) to navigate busy traffic situations, in recent years there has been a focus on game-theoretic models for strategic behavior planning in AVs. However, a lack of common taxonomy …

Autonomous VehiclesNavigate

On Concept-Based Explanations in Deep Neural Networks

2019-09-25 · Chih-Kuan Yeh, Been Kim, Sercan Arik, Chun-Liang Li 외

Deep neural networks (DNNs) build high-level intelligence on low-level raw features. Understanding of this high-level intelligence can be enabled by deciphering the concepts they base their decisions on, as human-level t…

Contrastive Sparse Autoencoders for Interpreting Planning of Chess-Playing Agents

2024-06-06 · Yoann Poupart

AI led chess systems to a superhuman level, yet these systems heavily rely on black-box algorithms. This is unsustainable in ensuring transparency to the end-user, particularly when these systems are responsible for sens…

Decision Making

A survey on Concept-based Approaches For Model Improvement

2024-03-21 · Avani Gupta, P J Narayanan

The focus of recent research has shifted from merely improving the metrics based performance of Deep Neural Networks (DNNs) to DNNs which are more interpretable to humans. The field of eXplainable Artificial Intelligence…

DisentanglementExplainable artificial intelligenceExplainable Artificial Intelligence (XAI)Survey

Using Cooperative Game Theory to Prune Neural Networks

2023-11-17 · Mauricio Diaz-Ortiz Jr, Benjamin Kempinski, Daphne Cornelisse, Yoram Bachrach 외

We show how solution concepts from cooperative game theory can be used to tackle the problem of pruning neural networks. The ever-growing size of deep neural networks (DNNs) increases their performance, but also their co…