paper-with-me

홈 › Papers

Visual Analysis of Neural Architecture Spaces for Summarizing Design Principles

2022-08-20 · Jun Yuan, Mengchen Liu, Fengyuan Tian, Shixia Liu

Recent advances in artificial intelligence largely benefit from better neural network architectures. These architectures are a product of a costly process of trial-and-error. To ease this process, we develop ArchExplorer, a visual analysis method for understanding a neural architecture space and summarizing design principles. The key idea behind our method is to make the architecture space explainable by exploiting structural distances between architectures. We formulate the pairwise distance calculation as solving an all-pairs shortest path problem. To improve efficiency, we decompose this problem into a set of single-source shortest path problems. The time complexity is reduced from O(kn^2N) to O(knN). Architectures are hierarchically clustered according to the distances between them. A circle-packing-based architecture visualization has been developed to convey both the global relationships between clusters and local neighborhoods of the architectures in each cluster. Two case studies and a post-analysis are presented to demonstrate the effectiveness of ArchExplorer in summarizing design principles and selecting better-performing architectures.

📄 PDF Abstract BibTeX arXiv:2208.09665

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

On Network Design Spaces for Visual Recognition

2019-05-30 · ICCV 2019 10 · Ilija Radosavovic, Justin Johnson, Saining Xie, Wan-Yen Lo 외

Over the past several years progress in designing better neural network architectures for visual recognition has been substantial. To help sustain this rate of progress, in this work we propose to reexamine the methodolo…

Neural Architecture Search

embComp: Visual Interactive Comparison of Vector Embeddings

2019-11-05 · Florian Heimerl, Christoph Kralj, Torsten Möller, Michael Gleicher

This paper introduces embComp, a novel approach for comparing two embeddings that capture the similarity between objects, such as word and document embeddings. We survey scenarios where comparing these embedding spaces i…

Massive Data Clustering in Moderate Dimensions from the Dual Spaces of Observation and Attribute Data Clouds

2017-04-06 · Fionn Murtagh

Cluster analysis of very high dimensional data can benefit from the properties of such high dimensionality. Informally expressed, in this work, our focus is on the analogous situation when the dimensionality is moderate …

AttributeClustering

Transformer-Based Visual Segmentation: A Survey

2023-04-19 · Xiangtai Li, Henghui Ding, Haobo Yuan, Wenwei Zhang 외

Visual segmentation seeks to partition images, video frames, or point clouds into multiple segments or groups. This technique has numerous real-world applications, such as autonomous driving, image editing, robot sensing…

Autonomous DrivingPoint Cloud SegmentationSegmentationSurvey

A Dataset for Distilling Knowledge Priors from Literature for Therapeutic Design

2025-08-14 · Haydn Thomas Jones, Natalie Maus, Josh Magnus Ludan, Maggie Ziyu Huan 외 arxiv

AI-driven discovery can greatly reduce design time and enhance new therapeutics' effectiveness. Models using simulators explore broad design spaces but risk violating implicit constraints due to a lack of experimental pr…