paper-with-me

홈 › Papers

Spectral Metric for Dataset Complexity Assessment

2019-05-17 · CVPR 2019 6 · Frederic Branchaud-Charron, Andrew Achkar, Pierre-Marc Jodoin

In this paper, we propose a new measure to gauge the complexity of image classification problems. Given an annotated image dataset, our method computes a complexity measure called the cumulative spectral gradient (CSG) which strongly correlates with the test accuracy of convolutional neural networks (CNN). The CSG measure is derived from the probabilistic divergence between classes in a spectral clustering framework. We show that this metric correlates with the overall separability of the dataset and thus its inherent complexity. As will be shown, our metric can be used for dataset reduction, to assess which classes are more difficult to disentangle, and approximate the accuracy one could expect to get with a CNN. Results obtained on 11 datasets and three CNN models reveal that our method is more accurate and faster than previous complexity measures.

📄 PDF Abstract BibTeX arXiv:1905.07299

Code (1)

Dref360/spectral_metric tf

Tasks

ClusteringGeneral Classificationimage-classificationImage Classification

Methods 이 논문이 사용한 방법론

Spectral Clustering Spectral clustering has attracted increasing attention due to the promising ability in dealing with nonlinearly separable datasets [15], [16]. In spectral clustering, the…

Similar Papers 제목 키워드 기반

ELADO: Elliptic PDE Assessment Datasets for Operator Learning

2026-06-18 · Frank Ehebrecht, Toni Scharle, Martin Atzmueller arxiv

We introduce ELADO (Elliptic PDE Assessment Datasets for Operator Learning), a systematic benchmark suite constructed to show and quantify failure modes of neural operator architectures when learning solution operators o…

RGB to Hyperspectral: Spectral Reconstruction for Enhanced Surgical Imaging

2024-10-17 · Tobias Czempiel, Alfie Roddan, Maria Leiloglou, Zepeng Hu 외

This study investigates the reconstruction of hyperspectral signatures from RGB data to enhance surgical imaging, utilizing the publicly available HeiPorSPECTRAL dataset from porcine surgery and an in-house neurosurgery …

Decision MakingSpectral ReconstructionSSIM

Perceptual Image Quality Assessment through Spectral Analysis of Error Representations

2018-10-14 · Dogancan Temel, Ghassan AlRegib

In this paper, we analyze the statistics of error signals to assess the perceived quality of images. Specifically, we focus on the magnitude spectrum of error images obtained from the difference of reference and distorte…

Image Quality Assessment

Full-reference Point Cloud Quality Assessment Using Spectral Graph Wavelets

2024-06-14 · Ryosuke Watanabe, Keisuke Nonaka, Eduardo Pavez, Tatsuya Kobayashi 외

Point clouds in 3D applications frequently experience quality degradation during processing, e.g., scanning and compression. Reliable point cloud quality assessment (PCQA) is important for developing compression algorith…

DenoisingPoint Cloud Quality Assessment

Evaluating Knowledge Graph Complexity via Semantic, Spectral, and Structural Metrics for Link Prediction

2025-08-21 · Haji Gul, Abul Ghani Naim, Ajaz Ahmad Bhat arxiv

Understanding dataset complexity is fundamental to evaluating and comparing link prediction models on knowledge graphs (KGs). While the Cumulative Spectral Gradient (CSG) metric, derived from probabilistic divergence bet…

Knowledge GraphsLink Prediction