paper-with-me

홈 › Papers

Geometric Analysis of Unconstrained Feature Models with $d=K$

2024-07-15 · Yi Shen, Shao Gu

Recently, interesting empirical phenomena known as Neural Collapse have been observed during the final phase of training deep neural networks for classification tasks. We examine this issue when the feature dimension d is equal to the number of classes K. We demonstrate that two popular unconstrained feature models are strict saddle functions, with every critical point being either a global minimum or a strict saddle point that can be exited using negative curvatures. The primary findings conclusively confirm the conjecture on the unconstrained feature models in previous articles.

📄 PDF Abstract BibTeX arXiv:2407.10702

Code (0)

등록된 구현이 없습니다.

Tasks

Articles

Similar Papers 제목 키워드 기반

Neural networks learn to magnify areas near decision boundaries

2023-01-26 · Jacob A. Zavatone-Veth, Sheng Yang, Julian A. Rubinfien, Cengiz Pehlevan

In machine learning, there is a long history of trying to build neural networks that can learn from fewer example data by baking in strong geometric priors. However, it is not always clear a priori what geometric constra…

image-classificationImage ClassificationRepresentation Learning

CADCrafter: Generating Computer-Aided Design Models from Unconstrained Images

2025-04-07 · CVPR 2025 1 · Cheng Chen, Jiacheng Wei, Tianrun Chen, Chi Zhang 외

Creating CAD digital twins from the physical world is crucial for manufacturing, design, and simulation. However, current methods typically rely on costly 3D scanning with labor-intensive post-processing. To provide a us…

A Geometric Analysis of Neural Collapse with Unconstrained Features

2021-05-06 · NeurIPS 2021 12 · Zhihui Zhu, Tianyu Ding, Jinxin Zhou, Xiao Li 외

We provide the first global optimization landscape analysis of $Neural\;Collapse$ -- an intriguing empirical phenomenon that arises in the last-layer classifiers and features of neural networks during the terminal phase …

global-optimization

Best-Buddies Similarity for Robust Template Matching

2015-06-01 · CVPR 2015 6 · Tali Dekel, Shaul Oron, Michael Rubinstein, Shai Avidan 외

We propose a novel method for template matching in unconstrained environments. Its essence is the Best Buddies Similarity (BBS), a useful, robust, and parameter-free similarity measure between two sets of points. BBS is …

Template Matching

Best-Buddies Similarity - Robust Template Matching using Mutual Nearest Neighbors

2016-09-06 · Shaul Oron, Tali Dekel, Tianfan Xue, William T. Freeman 외

We propose a novel method for template matching in unconstrained environments. Its essence is the Best-Buddies Similarity (BBS), a useful, robust, and parameter-free similarity measure between two sets of points. BBS is …

Template Matching