paper-with-me

Papers

GeomCA: Geometric Evaluation of Data Representations

2021-05-26 · Petra Poklukar, Anastasia Varava, Danica Kragic

Evaluating the quality of learned representations without relying on a downstream task remains one of the challenges in representation learning. In this work, we present Geometric Component Analysis (GeomCA) algorithm that evaluates representation spaces based on their geometric and topological properties. GeomCA can be applied to representations of any dimension, independently of the model that generated them. We demonstrate its applicability by analyzing representations obtained from a variety of scenarios, such as contrastive learning models, generative models and supervised learning models.

📄 PDF Abstract BibTeX arXiv:2105.12486

Code (1)

petrapoklukar/GeomCA 공식 구현

Tasks

Contrastive LearningRepresentation Learning

Methods 이 논문이 사용한 방법론

Contrastive Learning 설명 없음

Similar Papers 제목 키워드 기반

Evaluating Local Geometric Feature Representations for 3D Rigid Data Matching

2019-06-29 · Jiaqi Yang, Siwen Quan, Peng Wang, Yanning Zhang

Local geometric descriptors remain an essential component for 3D rigid data matching and fusion. The devise of a rotational invariant local geometric descriptor usually consists of two steps: local reference frame (LRF) …

Object RecognitionPoint Cloud RegistrationRetrieval

Delaunay Component Analysis for Evaluation of Data Representations

2022-02-14 · ICLR 2022 4 · Petra Poklukar, Vladislav Polianskii, Anastasia Varava, Florian Pokorny 외

Advanced representation learning techniques require reliable and general evaluation methods. Recently, several algorithms based on the common idea of geometric and topological analysis of a manifold approximated from the…

Representation Learning

Skeletal Point Representations with Geometric Deep Learning

2023-03-03 · Ninad Khargonkar, Beatriz Paniagua, Jared Vicory

Skeletonization has been a popular shape analysis technique that models both the interior and exterior of an object. Existing template-based calculations of skeletal models from anatomical structures are a time-consuming…

Deep Learning

From Symbolic to Geometric: Enabling Spatial Reasoning in Large Language Models

2026-06-03 · Chen Chu, Bita Azarijoo, Li Xiong, Khurram Shafique 외 arxiv

Recent large language models (LLMs) often appear to exhibit spatial reasoning ability; however, this capability is largely \emph{symbolic}, arising from pattern matching over spatial language rather than true \emph{geome…

Prompt EngineeringSpatial Reasoning

SAND: Spatially Adaptive Network Depth for Fast Sampling of Neural Implicit Surfaces

2026-04-15 · Chuanxiang Yang, Junhui Hou, Yuan Liu, Siyu Ren 외 arxiv

Implicit neural representations are powerful for geometric modeling, but their practical use is often limited by the high computational cost of network evaluations. We observe that implicit representations require progre…