GeomCA: Geometric Evaluation of Data Representations
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.
Code (1)
Tasks
Contrastive LearningRepresentation LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Evaluating Local Geometric Feature Representations for 3D Rigid Data Matching
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 RegistrationRetrievalDelaunay Component Analysis for Evaluation of Data Representations
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 LearningSkeletal Point Representations with Geometric Deep Learning
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 LearningFrom Symbolic to Geometric: Enabling Spatial Reasoning in Large Language Models
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 ReasoningSAND: Spatially Adaptive Network Depth for Fast Sampling of Neural Implicit Surfaces
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…