paper-with-me

Papers

ShapeY: Measuring Shape Recognition Capacity Using Nearest Neighbor Matching

2021-11-16 · NeurIPS Workshop ImageNet_PPF 2021 12 · Jong Woo Nam, Amanda S. Rios, Bartlett W. Mel

Object recognition in humans depends primarily on shape cues. We have developed a new approach to measuring the shape recognition performance of a vision system based on nearest neighbor view matching within the system's embedding space. Our performance benchmark, ShapeY, allows for precise control of task difficulty, by enforcing that view matching span a specified degree of 3D viewpoint change and/or appearance change. As a first test case we measured the performance of ResNet50 pre-trained on ImageNet. Matching error rates were high. For example, a 27 degree change in object pitch led ResNet50 to match the incorrect object 45% of the time. Appearance changes were also highly disruptive. Examination of false matches indicates that ResNet50's embedding space is severely "tangled". These findings suggest ShapeY can be a useful tool for charting the progress of artificial vision systems towards human-level shape recognition capabilities.

📄 PDF Abstract BibTeX arXiv:2111.08174

Code (0)

등록된 구현이 없습니다.

Tasks

ObjectObject Recognition

Similar Papers 제목 키워드 기반

ShapeY: A Principled Framework for Measuring Shape Recognition Capacity via Nearest-Neighbor Matching

2026-04-27 · Jong Woo Nam, Amanda S. Rios, Bartlett W. Mel arxiv

Object recognition (OR) in humans relies heavily on shape cues and the ability to recognize objects across varying 3D viewpoints. Unlike humans, deep networks often rely on non-shape cues such as texture and background, …

Object Recognition

Disentangling Features in 3D Face Shapes for Joint Face Reconstruction and Recognition

2018-03-30 · CVPR 2018 6 · Feng Liu, Ronghang Zhu, Dan Zeng, Qijun Zhao 외

This paper proposes an encoder-decoder network to disentangle shape features during 3D face reconstruction from single 2D images, such that the tasks of reconstructing accurate 3D face shapes and learning discriminative …

3D Face ReconstructionDecoderFace IdentificationFace Recognition+1

Towards Applying the OPRA Theory to Shape Similarity

2017-05-07 · Christopher H. Dorr, Reinhard Moratz

The motivation for using qualitative shape descriptions is as follows: qualitative shape descriptions can implicitly act as a schema for measuring the similarity of shapes, which has the potential to be cognitively adequ…

Comprehensive Equity Index (CEI): Definition and Application to Bias Evaluation in Biometrics

2024-09-03 · Imanol Solano, Alejandro Peña, Aythami Morales, Julian Fierrez 외

We present a novel metric designed, among other applications, to quantify biased behaviors of machine learning models. As its core, the metric consists of a new similarity metric between score distributions that balances…

Face RecognitionFairness

The Platonic Universe: Do Foundation Models See the Same Sky?

2025-09-23 · UniverseTBD, :, Kshitij Duraphe, Michael J. Smith 외 arxiv

We test the Platonic Representation Hypothesis (PRH) in astronomy by measuring representational convergence across a range of foundation models trained on different data types. Using spectroscopic and imaging observation…