Research map / Label-efficient and robust learning / Recognition and long-tail
Visual Psychophysics for Making Face Recognition Algorithms More Explainable
Brandon RichardWebster, So Yon Kwon, Christopher Clarizio, Samuel E. Anthony, Walter J. Scheirer
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use VGG-Face instead of FaceNet and OpenFace under stimulus perturbation | Face recognition models · LFW 2D perturbation item-response curves | match rate under perturbation | Improved |
| use handcrafted-feature OpenBR instead of deep FaceNet/OpenFace | Face recognition models · LFW 2D perturbation item-response curves | match rate under perturbation | Improved |
| use three-layer random-search CNN (slmsimple) instead of FaceNet/OpenFace | Face recognition models · FaceGen 3D blinking expression | match rate | Improved |
| use FaceNet implementation instead of OpenFace despite higher LFW accuracy | FaceNet · LFW and psychophysics curves | LFW accuracy vs invariance: 0.9292 -> 0.992 | Mixed |
| perturb 6% of VGG-Face weights | VGG-Face · LFW contrast perturbation | match rate: 6% | No clear effect |
| perturb 10% of VGG-Face weights instead of 2% | VGG-Face · LFW contrast perturbation | match rate variance: 2% -> 10% | Hurt |
| blinking expression applied to 3D faces | FaceNet, OpenFace and OpenBR · FaceGen 3D blinking | match rate | Hurt |
Closest papers by meaning
- PsyPhy: A Psychophysics Driven Evaluation Framework for Visual Recognition (TPAMI 2018 · similarity 0.94)
- Measuring Human Perception to Improve Open Set Recognition (TPAMI 2023 · similarity 0.88)
- Self-Calibrating BCIs: Ranking and Recovery of Mental Targets Without Labels (NeurIPS 2025 · similarity 0.86)
- Diff-2-in-1: Bridging Generation and Dense Perception with Diffusion Models (ICLR 2025 · similarity 0.85)
- Hidden in Plain Sight: Evaluating Abstract Shape Recognition in Vision-Language Models (NeurIPS 2024 · similarity 0.84)
- Contour Integration Underlies Human-Like Vision (ICML 2025 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
