AI Paper Atlas

Research map / Learning theory and algorithms / Clustering

Video Face Clustering With Unknown Number of Clusters

Makarand Tapaswi, Marc T. Law, Sanja Fidler

ICCV 2019 · Learning theory and algorithms › Clustering · approach: Clustering approximation algorithms · 67 citations (OpenAlex)

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 changedWhereMeasuredEffect
add L2 normalization of embeddings (ablation)BCL · Validation (66 actors)NMI: 74.57 -> 77.09Improved
train on single face images instead of averaging a random half subset of track images (ablation)BCL · Validation (66 actors)NMI: 7% lower NMI (absolute) with 124 clustersImproved
use mini-batch size 2000 instead of 500 (ablation)BCL · Validation (66 actors)NMI: 72.13 -> 77.09Improved
use mini-batch size 2000 instead of 4000 (ablation)BCL · Validation (66 actors)WCP: 79.68 -> 85.65Improved
use embedding dimension 64 instead of 8 (ablation)BCL · Validation (66 actors)NMI: 47.62 -> 77.09Improved
use embedding dimension 64 instead of 32 (ablation)BCL · Validation (66 actors)NMI: 75.48 -> 77.09No clear effect
swap SE-ResNet50-256 for ResNet50 base CNN (ablation)BCL · Validation (66 actors)NMI: 77.09 -> 76.74No clear effect
add L2 normalization of embeddings (ablation)Prototypical loss · Test episodesNMI: over 15% NMI reductionHurt
replace prototypical loss with BCL loss, evaluated with HAC (K known)clustering embeddings · Test BBT (6 episodes)NMI: 68.3 -> 70.6Improved
replace prototypical loss with BCL loss, evaluated with K-means (K known)clustering embeddings · Test BBT (6 episodes)NMI: 60.7 -> 60.5Improved
fine-tune with automatically obtained positive/negative pairsBCL · Test BBT (6 episodes)NMI: 73.22 -> 88.26Improved
fine-tune with automatically obtained positive/negative pairsBCL · Test BUFFY (6 episodes)NMI: 71.23 -> 77.05Improved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy