AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Trusted Multi-View Classification With Dynamic Evidential Fusion

Zongbo Han, Changqing Zhang, Huazhu Fu, Joey Tianyi Zhou

TPAMI 2022 · Label-efficient and robust learning › Recognition and long-tail · approach: Uncertainty-aware multi-view learning · 712 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 a pseudo-view (concatenated features) with its own opinion (ablation)TMC · Scene15accuracy (%): 67.74 -> 71.61Improved
add a pseudo-view (concatenated features) (ablation)TMC · HMDBaccuracy (%): 65.26 -> 69.43Improved
add a pseudo-view (concatenated features) (ablation)TMC · PIEaccuracy (%): 91.99 -> 93.75Improved
add a pseudo-view (concatenated features) (ablation)TMC · Caltech101accuracy (%): 92.93 -> 92.83No clear effect
add a pseudo-view (concatenated backbone outputs) (ablation)TMC · SUN RGB-D (fusion)accuracy (%): 60.7 -> 61.3Improved
add a pseudo-view (concatenated backbone outputs) (ablation)TMC · SUN RGB-D (RGB only)accuracy (%): 57.1 -> 56.2Hurt
add a pseudo-view (concatenated backbone outputs) (ablation)TMC · NYUD Depth V2 (fusion)accuracy (%): 70.0 -> 72.5Improved
use evidence-level uncertainty fusion instead of CCA plus linear SVMTMC · Scene15accuracy (%): 55.77 -> 67.74Improved
use stronger correlation maximization (DCCA instead of CCA)CCA baseline · Scene15accuracy (%): 55.77 -> 54.85Hurt
fuse views with uncertainty-based fusion instead of EDL on feature-concatenated inputEDL · UMPC-FOOD101accuracy (%): 90.50 -> 91.30Improved
use feature fusion of image and text instead of best single viewEDL · UMPC-FOOD101accuracy (%): 87.40 -> 90.50Improved
discard samples with uncertainty greater than the largest belief massETMC · SUN RGB-Dmisclassification rate: 0.387 -> 0.187Improved

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