AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

Class-Incremental Domain Adaptation

Jogendra Nath Kundu, Rahul Mysore Venkatesh, Naveen Venkat, Ambareesh Revanur, R. Venkatesh Babu

ECCV 2020 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Conditional distribution alignment · 50 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 trainable guides via domain projection networks (target-specific latent space) (ablation)Ours · Office (20 shared/31 classes, one-shot)avg accuracy, all classes (%): 66.4 -> 72.4Improved
add regularization loss L_r on proxy-source samples (ablation)Ours · Office (20 shared/31 classes, one-shot)avg accuracy, all classes (%): 67.5 -> 72.4Improved
add compactness loss L_a2 (ablation)Ours · Office (20 shared/31 classes, one-shot)avg accuracy, private classes (%): 68.1 -> 71.8Improved
use real source data instead of Gaussian prototype proxy samples (ablation)Ours · Office (20 shared/31 classes, one-shot)avg accuracy, all classes (%): 72.4 -> 72.9No clear effect
add class separability objective L_s1 in source training (ablation)Ours · Office A->D (one-shot)accuracy (%): 68.6 -> 72.2Improved
add negative training samples in source training (ablation)Ours · Office A->D (one-shot)accuracy (%): 67.4 -> 72.2Improved
add negative training samples in source training (ablation)Ours · Office A->D (one-shot)private-class accuracy (%): 62.3 -> 72.6Improved
add negative training samples in source training (ablation)source model · Office A->Dsource accuracy (%): 96.9 -> 96.7No clear effect
add trainable guides via domain projection networks (ablation)Ours · Office (20 shared/31 classes, one-shot)avg private-class accuracy (%): 64.5 -> 71.8Improved
two-step model upgrade (A to D to W) instead of direct adaptationOurs · Office W targetaccuracy (%): 80.3 -> 79.9No clear effect
use proposed method instead of UAN+TPC (few-shot)UAN+TPC · Office (10/20 classes, few-shot)avg private accuracy: 28.6 -> 75.3Improved

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