AI Paper Atlas

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

Less-Forgetful Learning for Domain Expansion in Deep Neural Networks

Heechul Jung, Jeongwoo Ju, Minju Jung, Junmo Kim

AAAI 2018 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Adversarial domain adaptation · 77 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
Use LF instead of modified LwFDomain expansion learning · MNIST ∪ SVHNAvg. (%): 89.28 -> 90.58Improved
Use LF instead of modified LwFDomain expansion learning · CIFAR Color ∪ CIFAR GrayAvg. (%): 74.33 -> 74.77Improved
Use LF instead of modified LwFDomain expansion learning · ImageNet Normal ∪ Dark & BrightAvg. (%): 83.56 -> 84.69Improved
Use LF instead of fine-tuningDomain expansion learning · CIFAR-10 continual learningClassification rate: 67.18 -> 71.1Improved
Use LF instead of offline trainingCIFAR-10 continual learning · CIFAR-10 continual learningClassification rate: 78.16 -> 71.1Hurt
Increase the feature-matching loss weight λe from 2.0×10^-4 to 1.6×10^-3 (ablation)LF · MNIST ∪ SVHNAvg. (%): 86.91 -> 90.58Improved
Increase the feature-matching loss weight λe from 2.0×10^-4 to 1.6×10^-3 (ablation)LF · CIFAR Color ∪ CIFAR GrayAvg. (%): 73.51 -> 74.77Improved
Vary λe across the tested values (ablation)LF · ImageNet Normal ∪ Dark & BrightAvg. (%): 84.04; 84.69; 84.34; 84.30Mixed
Replace ReLU with Maxout (ablation)Fine-tuning · Tiny image experimentsOld/new domain classification ratesMixed
Replace ReLU with LWTA (ablation)Fine-tuning · Tiny image experimentsOld/new domain classification ratesNo clear effect
Fine-tune only the softmax classifier layer (ablation)Domain expansion learning · MNIST ∪ SVHNNew (%): 52.01Hurt
Use weight constraint instead of LF (ablation)Domain expansion learning · MNIST ∪ SVHNOld (%): 97.37 vs 80.29Hurt

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