AI Paper Atlas

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

Learn-to-Decompose: Cascaded Decomposition Network for Cross-Domain Few-Shot Facial Expression Recognition

Xinyi Zou, Yan Yan, Jing-Hao Xue, Si Chen, Hanzi Wang

ECCV 2022 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Cross-domain few-shot with transformers

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 partial regularization instead of full regularization (ablation)CDNet · CFEE_C 1-shot (pre-trained)accuracy: 55.91 -> 56.99Improved
use partial regularization instead of fixing the pre-trained decomposition block (ablation)CDNet · RAF_C 5-shot (pre-trained)accuracy: 62.12 -> 63.03Improved
add partial regularization from the pre-trained decomposition block (ablation)CDNet · RAF_C 5-shot (pre-trained)accuracy: 61.00 -> 63.03Improved
use sequential decomposition with shared LD modules instead of parallel modules (ablation)CDNet · EmotioNet_C 1-shot (pre-trained)accuracy: 54.27 -> 55.16Improved
use two-block LD module instead of single transformation module (ablation)CDNet · RAF_C 1-shot (pre-trained)accuracy: 43.22 -> 46.07Improved
add the cascaded decomposition design (no regularization) to ProtoNet baseline (ablation)ProtoNet · CFEE_C 1-shot (pre-trained)accuracy: 53.43 -> 55.17Improved
initialize fine-tuning from batch-trained pre-trained model (ablation)CDNet · RAF_C 5-shotaccuracy: 61.75 -> 63.03Improved
initialize fine-tuning from batch-trained pre-trained model (ablation)ProtoNet baseline · CFEE_C 1-shotaccuracy: 53.29 -> 53.43Improved
increase the number of cascaded LD modules beyond 3 (ablation)CDNet · CFEE_C, EmotioNet_C, RAF_CaccuracyHurt
cascade 2 or 3 shared LD modules instead of 1 (ablation)CDNet · CFEE_C, EmotioNet_C, RAF_CaccuracyImproved
add a single LD module to the baseline (1 cascaded module vs 0) (ablation)CDNet · CFEE_C, EmotioNet_C, RAF_CaccuracyImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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