AI Paper Atlas

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

Grounding Visual Representations with Texts for Domain Generalization

Seonwoo Min, Nokyung Park, Siwon Kim, Seunghyun Park, Jinkyu Kim

ECCV 2022 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Augmentation and mixture-of-experts generalization · 24 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 Visual and Textual Joint Embedder (ablation)Ours w/ PTE · CUB-DG multi-source (avg over 4 target domains)accuracy: 49.3 -> 57.0Improved
add Textual Explanation Generator (ablation)Ours w/ PTE · CUB-DG multi-source (avg over 4 target domains)accuracy: 56.1 -> 57.0Improved
use per-image texts instead of per-class texts (ablation)Ours w/ PTE · CUB-DG multi-source (avg over 4 target domains)accuracy: 56.5 -> 57.0Improved
raise lambda_align from 0.1 to 1.0 (lambda_expl 1.0) (ablation)Ours w/ PTE · CUB-DG multi-source (avg over 4 target domains)accuracy: 54.8 -> 57.0Improved
raise lambda_expl from 0.1 to 1.0 (lambda_align 1.0) (ablation)Ours w/ PTE · CUB-DG multi-source (avg over 4 target domains)accuracy: 55.9 -> 57.0Improved
raise both lambdas from 0.1 to 1.0 (ablation)Ours w/ PTE · CUB-DG multi-source (avg over 4 target domains)accuracy: 53.5 -> 57.0Improved
replace CLIP text encoder with MPNet, DistillBERT or MiniLM (ablation)Ours w/ PTE · CUB-DG multi-source (avg over 4 target domains)accuracy: 57.0 -> 56.3No clear effect
use self-supervised textual encoder instead of pre-trained CLIP encoderOurs · CUB-DG multi-source (avg over 4 target domains)accuracy: 57.0 vs 56.6No clear effect
add joint embedder to explanation generator (ablation)Ours · Generated explanation quality (CUB-DG)CIDEr-D: 28.4 -> 40.7Improved
add joint embedder to explanation generator (ablation)Ours · Generated explanation quality (CUB-DG)BLEU-4: 42.9 -> 48.0Improved
add text grounding vs best baseline SDOurs w/ PTE · CUB-DG single-source (avg over target domains)accuracy: 41.7 -> 45.7Improved
add text grounding vs best baseline CORALOurs w/ PTE · CUB-DG multi-source (avg over 4 target domains)accuracy: 55.4 -> 57.0Improved

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