AI Paper Atlas

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

Domain Specified Optimization for Deployment Authorization

Haotian Wang, Haoang Chi, Wenjing Yang, Zhipeng Lin, Mingyang Geng, Long Lan, Jing Zhang, Dacheng Tao

ICCV 2023 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Augmentation and mixture-of-experts generalization · 8 citations (OpenAlex)

Read the paper

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 DSO divergence-ball risk maximization instead of GNTL generative baselineSource-only deployment authorization · Uniform authorization tasks (16 tasks)successful authorization rate: 4/16 -> 15/16Improved
use DSO instead of GNTL on Office-31 trained on AmazonSource-only authorization · Office-31 (Amazon)T-Drop (%): 9.0% -> 30.0%Improved
DSO versus GNTL on digit MNIST_M sourceSource-only authorization · Digit (MNIST_M)T-Drop (%): 35.7% -> 35.0%Mixed
use TDSO with unlabeled unauthorized data instead of DSOTarget-combined authorization · Office-31 (Amazon)T-Drop (%): 30.0% -> 67.5%Improved
increase ratio of unlabeled target data for TDSO from 0.2 to 1.0 (ablation)TDSO · Office-31 Dslr to Webcamunauthorized accuracy: 36.9% -> 4.8%Improved
random label corruption instead of Y_err = Y_S + 1 (ablation)DSO · Office-31 and Visda2017authorization performanceNo clear effect
vary radius rho from 50 to 300 (ablation)DSO · VLCS, Digit, Visda2017authorization accuracyNo clear effect
apply DSO instead of purely supervised trainingSource (authorized) domain performance · Six benchmarksS-Drop: usually less than 3%No clear effect

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