AI Paper Atlas

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

Multi-Source Open-Set Deep Adversarial Domain Adaptation

Sayan Rakshit, Dipesh Tamboli, Pragati Shuddhodhan Meshram, Biplab Banerjee, Gemma Roig, Subhasis Chaudhuri

ECCV 2020 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Adversarial domain adaptation · 32 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 margin loss L_margin (ablation)MOSDANet · Office-31 A,D-W and Office-Home ACR-POS (%): at least by 4%Improved
add margin loss L_margin (ablation)MOSDANet · Office-31 A,D-Wknown vs unknown probability difference: ≈0.3 -> ≈0.55Improved
raise margin tau from 0.2 to 0.6 (ablation)MOSDANet · Office-Home ACR-POS (%): 66.4 -> 80.0Improved
raise margin tau from 0.2 to 0.6 (ablation)MOSDANet · Office-31 AD-WOS (%): 95.8 -> 98.2Improved
add explicit source-domain alignment term (ablation)MOSDANet · Office-31 A,D-WOS and OS* (%): more than 10%Improved
use ensemble decision fusion instead of best member classifier (ablation)MOSDANet · Office-31 (avg)OS (%): 84.9 -> 91.9Improved
use ensemble decision fusion instead of best member classifier (ablation)MOSDANet · Office-Caltech (avg)OS (%): 92.9 -> 95.8Improved
use ensemble decision fusion instead of best member classifier (ablation)MOSDANet · Office-Home (avg)OS (%): 70.5 -> 72.1Improved
multi-source MOSDANet vs source-combine IOSDA-BPIOSDA-BP · Office-31 (avg)OS (%): 83.2 -> 91.9Improved
increase openness from O=0.03 to O=0.35 (ablation)MOSDANet · Office-31 AD-WOS (%): 89.4 -> 98.2Improved
closed-set DA (DANN) alignment before OSVM vs OSVM aloneOSVM (source combine) · Office-31 (avg)OS (%): 56.3 -> 70.9Improved

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