AI Paper Atlas

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

Gradual Domain Adaptation via Gradient Flow

Zhan Zhuang, Yu Zhang, Ying Wei

ICLR 2024 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Feature alignment for unsupervised adaptation

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes a gradual domain adaptation method based on gradient flow that bridges source and target domains without requiring real intermediate domains, improving the source classifier.

Problem

Domain shift degrades classifiers on new distributions; gradual domain adaptation needs continuous intermediate domains, which are sometimes unavailable.

Approach

Instead of relying on real intermediate domains with pseudo-labels, the method generates intermediate domains via gradient flow to gradually adapt the source classifier toward the target. Abstract is truncated; details beyond the abstract are not stated.

Experimental setup

Builds on: gradual domain adaptation unsupervised domain adaptation

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