SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2004.04393 · 2020

Universal Source-Free Domain Adaptation

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

There is a strong incentive to develop versatile learning techniques that can transfer the knowledge of class-separability from a labeled source domain to an unlabeled target domain in the presence of a domain-shift. Existing domain adaptation (DA) approaches are not equipped for practical DA scenarios as a result of their reliance on the knowledge of source-target label-set relationship (e.g. Closed-set, Open-set or Partial DA). Furthermore, almost all prior unsupervised DA works require coexistence of source and target samples even during deployment, making them unsuitable for real-time adaptation. Devoid of such impractical assumptions, we propose a novel two-stage learning process. 1) In the Procurement stage, we aim to equip the model for future source-free deployment, assuming no prior knowledge of the upcoming category-gap and domain-shift. To achieve this, we enhance the model's ability to reject out-of-source distribution samples by leveraging the available source data, in a novel generative classifier framework. 2) In the Deployment stage, the goal is to design a unified adaptation algorithm capable of operating across a wide range of category-gaps, with no access to the previously seen source samples. To this end, in contrast to the usage of complex adversarial training regimes, we define a simple yet effective source-free adaptation objective by utilizing a novel instance-level weighting mechanism, named as Source Similarity Metric (SSM). A thorough evaluation shows the practical usability of the proposed learning framework with superior DA performance even over state-of-the-art source-dependent approaches.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2004.04393")
get_code_for_paper("2004.04393")
have("2004.04393")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2004.04393.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2004.04393.svg)](https://syntology.ai/paper/2004.04393)

Connect an agent — have() is free.