# tim-learn/awesome-test-time-adaptation

Collection of awesome test-time (domain/batch/instance) adaptation methods

Repository: https://github.com/tim-learn/awesome-test-time-adaptation
Canonical: https://ross.abutalabs.com/products/awesome-test-time-adaptation
License: MIT
License Family: permissive
Topics: distribution-shift, source-free-domain-adaptation, test-time-adaptation, test-time-augmentation, test-time-training, continual-test-time-adaptation, domain-adaptation, domain-generalization, transfer-learning
Last push: 2025-11-14T11:14:42+00:00

## Health v2 (maintenance only)
Score: 56/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 52, release rhythm 35, longevity 100
- inputs: {"age_days": 1723, "days_push": 292, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1310, forks 76 (observed 2026-08-28T04:04:19.912591+00:00)

## What it is
A curated awesome-list of research papers, surveys, and resources on test-time adaptation under distribution shifts, covering source-free domain adaptation, batch/instance adaptation, online adaptation, and prior adaptation. It accompanies a comprehensive IJCV survey and includes a shared dataset reference sheet.

## Use cases
- find papers on test-time adaptation under distribution shift
- research source-free domain adaptation methods
- get started with continual test-time adaptation
- find datasets used in TTA benchmarks
- survey online test-time adaptation literature
- compare test-time batch vs instance adaptation approaches

## When to choose
- you are a researcher or student surveying test-time adaptation literature
- you need a structured reading list for domain adaptation under distribution shift
- you want links to surveys and benchmarks in one place

## When to avoid
- you need runnable code or a library rather than a paper list
- you want a maintained software tool for production adaptation
- your topic is unrelated to distribution shift or adaptation

## Facets
- artifact type: learning-resource
- maturity: active
- function: machine-learning, developer-tools
- domain: machine-learning, deep-learning, computer-vision, tutorials
- platform: cross-platform
- tags: awesome-list, test-time-adaptation, domain-adaptation, distribution-shift, survey, transfer-learning

## Member repositories
- tim-learn/awesome-test-time-adaptation (main) score 56

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:19.912591+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:49:56.617584+00:00, confidence not recorded.
  - readme: https://github.com/tim-learn/awesome-test-time-adaptation (fetched 2026-08-28T04:04:19.912591+00:00, sha 320ac1a3543e)
- Data as of 2026-08-30T08:39:29.467469+00:00.