SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2303.13899 · CVPR · 2023

Robust Test-Time Adaptation in Dynamic Scenarios

Shuang Li, Binhui Xie, Longhui Yuan

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 5 functions out of this paper's own repositories and ran 2 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
BIT-DA/RoTTA — 2 of 5
FunctionStatusWhere it lives
ColorJitterPro Ran BIT-DA/RoTTA/core/adapter/rotta.py
code served (permissive licence) · get_code("a0c7ae238f5f94ce")
timeliness_reweighting Ran BIT-DA/RoTTA/core/adapter/rotta.py
code served (permissive licence) · get_code("2fd0610ee153f304")
BaseAdapter Not yet run BIT-DA/RoTTA/core/adapter/rotta.py
code served (permissive licence) · get_code("8d1f9b683822a8a0")
RoTTA Not yet run BIT-DA/RoTTA/core/adapter/rotta.py
code served (permissive licence) · get_code("a381237713615fae")
get_tta_transforms Not yet run BIT-DA/RoTTA/core/adapter/rotta.py
code served (permissive licence) · get_code("2810e57d868cd873")

Repositories linked to this paper

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

Abstract

Test-time adaptation (TTA) intends to adapt the pretrained model to test distributions with only unlabeled test data streams. Most of the previous TTA methods have achieved great success on simple test data streams such as independently sampled data from single or multiple distributions. However, these attempts may fail in dynamic scenarios of real-world applications like autonomous driving, where the environments gradually change and the test data is sampled correlatively over time. In this work, we explore such practical test data streams to deploy the model on the fly, namely practical test-time adaptation (PTTA). To do so, we elaborate a Robust Test-Time Adaptation (RoTTA) method against the complex data stream in PTTA. More specifically, we present a robust batch normalization scheme to estimate the normalization statistics. Meanwhile, a memory bank is utilized to sample category-balanced data with consideration of timeliness and uncertainty. Further, to stabilize the training procedure, we develop a time-aware reweighting strategy with a teacher-student model. Extensive experiments prove that RoTTA enables continual testtime adaptation on the correlatively sampled data streams. Our method is easy to implement, making it a good choice for rapid deployment. The code is publicly available at https://github.com/BIT-DA/RoTTA

For agents

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

get_harvested_code_for_paper("2303.13899")
get_code_for_paper("2303.13899")
have("2303.13899")

Connect an agent — have() is free.