SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2310.01926 · ICCV · 2023

DARTH: Holistic Test-time Adaptation for Multiple Object Tracking

Bernt Schiele, Fisher Yu, Mattia Segu

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 3 functions out of this paper's own repositories and ran 3 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
mattiasegu/darth canonical 3 of 3
FunctionStatusWhere it lives
majority_vote Ran mattiasegu/darth/darth/core/track/postprocessing.py
code served (permissive licence) · get_code("d322dd3188b65f75")
random_color Ran mattiasegu/darth/darth/core/utils/visualization.py
code served (permissive licence) · get_code("f5582ad06308b3d9")
xyxy2xywh Ran mattiasegu/darth/darth/core/to_scalabel/utils.py
code served (permissive licence) · get_code("443a802f0281709c")

Repositories linked to this paper

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

Abstract

Multiple object tracking (MOT) is a fundamental component of perception systems for autonomous driving, and its robustness to unseen conditions is a requirement to avoid life-critical failures. Despite the urge of safety in driving systems, no solution to the MOT adaptation problem to domain shift in test-time conditions has ever been proposed. However, the nature of a MOT system is manifold -requiring object detection and instance association -and adapting all its components is non-trivial. In this paper, we analyze the effect of domain shift on appearance-based trackers, and introduce DARTH, a holistic test-time adaptation framework for MOT. We propose a detection consistency formulation to adapt object detection in a self-supervised fashion, while adapting the instance appearance representations via our novel patch contrastive loss. We evaluate our method on a variety of domain shifts -including sim-toreal, outdoor-to-indoor, indoor-to-outdoor -and substantially improve the source model performance on all metrics.

For agents

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

get_harvested_code_for_paper("2310.01926")
get_code_for_paper("2310.01926")
have("2310.01926")

Connect an agent — have() is free.