# You Only Look Once at Anytime (AnytimeYOLO): Analysis and Optimization of Early-Exits for Object-Detection

Source: [You Only Look Once at Anytime (AnytimeYOLO): Analysis and Optimization of Early-Exits for Object-Detection](<https://www.sota2.com/research/paper/68fa778f1e209131cea73e3e>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T04:21:39.376Z

Authors: Daniel Kuhse, Harun Teper, Sebastian Buschj\\"ager, Chien-Yao Wang, Jian-Jia Chen

Published: 2025-03-21T19:16:38.000Z

## Abstract

We introduce AnytimeYOLO, a family of variants of the YOLO architecture that enables anytime object detection. Our AnytimeYOLO networks allow for interruptible inference, i.e., they provide a prediction at any point in time, a property desirable for safety-critical real-time applications.   We present structured explorations to modify the YOLO architecture, enabling early termination to obtain intermediate results. We focus on providing fine-grained control through high granularity of available termination points. First, we formalize Anytime Models as a special class of prediction models that offer anytime predictions. Then, we discuss a novel transposed variant of the YOLO architecture, that changes the architecture to enable better early predictions and greater freedom for the order of processing stages. Finally, we propose two optimization algorithms that, given an anytime model, can be used to determine the optimal exit execution order and the optimal subset of early-exits to select for deployment in low-resource environments. We evaluate the anytime performance and trade-offs of design choices, proposing a new anytime quality metric for this purpose. In particular, we also discuss key challenges for anytime inference that currently make its deployment costly.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2503.17497>)

[PDF](<https://arxiv.org/pdf/2503.17497.pdf>)
