# AnyDepth-DETR/-YOLO: Any-depth object detection with a single network

Source: [AnyDepth-DETR/-YOLO: Any-depth object detection with a single network](<https://www.sota2.com/research/paper/6a02b467dbc836b87d824afd>)

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

Data updated: 2026-05-13T05:00:12.693Z

Authors: Woochul Kang, Hyungseop Lee, Jiho Lee

Published: 2026-05-10T08:12:18.000Z

## Abstract

Modern object detectors are static, fixed-depth networks optimized for a single operating point, requiring separate models for different deployment scenarios. We present an any-depth detection framework that enables a single network to span a continuous range of accuracy--efficiency trade-offs by controlling depth at inference time without retraining. Each backbone and neck stage is divided into an essential path, which always executes, and a skippable refinement path; this decomposition preserves the full multi-scale feature hierarchy at every depth configuration, unlike conventional early exiting that discards entire stages. To train such a network, jointly optimizing many sub-networks of varying depth introduces conflicting gradient signals. We address this via self-distillation between only the two extremes, with prediction-level and feature-level alignment losses that enforce stage-wise modularity, ensuring the outputs of each stage remain compatible regardless of the paths taken. Instantiated on RT-DETR and YOLOv12, our full-depth configurations match or surpass their respective SOTA baselines with negligible parameter overhead, while the most efficient configurations achieve up to $1.82\\times$ speedup at a cost of only 2.0 AP, all from a single set of weights.

## 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.

- [Object Detection on COCO 2017 (val)](<https://www.sota2.com/research/sota/object-detection-on-coco-2017-val.md>): Object Detection; COCO 2017 (val); AP: 55.5.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2605.09407>)

[PDF](<https://arxiv.org/pdf/2605.09407.pdf>)
