# DATE: Dual Assignment for End-to-End Fully Convolutional Object Detection

Source: [DATE: Dual Assignment for End-to-End Fully Convolutional Object Detection](<https://www.sota2.com/research/paper/68fa6e481e209131cea3ef8d>)

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

Data updated: 2025-10-27T06:19:28.634Z

Authors: Yiqun Chen, Qiang Chen, Qinghao Hu, Jian Cheng

Published: 2022-11-25T02:12:57.000Z

## Abstract

Fully convolutional detectors discard the one-to-many assignment and adopt a one-to-one assigning strategy to achieve end-to-end detection but suffer from the slow convergence issue. In this paper, we revisit these two assignment methods and find that bringing one-to-many assignment back to end-to-end fully convolutional detectors helps with model convergence. Based on this observation, we propose {\\em \\textbf{D}ual \\textbf{A}ssignment} for end-to-end fully convolutional de\\textbf{TE}ction (DATE). Our method constructs two branches with one-to-many and one-to-one assignment during training and speeds up the convergence of the one-to-one assignment branch by providing more supervision signals. DATE only uses the branch with the one-to-one matching strategy for model inference, which doesn't bring inference overhead. Experimental results show that Dual Assignment gives nontrivial improvements and speeds up model convergence upon OneNet and DeFCN. Code: https://github.com/YiqunChen1999/date.

## 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/2211.13859>)

[PDF](<https://arxiv.org/pdf/2211.13859.pdf>)
