CVFeb 26, 2024

DEYO: DETR with YOLO for End-to-End Object Detection

arXiv:2402.16370v120 citationsh-index: 1Has Code
Originality Highly original
AI Analysis

This work addresses training challenges for real-time object detection in computer vision, offering a more efficient and stable approach that reduces computational costs.

The paper tackles the training inefficiencies and instability in DETR-based object detectors by introducing a step-by-step training method that initializes the model with a pre-trained YOLO detector, resulting in DEYO, a real-time end-to-end model that achieves state-of-the-art speed and accuracy on COCO without extra data.

The training paradigm of DETRs is heavily contingent upon pre-training their backbone on the ImageNet dataset. However, the limited supervisory signals provided by the image classification task and one-to-one matching strategy result in an inadequately pre-trained neck for DETRs. Additionally, the instability of matching in the early stages of training engenders inconsistencies in the optimization objectives of DETRs. To address these issues, we have devised an innovative training methodology termed step-by-step training. Specifically, in the first stage of training, we employ a classic detector, pre-trained with a one-to-many matching strategy, to initialize the backbone and neck of the end-to-end detector. In the second stage of training, we froze the backbone and neck of the end-to-end detector, necessitating the training of the decoder from scratch. Through the application of step-by-step training, we have introduced the first real-time end-to-end object detection model that utilizes a purely convolutional structure encoder, DETR with YOLO (DEYO). Without reliance on any supplementary training data, DEYO surpasses all existing real-time object detectors in both speed and accuracy. Moreover, the comprehensive DEYO series can complete its second-phase training on the COCO dataset using a single 8GB RTX 4060 GPU, significantly reducing the training expenditure. Source code and pre-trained models are available at https://github.com/ouyanghaodong/DEYO.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes