DEYO: DETR with YOLO for Step-by-Step Object Detection

11/12/2022
by   Haodong Ouyang, et al.
0

Object detection is an important topic in computer vision, with post-processing, an essential part of the typical object detection pipeline, posing a significant bottleneck affecting the performance of traditional object detection models. The detection transformer (DETR), as the first end-to-end target detection model, discards the requirement of manual components like the anchor and non-maximum suppression (NMS), significantly simplifying the target detection process. However, compared with most traditional object detection models, DETR converges very slowly, and a query's meaning is obscure. Thus, inspired by the Step-by-Step concept, this paper proposes a new two-stage object detection model, named DETR with YOLO (DEYO), which relies on a progressive inference to solve the above problems. DEYO is a two-stage architecture comprising a classic target detection model and a DETR-like model as the first and second stages, respectively. Specifically, the first stage provides high-quality query and anchor feeding into the second stage, improving the performance and efficiency of the second stage compared to the original DETR model. Meanwhile, the second stage compensates for the performance degradation caused by the first stage detector's limitations. Extensive experiments demonstrate that DEYO attains 50.6 AP and 52.1 AP in 12 and 36 epochs, respectively, while utilizing ResNet-50 as the backbone and multi-scale features on the COCO dataset. Compared with DINO, an optimal DETR-like model, the developed DEYO model affords a significant performance improvement of 1.6 AP and 1.2 AP in two epoch settings.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/15/2023

DEYOv2: Rank Feature with Greedy Matching for End-to-End Object Detection

This paper presents a novel object detector called DEYOv2, an improved v...
research
01/19/2019

Consistent Optimization for Single-Shot Object Detection

We present consistent optimization for single stage object detection. Pr...
research
04/01/2021

Anchor Pruning for Object Detection

This paper proposes anchor pruning for object detection in one-stage anc...
research
12/26/2021

AlertTrap: A study on object detection in remote insects trap monitoring system using on-the-edge deep learning platform

Fruit flies are one of the most harmful insect species to fruit yields. ...
research
10/21/2022

Automatic Cattle Identification using YOLOv5 and Mosaic Augmentation: A Comparative Analysis

You Only Look Once (YOLO) is a single-stage object detection model popul...
research
05/28/2021

Augmenting Anchors by the Detector Itself

It is difficult to determine the scale and aspect ratio of anchors for a...
research
01/19/2021

An Improvement of Object Detection Performance using Multi-step Machine Learnings

Connecting multiple machine learning models into a pipeline is effective...

Please sign up or login with your details

Forgot password? Click here to reset