Saved in:
Bibliographic Details
Main Authors: Tsui, Hao-Tang, Wang, Chien-Yao, Liao, Hong-Yuan Mark
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2410.15346
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916603974647808
author Tsui, Hao-Tang
Wang, Chien-Yao
Liao, Hong-Yuan Mark
author_facet Tsui, Hao-Tang
Wang, Chien-Yao
Liao, Hong-Yuan Mark
contents Identifying and localizing objects within images is a fundamental challenge, and numerous efforts have been made to enhance model accuracy by experimenting with diverse architectures and refining training strategies. Nevertheless, a prevalent limitation in existing models is overemphasizing the current input while ignoring the information from the entire dataset. We introduce an innovative Retriever-Dictionary (RD) module to address this issue. This architecture enables YOLO-based models to efficiently retrieve features from a Dictionary that contains the insight of the dataset, which is built by the knowledge from Visual Models (VM), Large Language Models (LLM), or Visual Language Models (VLM). The flexible RD enables the model to incorporate such explicit knowledge that enhances the ability to benefit multiple tasks, specifically, segmentation, detection, and classification, from pixel to image level. The experiments show that using the RD significantly improves model performance, achieving more than a 3\% increase in mean Average Precision for object detection with less than a 1% increase in model parameters. Beyond 1-stage object detection models, the RD module improves the effectiveness of 2-stage models and DETR-based architectures, such as Faster R-CNN and Deformable DETR. Code is released at https://github.com/henrytsui000/YOLO.
format Preprint
id arxiv_https___arxiv_org_abs_2410_15346
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle YOLO-RD: Introducing Relevant and Compact Explicit Knowledge to YOLO by Retriever-Dictionary
Tsui, Hao-Tang
Wang, Chien-Yao
Liao, Hong-Yuan Mark
Computer Vision and Pattern Recognition
Artificial Intelligence
Identifying and localizing objects within images is a fundamental challenge, and numerous efforts have been made to enhance model accuracy by experimenting with diverse architectures and refining training strategies. Nevertheless, a prevalent limitation in existing models is overemphasizing the current input while ignoring the information from the entire dataset. We introduce an innovative Retriever-Dictionary (RD) module to address this issue. This architecture enables YOLO-based models to efficiently retrieve features from a Dictionary that contains the insight of the dataset, which is built by the knowledge from Visual Models (VM), Large Language Models (LLM), or Visual Language Models (VLM). The flexible RD enables the model to incorporate such explicit knowledge that enhances the ability to benefit multiple tasks, specifically, segmentation, detection, and classification, from pixel to image level. The experiments show that using the RD significantly improves model performance, achieving more than a 3\% increase in mean Average Precision for object detection with less than a 1% increase in model parameters. Beyond 1-stage object detection models, the RD module improves the effectiveness of 2-stage models and DETR-based architectures, such as Faster R-CNN and Deformable DETR. Code is released at https://github.com/henrytsui000/YOLO.
title YOLO-RD: Introducing Relevant and Compact Explicit Knowledge to YOLO by Retriever-Dictionary
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2410.15346