Saved in:
Bibliographic Details
Main Authors: Shang, Chuyang, Ma, Tian, Ren, Wanzhu, Li, Yuancheng, Yang, Jiayi
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2403.19306
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915082565320704
author Shang, Chuyang
Ma, Tian
Ren, Wanzhu
Li, Yuancheng
Yang, Jiayi
author_facet Shang, Chuyang
Ma, Tian
Ren, Wanzhu
Li, Yuancheng
Yang, Jiayi
contents Existing pseudo label generation methods for point weakly supervised object detection are inadequate in low data volume and dense object detection tasks. We consider the generation of weakly supervised pseudo labels as the model's sparse output, and propose Sparse Generation as a solution to make pseudo labels sparse. The method employs three processing stages (Mapping, Mask, Regression), constructs dense tensors through the relationship between data and detector model, optimizes three of its parameters, and obtains a sparse tensor, thereby indirectly obtaining higher quality pseudo labels, and addresses the model's density problem on low data volume. Additionally, we propose perspective-based matching, which provides more rational pseudo boxes for prediction missed on instances. In comparison to the SOTA method, on four datasets (MS COCO-val, RSOD, SIMD, Bullet-Hole), the experimental results demonstrated a significant advantage.
format Preprint
id arxiv_https___arxiv_org_abs_2403_19306
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Sparse Generation: Making Pseudo Labels Sparse for Point Weakly Supervised Object Detection on Low Data Volume
Shang, Chuyang
Ma, Tian
Ren, Wanzhu
Li, Yuancheng
Yang, Jiayi
Computer Vision and Pattern Recognition
Existing pseudo label generation methods for point weakly supervised object detection are inadequate in low data volume and dense object detection tasks. We consider the generation of weakly supervised pseudo labels as the model's sparse output, and propose Sparse Generation as a solution to make pseudo labels sparse. The method employs three processing stages (Mapping, Mask, Regression), constructs dense tensors through the relationship between data and detector model, optimizes three of its parameters, and obtains a sparse tensor, thereby indirectly obtaining higher quality pseudo labels, and addresses the model's density problem on low data volume. Additionally, we propose perspective-based matching, which provides more rational pseudo boxes for prediction missed on instances. In comparison to the SOTA method, on four datasets (MS COCO-val, RSOD, SIMD, Bullet-Hole), the experimental results demonstrated a significant advantage.
title Sparse Generation: Making Pseudo Labels Sparse for Point Weakly Supervised Object Detection on Low Data Volume
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2403.19306