AO2-DETR: Arbitrary-Oriented Object Detection Transformer

计算机科学 目标检测 变压器 联营 人工智能 不变(物理) 计算机视觉 模式识别(心理学) 电压 数学 数学物理 量子力学 物理
作者
Linhui Dai,Hong Liu,Hao Tang,Zhiwei Wu,Pinhao Song
出处
期刊:IEEE Transactions on Circuits and Systems for Video Technology [Institute of Electrical and Electronics Engineers]
卷期号:33 (5): 2342-2356 被引量:116
标识
DOI:10.1109/tcsvt.2022.3222906
摘要

Arbitrary-oriented object detection (AOOD) is a challenging task to detect objects in the wild with arbitrary orientations and cluttered arrangements. Existing approaches are mainly based on anchor-based boxes or dense points, which rely on complicated hand-designed processing steps and inductive bias, such as anchor generation, transformation, and non-maximum suppression reasoning. Recently, the emerging transformer-based approaches view object detection as a direct set prediction problem that effectively removes the need for hand-designed components and inductive biases. In this paper, we propose an Arbitrary-Oriented Object DEtection TRansformer framework, termed AO2-DETR, which comprises three dedicated components. More precisely, an oriented proposal generation mechanism is proposed to explicitly generate oriented proposals, which provides better positional priors for pooling features to modulate the cross-attention in the transformer decoder. An adaptive oriented proposal refinement module is introduced to extract rotation-invariant region features and eliminate the misalignment between region features and objects. And a rotation-aware set matching loss is used to ensure the one-to-one matching process for direct set prediction without duplicate predictions. Our method considerably simplifies the overall pipeline and presents a new AOOD paradigm. Comprehensive experiments on several challenging datasets show that our method achieves superior performance on the AOOD task.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
所所应助孤独士晋采纳,获得10
刚刚
1秒前
echo发布了新的文献求助20
2秒前
4秒前
Victoria发布了新的文献求助10
4秒前
多情含灵发布了新的文献求助10
5秒前
慕青应助JackeyChen采纳,获得10
6秒前
小马甲应助忧虑的冰姬采纳,获得10
6秒前
6秒前
烟花应助123采纳,获得10
7秒前
cc完成签到,获得积分20
7秒前
7秒前
8秒前
AZUSA完成签到,获得积分20
9秒前
9秒前
在水一方应助猪猪院长采纳,获得10
9秒前
10秒前
朴素烧鹅发布了新的文献求助10
10秒前
superbada完成签到,获得积分10
11秒前
nanween完成签到,获得积分10
11秒前
zhaoyy发布了新的文献求助10
11秒前
11秒前
chang发布了新的文献求助10
13秒前
13秒前
13秒前
hhhi应助虚幻靖易采纳,获得10
14秒前
丘比特应助老武采纳,获得10
14秒前
15秒前
科目三应助frl采纳,获得10
15秒前
cookie完成签到,获得积分10
15秒前
畅快的天空完成签到,获得积分10
17秒前
bbanshan完成签到,获得积分10
17秒前
四时万物兮完成签到,获得积分10
18秒前
Orange应助yshhhhhhhh采纳,获得10
19秒前
隐形曼青应助哈哈哈哈哈采纳,获得10
20秒前
21秒前
Victoria发布了新的文献求助10
22秒前
22秒前
FancyShi发布了新的文献求助30
23秒前
小牧鱼完成签到,获得积分10
23秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
‘Unruly’ Children: Historical Fieldnotes and Learning Morality in a Taiwan Village (New Departures in Anthropology) 400
Indomethacinのヒトにおける経皮吸収 400
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 370
基于可调谐半导体激光吸收光谱技术泄漏气体检测系统的研究 350
Robot-supported joining of reinforcement textiles with one-sided sewing heads 320
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3988646
求助须知:如何正确求助?哪些是违规求助? 3531027
关于积分的说明 11252059
捐赠科研通 3269632
什么是DOI,文献DOI怎么找? 1804713
邀请新用户注册赠送积分活动 881865
科研通“疑难数据库(出版商)”最低求助积分说明 809012