Domain Adaptive Object Detection via Balancing Between Self-Training and Adversarial Learning

计算机科学 人工智能 最小边界框 杠杆(统计) 对抗制 目标检测 边距(机器学习) 跳跃式监视 特征(语言学) 模式识别(心理学) 机器学习 领域(数学分析) 背景(考古学) 班级(哲学) 计算机视觉 图像(数学) 数学 古生物学 哲学 数学分析 生物 语言学
作者
Muhammad Akhtar Munir,Muhammad Haris Khan,M. Saquib Sarfraz,Mohsen Ali
出处
期刊:IEEE Transactions on Pattern Analysis and Machine Intelligence [Institute of Electrical and Electronics Engineers]
卷期号:45 (12): 14353-14365 被引量:1
标识
DOI:10.1109/tpami.2023.3290135
摘要

Deep learning based object detectors struggle generalizing to a new target domain bearing significant variations in object and background. Most current methods align domains by using image or instance-level adversarial feature alignment. This often suffers due to unwanted background and lacks class-specific alignment. A straightforward approach to promote class-level alignment is to use high confidence predictions on unlabeled domain as pseudo-labels. These predictions are often noisy since model is poorly calibrated under domain shift. In this paper, we propose to leverage model's predictive uncertainty to strike the right balance between adversarial feature alignment and class-level alignment. We develop a technique to quantify predictive uncertainty on class assignments and bounding-box predictions. Model predictions with low uncertainty are used to generate pseudo-labels for self-training, whereas the ones with higher uncertainty are used to generate tiles for adversarial feature alignment. This synergy between tiling around uncertain object regions and generating pseudo-labels from highly certain object regions allows capturing both image and instance-level context during the model adaptation. We report thorough ablation study to reveal the impact of different components in our approach. Results on five diverse and challenging adaptation scenarios show that our approach outperforms existing state-of-the-art methods with noticeable margins.

科研通智能强力驱动
Strongly Powered by AbleSci AI
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
hetty完成签到,获得积分10
刚刚
zhonglv7应助科研通管家采纳,获得10
刚刚
杨杨应助科研通管家采纳,获得10
刚刚
墨琼琼应助科研通管家采纳,获得10
刚刚
酷波er应助科研通管家采纳,获得10
刚刚
刚刚
科目三应助lmr采纳,获得10
刚刚
刚刚
情怀应助科研通管家采纳,获得10
1秒前
1秒前
深情安青应助科研通管家采纳,获得10
1秒前
爆米花应助科研通管家采纳,获得10
1秒前
量子星尘发布了新的文献求助10
1秒前
小蘑菇应助科研通管家采纳,获得10
1秒前
科研通AI2S应助科研通管家采纳,获得10
1秒前
1秒前
成就的咖啡完成签到,获得积分10
1秒前
1秒前
1秒前
在水一方应助科研通管家采纳,获得10
2秒前
情怀应助科研通管家采纳,获得10
2秒前
2秒前
科研通AI6应助科研通管家采纳,获得10
2秒前
2秒前
2秒前
深情安青应助科研通管家采纳,获得30
2秒前
2秒前
HLS应助科研通管家采纳,获得10
3秒前
zhonglv7应助科研通管家采纳,获得10
3秒前
lizishu应助1212采纳,获得20
3秒前
杨杨应助科研通管家采纳,获得10
3秒前
天天快乐应助科研通管家采纳,获得10
3秒前
墨琼琼应助科研通管家采纳,获得10
3秒前
俏皮晓曼完成签到,获得积分10
3秒前
酷波er应助科研通管家采纳,获得10
3秒前
3秒前
3秒前
3秒前
情怀应助科研通管家采纳,获得10
3秒前
在水一方应助科研通管家采纳,获得10
3秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
Encyclopedia of Forensic and Legal Medicine Third Edition 5000
Introduction to strong mixing conditions volume 1-3 5000
Aerospace Engineering Education During the First Century of Flight 3000
Agyptische Geschichte der 21.30. Dynastie 3000
Les Mantodea de guyane 2000
从k到英国情人 1700
热门求助领域 (近24小时)
化学 材料科学 生物 医学 工程类 计算机科学 有机化学 物理 生物化学 纳米技术 复合材料 内科学 化学工程 人工智能 催化作用 遗传学 数学 基因 量子力学 物理化学
热门帖子
关注 科研通微信公众号,转发送积分 5776350
求助须知:如何正确求助?哪些是违规求助? 5628713
关于积分的说明 15442059
捐赠科研通 4908468
什么是DOI,文献DOI怎么找? 2641217
邀请新用户注册赠送积分活动 1589167
关于科研通互助平台的介绍 1543851