From Global to Local: Multi-Scale Out-of-Distribution Detection

判别式 计算机科学 成对比较 人工智能 模式识别(心理学) 代表(政治) 杂乱 机器学习 电信 雷达 政治 政治学 法学
作者
Ji Zhang,Lianli Gao,Bingguang Hao,Hao Huang,Jingkuan Song,Heng Tao Shen
出处
期刊:IEEE transactions on image processing [Institute of Electrical and Electronics Engineers]
卷期号:32: 6115-6128 被引量:10
标识
DOI:10.1109/tip.2023.3328478
摘要

Out-of-distribution (OOD) detection aims to detect "unknown" data whose labels have not been seen during the in-distribution (ID) training process. Recent progress in representation learning gives rise to distance-based OOD detection that recognizes inputs as ID/OOD according to their relative distances to the training data of ID classes. Previous approaches calculate pairwise distances relying only on global image representations, which can be sub-optimal as the inevitable background clutter and intra-class variation may drive image-level representations from the same ID class far apart in a given representation space. In this work, we overcome this challenge by proposing Multi-scale OOD DEtection (MODE), a first framework leveraging both global visual information and local region details of images to maximally benefit OOD detection. Specifically, we first find that existing models pretrained by off-the-shelf cross-entropy or contrastive losses are incompetent to capture valuable local representations for MODE, due to the scale-discrepancy between the ID training and OOD detection processes. To mitigate this issue and encourage locally discriminative representations in ID training, we propose Attention-based Local PropAgation (ALPA), a trainable objective that exploits a cross-attention mechanism to align and highlight the local regions of the target objects for pairwise examples. During test-time OOD detection, a Cross-Scale Decision (CSD) function is further devised on the most discriminative multi-scale representations to distinguish ID/OOD data more faithfully. We demonstrate the effectiveness and flexibility of MODE on several benchmarks - on average, MODE outperforms the previous state-of-the-art by up to 19.24% in FPR, 2.77% in AUROC. Code is available at https://github.com/JimZAI/MODE-OOD.
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
大幅提高文件上传限制,最高150M (2024-4-1)

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
tuanheqi应助wellforever采纳,获得200
1秒前
1秒前
sunrase发布了新的文献求助10
2秒前
永远少年完成签到,获得积分10
3秒前
周芷卉发布了新的文献求助10
4秒前
6秒前
6秒前
Revovler完成签到,获得积分10
7秒前
枫叶完成签到,获得积分20
8秒前
LMY发布了新的文献求助30
8秒前
CipherSage应助Dd采纳,获得10
8秒前
大大小小发布了新的文献求助10
9秒前
小马甲应助weirdo采纳,获得10
9秒前
小二郎应助dear采纳,获得10
9秒前
10秒前
研友_VZG7GZ应助小田采纳,获得10
10秒前
khurram发布了新的文献求助10
11秒前
Songs完成签到,获得积分10
11秒前
斯文败类应助安详的书本采纳,获得10
13秒前
Lucas应助大大小小采纳,获得10
14秒前
deng完成签到 ,获得积分10
15秒前
15秒前
是莉莉娅完成签到,获得积分10
16秒前
顺心醉蝶完成签到,获得积分10
17秒前
18秒前
18秒前
胡桃夹馍发布了新的文献求助10
19秒前
Draeck发布了新的文献求助10
21秒前
22秒前
23秒前
123发布了新的文献求助10
23秒前
23秒前
robert3324完成签到,获得积分10
26秒前
27秒前
27秒前
王肖完成签到,获得积分10
27秒前
钧钧发布了新的文献求助10
28秒前
Aaaaaa瘾发布了新的文献求助10
28秒前
Jasper应助GU采纳,获得10
28秒前
28秒前
高分求助中
Sustainability in Tides Chemistry 2800
Kinetics of the Esterification Between 2-[(4-hydroxybutoxy)carbonyl] Benzoic Acid with 1,4-Butanediol: Tetrabutyl Orthotitanate as Catalyst 1000
The Young builders of New china : the visit of the delegation of the WFDY to the Chinese People's Republic 1000
Rechtsphilosophie 1000
Very-high-order BVD Schemes Using β-variable THINC Method 568
Chen Hansheng: China’s Last Romantic Revolutionary 500
Mantiden: Faszinierende Lauerjäger Faszinierende Lauerjäger 500
热门求助领域 (近24小时)
化学 医学 生物 材料科学 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 基因 遗传学 催化作用 物理化学 免疫学 量子力学 细胞生物学
热门帖子
关注 科研通微信公众号,转发送积分 3138933
求助须知:如何正确求助?哪些是违规求助? 2789871
关于积分的说明 7793019
捐赠科研通 2446289
什么是DOI,文献DOI怎么找? 1301004
科研通“疑难数据库(出版商)”最低求助积分说明 626087
版权声明 601096