Increasing the Generalization of Supervised Fabric Anomaly Detection Methods to Unseen Fabrics

作者
Oliver Rippel,Corinna Zwinge,Dorit Merhof
出处
期刊:Sensors [Multidisciplinary Digital Publishing Institute]
卷期号:22 (13): 4750-4750 被引量:6
标识
DOI:10.3390/s22134750
摘要

Fabric anomaly detection (AD) tries to detect anomalies (i.e., defects) in fabrics, and fabric AD approaches are continuously improved with respect to their AD performance. However, developed solutions are known to generalize poorly to previously unseen fabrics, posing a crucial limitation to their applicability. Moreover, current research focuses on adapting converged models to previously unseen fabrics in a post hoc manner, rather than training models that generalize better in the first place. In our work, we explore this potential for the first time. Specifically, we propose that previously unseen fabrics can be regarded as shifts in the underlying data distribution. We therefore argue that factors which reportedly improve a model's resistance to distribution shifts should also improve the performance of supervised fabric AD methods on unseen fabrics. Hence, we assess the potential benefits of: (I) vicinal risk minimization (VRM) techniques adapted to the fabric AD use-case, (II) different loss functions, (III) ImageNet pre-training, (IV) dataset diversity, and (V) model architecture as well as model complexity. The subsequently performed large-scale analysis reveals that (I) only the VRM technique, AugMix, consistently improves performance on unseen fabrics; (II) hypersphere classifier outperforms other loss functions when combined with AugMix and (III) ImageNet pre-training, which is already beneficial on its own; (IV) increasing dataset diversity improves performance on unseen fabrics; and (V) architectures with better ImageNet performance also perform better on unseen fabrics, yet the same does not hold for more complex models. Notably, the results show that not all factors and techniques which reportedly improve a model's resistance to distribution shifts in natural images also improve the generalization of supervised fabric AD methods to unseen fabrics, demonstrating the necessity of our work. Additionally, we also assess whether the performance gains of models which generalize better propagate to post hoc adaptation methods and show this to be the case. Since no suitable fabric dataset was publicly available at the time of this work, we acquired our own fabric dataset, called OLP, as the basis for the above experiments. OLP consists of 38 complex, patterned fabrics, more than 6400 images in total, and is made publicly available.
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
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
Perrylin718完成签到,获得积分10
1秒前
MUAN完成签到 ,获得积分10
8秒前
mengmenglv完成签到 ,获得积分0
9秒前
光亮的幻桃完成签到,获得积分10
11秒前
等待的幼晴完成签到,获得积分10
14秒前
小白完成签到 ,获得积分10
15秒前
糖宝完成签到 ,获得积分0
17秒前
淡淡的志泽完成签到,获得积分10
18秒前
孤独宝马完成签到 ,获得积分10
18秒前
辰侑依完成签到 ,获得积分10
19秒前
Heaven完成签到 ,获得积分10
24秒前
WHW完成签到 ,获得积分10
25秒前
wanghao完成签到 ,获得积分10
26秒前
慧子发布了新的文献求助10
33秒前
俗人完成签到 ,获得积分10
36秒前
帅气的曼雁完成签到 ,获得积分10
38秒前
象象完成签到 ,获得积分10
38秒前
芍药完成签到 ,获得积分10
38秒前
LL路完成签到 ,获得积分10
40秒前
未来完成签到 ,获得积分10
46秒前
星宇完成签到 ,获得积分10
49秒前
星辰大海的应助被Brave采纳,获得10
50秒前
隐形期待完成签到,获得积分10
54秒前
陶醉静竹发布了新的文献求助10
55秒前
zhao完成签到,获得积分10
55秒前
小墨墨完成签到 ,获得积分10
58秒前
锂电说完成签到 ,获得积分10
1分钟前
1分钟前
独指蜗牛完成签到 ,获得积分10
1分钟前
Brave完成签到,获得积分10
1分钟前
maclogos完成签到,获得积分10
1分钟前
Brave发布了新的文献求助10
1分钟前
李希完成签到 ,获得积分10
1分钟前
阿俊1212完成签到 ,获得积分10
1分钟前
chenpy1990完成签到 ,获得积分10
1分钟前
科研菜鸡完成签到 ,获得积分10
1分钟前
佳言2009完成签到 ,获得积分10
1分钟前
小丽酱完成签到 ,获得积分10
1分钟前
zz6532完成签到 ,获得积分10
1分钟前
漂亮夏兰完成签到 ,获得积分10
1分钟前
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
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
John McDowells Bildungstheorie 800
Social Psychology in the Real World 600
八旗制度の研究 600
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8180068
求助须知:如何正确求助?哪些是违规求助? 9570224
关于积分的说明 21808724
捐赠科研通 7776054
什么是DOI,文献DOI怎么找? 3433261
关于科研通互助平台的介绍 2557425
邀请新用户注册赠送积分活动 2479012