arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2209.04861cs.CV
收藏

逆图像频率用于长尾图像识别

Inverse Image Frequency for Long-tailed Image Recognition

University of Liverpool(利物浦大学);Imperial College London(帝国理工学院)

Konstantinos Panagiotis Alexandridis, Shan Luo, Anh Nguyen, Jiankang Deng, Stefanos Zafeiriou

AI总结:

针对长尾图像识别中的类别不平衡问题,提出逆图像频率(IIF)方法,通过对分类层logits进行乘法边际调整来去偏,在多个长尾基准上达到最先进性能。

摘要:

长尾分布是现实世界中的常见现象。提取的大规模图像数据集不可避免地表现出长尾特性,而在不平衡数据上训练的模型对过度表示的类别可以获得高性能,但对欠表示的类别却难以应对,导致预测偏差和性能下降。为了解决这一挑战,我们提出了一种新颖的去偏方法,名为逆图像频率(IIF)。IIF是卷积神经网络分类层中logits的乘法边际调整变换。我们的方法比类似工作取得了更强的性能,并且对于长尾实例分割等下游任务特别有用,因为它产生更少的假阳性检测。我们的大量实验表明,IIF在ImageNet-LT、CIFAR-LT、Places-LT和LVIS等许多长尾基准上超越了最先进水平,在ImageNet-LT上使用ResNet50达到55.8%的top-1准确率,在LVIS上使用MaskRCNN达到26.2%的分割AP。代码可在https://github.com/kostas1515/iif获取。

英文摘要:

The long-tailed distribution is a common phenomenon in the real world. Extracted large scale image datasets inevitably demonstrate the long-tailed property and models trained with imbalanced data can obtain high performance for the over-represented categories, but struggle for the under-represented categories, leading to biased predictions and performance degradation. To address this challenge, we propose a novel de-biasing method named Inverse Image Frequency (IIF). IIF is a multiplicative margin adjustment transformation of the logits in the classification layer of a convolutional neural network. Our method achieves stronger performance than similar works and it is especially useful for downstream tasks such as long-tailed instance segmentation as it produces fewer false positive detections. Our extensive experiments show that IIF surpasses the state of the art on many long-tailed benchmarks such as ImageNet-LT, CIFAR-LT, Places-LT and LVIS, reaching 55.8% top-1 accuracy with ResNet50 on ImageNet-LT and 26.2% segmentation AP with MaskRCNN on LVIS. Code available at https://github.com/kostas1515/iif

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑