计算机科学
卷积神经网络
人工智能
纹理(宇宙学)
范畴变量
模式识别(心理学)
纹理合成
参数统计
双线性插值
图像纹理
深度学习
图像(数学)
计算机视觉
机器学习
图像处理
数学
统计
作者
Tsung‐Yu Lin,Subhransu Maji
标识
DOI:10.1109/cvpr.2016.305
摘要
A number of recent approaches have used deep convolutional neural networks (CNNs) to build texture representations. Nevertheless, it is still unclear how these models represent texture and invariances to categorical variations. This work conducts a systematic evaluation of recent CNN-based texture descriptors for recognition and attempts to understand the nature of invariances captured by these representations. First we show that the recently proposed bilinear CNN model [25] is an excellent generalpurpose texture descriptor and compares favorably to other CNN-based descriptors on various texture and scene recognition benchmarks. The model is translationally invariant and obtains better accuracy on the ImageNet dataset without requiring spatial jittering of data compared to corresponding models trained with spatial jittering. Based on recent work [13, 28] we propose a technique to visualize pre-images, providing a means for understanding categorical properties that are captured by these representations. Finally, we show preliminary results on how a unified parametric model of texture analysis and synthesis can be used for attribute-based image manipulation, e.g. to make an image more swirly, honeycombed, or knitted. The source code and additional visualizations are available at http://vis-www.cs.umass.edu/texture.
科研通智能强力驱动
Strongly Powered by AbleSci AI