本文介绍了使用 Places 数据集进行场景识别的深度学习研究。 Places 数据集具有高密度和多样性，与 ImageNet 相比更注重场景多样性。通过 AlexNet 训练在两个数据集上，发现在深层特征中，Places-CNN 更倾向于捕捉场景的结构，而 ImageNet-CNN 则聚焦于对象。实验表明，Places-CNN 特征在场景分类任务上超越了当前最佳方法，而 ImageNet-CNN 在对象相关任务上表现更好。结合两个数据集训练的 Hybrid-CNN 在某些基准测试中提升性能，但并非全部。
Zhou, Bolei, et al. “Learning deep features for scene recognition using places database.” Advances in neural information processing systems. 2014.
• Places205: 5k images, 205 place categories.
• Places88: 88 common categories also contained in ImageNet.
1 Places Dataset
7M images, 476 place categories.• Places205: 5k images, 205 place categories.
• Places88: 88 common categories also contained in ImageNet.
2 Density and Diversity
[Density] A good datase should have a high degree of data concentration. Given two databases A and B, let a 1 be a random image from set A and b 1 from set B. Let us take their respective nearest neighbors (computed by Gist descriptor) in each set, a 2 from A and b 2 from B. If A is denser than B, then it would be more likely that a 1 and a 2 are closer to each other than b 1 and b 2 .
[Diversity] A good datase should also have a high variability of appearances and viewpoints. If set A is more diverse than set B, then two random images from set B are more li
最低0.47元/天 解锁文章
6210
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
