SmileLing的专栏

Girshick, Ross, et al. “[Rich feature hierarchies for accurate object detection and semantic segmentation.](../R-CNN (Rich feature hierarchies for accurate object detection and semantic segmentatio...

K. He, X. Zhang, S. Ren, and J. Sun. Spatial pyramid pooling in deep convolutional networks for visual recognition. In ECCV, 2014. Kaiming的这篇paper，是在R-CNN的基础上提出了空间金字塔变换层(Spatial Pyramid Pooling)...

Girshick, Ross. “Fast r-cnn.” Proceedings of the IEEE International Conference on Computer Vision. 2015.继2014年的RCNN, SPP-Net，Ross Girshick在15年推出Fast RCNN，构思精巧，流程更为紧凑，大幅提升了目标检测的速度。在Github上提供了源码。...

Ren, Shaoqing, et al. “Faster R-CNN: Towards real-time object detection with region proposal networks.” Advances in Neural Information Processing Systems. 2015.本文是继RCNN[1]，fast RCNN[2]之后，目标检测界的领...

Contrastive loss 最初源于 Yann LeCun “Dimensionality Reduction by Learning an Invariant Mapping” CVPR 2016。 该损失函数主要是用于降维中，即本来相似的样本，在经过降维（特征提取）后，在特征空间中，两个样本仍旧相似；而原本不相似的样本，在经过降维后，在特征空间中，两个样本仍旧不相似。同样，...