Why do deep convolutional networks generalize so poorly to small image transformations? Intro CNN的设计初衷是为了使得模型具有微小平移.旋转不变性,而实际上本文通过实验验证了现在比较流行的神经网络都已经丧失了这样的能力,甚至图像只水平移动一个像素,预测的结果都将会发生很大的变化.之所以如此,作者认为CNN的下采样背离了隆奎斯特采样定理,就连augmentation也并不能缓解微小变化不变性的丧失. I
Deep Attributes Driven Multi-Camera Person Re-identification 2017-06-28 21:38:55 [Motivation] 本文的网络设计主要分为三个部分: Stage 1: Fully-supervised dCNN training Stage 2: Fine-tuning using attributes triplet loss Stage 3:Final fine-tuning on the combined da
Deep Recurrent Q-Learning for Partially Observable MDPs 摘要:DQN 的两个缺陷,分别是:limited memory 和 rely on being able to perceive the complete game screen at each decision point. 为了解决这两个问题,本文尝试用 LSTM 单元 替换到后面的 fc layer,这样就产生了 Deep Recurrent Q-Network (DRQN),
Deep Metric Learning via Lifted Structured Feature Embedding CVPR 2016 摘要:本文提出一种距离度量的方法,充分的发挥 training batches 的优势,by lifting the vector of pairwise distances within the batch to the matrix of pairwise distances. 刚开始看这个摘要,有点懵逼,不怕,后面会知道这段英文是啥意思的. 引言部分