发简信
IP属地：安徽
-
Incremental network quantizationApproach We present INQ which incorporates three interdependent operatio...
-
Paying more attention to attentionApproach By properly defining attention for convolutional neural network...
-
Recurrent-Attention-CNN简介 细粒度分类问题通常是很困难的，这是因为判别区域定位和细粒度特征学习是很具有挑战性的。现有方法常常忽略了区域检测和细粒度特征学习之间的相互关...
-
目标检测之SSDSSD的网络分为两部分，前半部分是用于图像分类的标准网络（去掉了分类相关的层），后面的网络是用于检测的多尺度特征映射层，从而达到检测不同大小的目...
-
Knowledge Distill via NSTApproach Knowledge Transfer (KT), which aims at training a smaller stude...
-
Channel Pruning for Accelerating DNN
Approach Given a trained CNN model, we propose an iterative two-step alg...
-
Speeding-up CNN using CP-Decomposition
Approach We propose a simple two-step approach for speeding up convoluti...
-
Deep CompressionApproach We introduce “deep compression”, a three stage pipeline: prunin...
-
Ternary weight networks
Approach We introduce ternary weight networks (TWNs) - neural networks w...