Deploying convolutional neural networks (CNNs) on embedded devices is difficult due to the limited memory and computation resources. The redundancy in feature maps is an important characteristic of those successful CNNs, but has rarely been investigated in neural architecture design. This paper proposes a novel Ghost module to generate more feature maps from cheap operations. Based on a set of intrinsic feature maps, we apply a series of linear transformations with cheap cost to generate many ghost feature maps that could fully reveal information underlying intrinsic features.
2019: Kai Han, Yunhe Wang, Qi Tian, Jianyuan Guo, Chunjing Xu, Chang Xu
https://arxiv.org/pdf/1911.11907v2.pdf
Can Wikipedia Help Offline Reinforcement Learning?
Language-driven Semantic Segmentation
R-Drop: Regularized Dropout for Neural Networks
Black-Box Tuning for Language-Model-as-a-Service
Vision Transformer with Deformable Attention
Transfer Learning for Pose Estimation of Illustrated Characters
Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets
A ConvNet for the 2020s
Detecting Twenty-thousand Classes using Image-level Supervision
YOLOX: Exceeding YOLO Series in 2021
Scaling Deep Contrastive Learning Batch Size under Memory Limited Setup
Contrastive Fine-grained Class Clustering via Generative Adversarial Networks
A Transformer-Based Siamese Network for Change Detection
Lawin Transformer: Improving Semantic Segmentation Transformer with Multi-Scale Representations via Large Window Attention
R3LIVE: A Robust, Real-time, RGB-colored, LiDAR-Inertial-Visual tightly-coupled state Estimation and mapping package
Robust Self-Supervised Audio-Visual Speech Recognition
Rethinking Soft Labels for Knowledge Distillation: A Bias-Variance Tradeoff Perspective
Vision Transformer for Small-Size Datasets
JoJoGAN: One Shot Face Stylization
Diffusion Models Beat GANs on Image Synthesis
Join Podbean Ads Marketplace and connect with engaged listeners.
Advertise Today
Create your
podcast in
minutes
It is Free
Cyber Security Headlines
Cybersecurity Today
The WAN Show
Babbage from The Economist
The Know