-
Harmonic Decompositions of Convolutional Networks
The dataset used in this paper is a collection of images of faces, each with a different expression. -
Going Deeper with Convolutions
The dataset used for training and testing the proposed method. -
Re-parameterization Operations Search for Easy-to-Deploy Network
Structural re-parameterization technology provides a new idea to improve the performance of traditional convolutional networks. -
Very Deep Convolutional Networks for Large-Scale Image Recognition
The dataset consists of 60,000 images of objects in 200 categories, with 300 images per category. -
High Performance Visual Object Tracking with Unified Convolutional Networks
Visual object tracking is a fundamental problem in many aspects such as visual analysis, automatic driving, pose tracking, robotics, and more. -
PointConv: Deep Convolutional Networks on 3D Point Clouds
3D point clouds are irregular and unordered, hence applying convolution on them can be difficult. PointConv can be applied on point clouds to build deep convolutional networks. -
Path of Destruction
The Path of Destruction method generates a large artificial dataset by iteratively destroying levels and creating a dataset of repair actions. -
Convolutional Networks with Adaptive Inference Graphs
ConvNet-AIG is a convolutional network that adaptsively defines its network topology conditioned on the input image.
