Search Results for author:
Found 9 papers, 3 papers with code
SE-MD: A Single-encoder multiple-decoder deep network for point cloud generation from 2D images
However, the body of research work is limited and there are various issues like using inefficient 3D representation formats, weak 3D model generation backbones, inability to generate dense point clouds, dependence of post-processing for generation of dense point clouds, and dependence on silhouettes in RGB images.
Attention mechanisms and deep learning for machine vision: A survey of the state of the art
Subsequently, the major categories of the intersection of attention mechanisms and deep learning for machine vision (MV) based are discussed.
Deep Q-Network Based Multi-agent Reinforcement Learning with Binary Action Agents
The learning is however specific to each agent and communication may be satisfactorily designed for the agents.
Deep Network Ensemble Learning applied to Image Classification using CNN Trees
The deep network used in the ensembles is ResNet50.
Image Classification by Reinforcement Learning with Two-State Q-Learning
Also, the proposed technique uses novel actions for processing images as compared to other techniques found in literature.
Digit Image Recognition Using an Ensemble of One-Versus-All Deep Network Classifiers
As shown in this paper, the classification capability of deep networks can be further increased by using an ensemble of binary classification (OVA) deep networks.
Reinforcement Learning Based Handwritten Digit Recognition with Two-State Q-Learning
Also, the approach uses unexplored actions for image processing vis-a-vis other contemporary techniques.
A Survey on Instance Segmentation: State of the art
Object detection or localization is an incremental step in progression from coarse to fine digital image inference.
Fast Training of Deep Networks with One-Class CNNs
For face recognition, a 1000 frame RGB video, featuring many faces together, has been used for benchmarking of the proposed approach.
