Search Results for author:
Found 18 papers, 3 papers with code
Multiagent Bidirectionally-Coordinated Nets: Emergence of Human-level Coordination in Learning to Play StarCraft Combat Games
Many artificial intelligence (AI) applications often require multiple intelligent agents to work in a collaborative effort.
Continual Match Based Training in Pommerman: Technical Report
We show in the experiments that Pommerman is a perfect environment for studying continual learning, and the agent can improve its performance by continually learning new skills without forgetting the old ones.
Artificial Intelligence for Prosthetics - challenge solutions
In the NeurIPS 2018 Artificial Intelligence for Prosthetics challenge, participants were tasked with building a controller for a musculoskeletal model with a goal of matching a given time-varying velocity vector.
Ferrograph image classification
For the problem of insufficient samples, we first proposed a data augmentation algorithm based on the permutation of image patches.
Segmentation overlapping wear particles with few labelled data and imbalance sample
The region segmentation network is an improved U shape network, and it is applied to separate the wear debris form background of ferrograph image.
A Unified Structure for Efficient RGB and RGB-D Salient Object Detection
The proposed structure is simple yet effective; the rich context information of RGB and depth can be appropriately extracted and fused by the proposed structure efficiently.
How to fine-tune deep neural networks in few-shot learning?
Fine-tuning of a deep model is simple and effective few-shot learning method.
SCC: an efficient deep reinforcement learning agent mastering the game of StarCraft II
In this paper, we will share the key insights and optimizations on efficient imitation learning and reinforcement learning for StarCraft II full game.
Thermal Infrared Image Colorization for Nighttime Driving Scenes with Top-Down Guided Attention
Furthermore, a new metric is devised to evaluate the geometric consistency in the translation process.
Learning Generalized Visual Odometry Using Position-Aware Optical Flow and Geometric Bundle Adjustment
The experiments show that the proposed system not only achieves comparable performance with other state-of-the-art self-supervised learning-based methods on the KITTI dataset, but also significantly improves the generalization capability compared with geometry-based, learning-based and hybrid VO systems on the noisy KITTI and the challenging outdoor (KAIST) scenes.
Evolutionary Game-Theoretical Analysis for General Multiplayer Asymmetric Games
First, there is inaccuracy when analysing the simplified payoff table.
Supervised Contrastive Learning with Tree-Structured Parzen Estimator Bayesian Optimization for Imbalanced Tabular Data
To solve this problem, we propose a Supervised Contrastive Learning (SCL) method with Tree-structured Parzen Estimator (TPE) technique for imbalanced tabular datasets.
UnICLAM:Contrastive Representation Learning with Adversarial Masking for Unified and Interpretable Medical Vision Question Answering
Moreover, for grasping the unified semantic representation, we extend the adversarial masking data augmentation to the contrastive representation learning of vision and text in a unified manner.
SCCAM: Supervised Contrastive Convolutional Attention Mechanism for Ante-hoc Interpretable Fault Diagnosis with Limited Fault Samples
The comprehensive results demonstrate that the proposed SCCAM method can achieve better performance compared with the state-of-the-art methods on fault classification and root cause analysis.
SCLIFD:Supervised Contrastive Knowledge Distillation for Incremental Fault Diagnosis under Limited Fault Data
Finally, the model decision is biased toward the new classes due to the class imbalance.
An Order-Invariant and Interpretable Hierarchical Dilated Convolution Neural Network for Chemical Fault Detection and Diagnosis
The novelty of HDLCNN lies in its capability of processing tabular data with features of arbitrary order without seeking the optimal order, due to the ability to agglomerate correlated features of feature clustering and the large receptive field of dilated convolution.
Hard Sample Mining Enabled Supervised Contrastive Feature Learning for Wind Turbine Pitch System Fault Diagnosis
The proposed method employs cosine similarity to identify hard samples and subsequently, leverages supervised contrastive learning to learn more discriminative representations by constructing hard sample pairs.
Internal Contrastive Learning for Generalized Out-of-distribution Fault Diagnosis (GOOFD) Framework
Additionally, a unified fault diagnosis method based on internal contrastive learning is put forward to underpin the proposed generalized framework.
