xingruiyu

Co-teaching

NeurIPS'18: Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels

SIGUA

ICML'20: SIGUA: Forgetting May Make Learning with Noisy Labels More Robust

coteaching_plus

ICML'19 How does Disagreement Help Generalization against Label Corruption?

GIRIL

ICML'20: Intrinsic Reward Driven Imitation Learning via Generative Model

OilSeg-SGAN.tensorflow

Tensorflow implementation of the TGRS paper entitled Oil Spill Segmentation via Adversarial f-Divergence Learning.

pytorch-a2c-ppo-acktr-gail

PyTorch implementation of Advantage Actor Critic (A2C), Proximal Policy Optimization (PPO), Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation (ACKTR) and Generative Adversarial Imitation Learning (GAIL).

xingruiyu.github.io

xingruiyu/coteaching_plus

ICML'19 How does Disagreement Help Generalization against Label Corruption?

xingruiyu/GIRIL

ICML'20: Intrinsic Reward Driven Imitation Learning via Generative Model

xingruiyu/OilSeg-SGAN.tensorflow

Tensorflow implementation of the TGRS paper entitled Oil Spill Segmentation via Adversarial f-Divergence Learning.

xingruiyu/pytorch-a2c-ppo-acktr-gail

PyTorch implementation of Advantage Actor Critic (A2C), Proximal Policy Optimization (PPO), Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation (ACKTR) and Generative Adversarial Imitation Learning (GAIL).

xingruiyu/xingruiyu.github.io