[Noisy Label] Robust Inference via Generative Classifiers for Handling Noisy Labels, ICML 2019

IT/Paper

성진팍 2021. 3. 4. 21:19

Robust Inference via Generative Classifiers for Handling Noisy Labels

직접 회사 프로젝트에도 적용해보았던 방법론.

To be updated.

[Optimization] LOOK AHEAD OPTIMIZER: K STEPS FORWARD, 1 STEP BACK, NeurIPS 2019 (0)	2021.03.06
[Optimization] SGDR: STOCHASTIC GRADIENT DESCENT WITH WARM RESTARTS, ICLR 2017 (0)	2021.03.06
[RL] Regularizing Trajectory Optimization with Denoising Autoencoders, NeurIPS 2019 (0)	2021.03.04
[RL] Never Give Up: Learning Directed Exploration Strategies, ICML 2020 (0)	2021.03.04
[XAI] Fooling Neural Network Interpretations via Adversarial Model Manipulation, NeurIPS 2019 (0)	2021.03.04

현재글[Noisy Label] Robust Inference via Generative Classifiers for Handling Noisy Labels, ICML 2019

jin's blog

Endure

R-CNN, CAV, Adversarial Examples Are Not Bugs, Interpretability Beyond Feature Attribution:Quantitative Testing with Concept Activation Vectors, Axiomatic Attribution for Deep Networks, intergrated gradient, Learning Directed Exploration Strategies, Quantifying Attention Flow in Transformers, XAI, They Are Features, smoothGrad, Concept vector, vision transformer, Deconvolution Network, Regularizing Trajectory Optimization with Denoising Autoencoders, Paper리뷰, RL논문, Fast R-CNN, TCAV, Never Give Up,

jin's blog