├── .gitignore ├── README.md ├── imgs └── MI2RL_logo.png └── reviews ├── 200803_BYOL.pdf ├── 200803_FickleNet. Weakly and Semi-supervised Semantic Image Segmentation using Stochastic Inference.pdf ├── 200810_Uncertainty-Aware Weakly Supervised Action Detection from Untrimmed Videos.pdf ├── 200810_What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?.pdf ├── 200831_Analyzing and Improving the Image Quality of StyleGAN.pdf ├── 200831_Dynamic Routing Between Capsules.pdf ├── 200907_A Closer look at Few-Shot Classification.pdf ├── 200907_DRIT.pdf ├── 200914_SIREN.pdf ├── 200914_Unsupervised Data Augmentation for Consistency Training.pdf ├── 200921_Lagging inference networks and posterior collapse in variational autoencoders.pdf ├── 200928_Probabilistic U-Net.pdf ├── 200928_RAFT.pdf ├── 201012_Big Transfer (BiT)_ General Visual Representation Learning.pdf ├── 201012_Regularizing Class-wise Predictions via Self-knowledge Distillation.pdf ├── 201012_VisionTransformer.pdf ├── 201019_Semi-Supervised StyleGAN for Disentanglement Learning.pdf ├── 201026_Learning Visual Context by Comparison.pdf ├── 201102_FixMatch. Simplifying Semi-Supervised Learning with Consistency and Confidence.pdf ├── 201109_REpresentation Learning via Invariant Causal mechanisms(RELIC).pdf ├── 201130_Do Wide and Deep Networks Learn the Same Things. Uncovering How Neural Network Representations Vary with Width and Depth.pdf ├── 211110_TransGAN.pdf ├── 211110_UNETR.pdf ├── 211124_Bert.pdf ├── 211215_Convit_20211215.pdf ├── 211215_GraphFPN.pdf ├── 220105_Towards Real-World Blind Face Restoration with Generative Facial Prior.pdf ├── 220105_Vision Transformers for Dense Prediction.pdf ├── 220112_FaceShifter.pdf ├── 220112_Florence_ A New Foundation Model for Computer Vision.pdf ├── 220126_CoAtNet_ Marrying Convolution and Attention for All Data Sizes_Zihang Dai, Hanxiao Liu, Quoc V. Le, Mingxing Tan Google Research, Brain Team (2021.06).pdf └── 220126_Instant Neural Graphics Primitives with a Multiresolution Hash Encoding.pdf /.gitignore: -------------------------------------------------------------------------------- 1 | *.DS_Store 2 | Thumbs.db* 3 | @eaDir/ -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mi2rl/MI2RL-PaperStudy/HEAD/README.md -------------------------------------------------------------------------------- /imgs/MI2RL_logo.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mi2rl/MI2RL-PaperStudy/HEAD/imgs/MI2RL_logo.png -------------------------------------------------------------------------------- /reviews/200803_BYOL.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mi2rl/MI2RL-PaperStudy/HEAD/reviews/200803_BYOL.pdf -------------------------------------------------------------------------------- /reviews/200803_FickleNet. Weakly and Semi-supervised Semantic Image Segmentation using Stochastic Inference.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mi2rl/MI2RL-PaperStudy/HEAD/reviews/200803_FickleNet. Weakly and Semi-supervised Semantic Image Segmentation using Stochastic Inference.pdf -------------------------------------------------------------------------------- /reviews/200810_Uncertainty-Aware Weakly Supervised Action Detection from Untrimmed Videos.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mi2rl/MI2RL-PaperStudy/HEAD/reviews/200810_Uncertainty-Aware Weakly Supervised Action Detection from Untrimmed Videos.pdf -------------------------------------------------------------------------------- /reviews/200810_What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mi2rl/MI2RL-PaperStudy/HEAD/reviews/200810_What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?.pdf -------------------------------------------------------------------------------- /reviews/200831_Analyzing and Improving the Image Quality of StyleGAN.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mi2rl/MI2RL-PaperStudy/HEAD/reviews/200831_Analyzing and Improving the Image Quality of StyleGAN.pdf -------------------------------------------------------------------------------- /reviews/200831_Dynamic Routing Between Capsules.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mi2rl/MI2RL-PaperStudy/HEAD/reviews/200831_Dynamic Routing Between Capsules.pdf -------------------------------------------------------------------------------- /reviews/200907_A Closer look at Few-Shot Classification.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mi2rl/MI2RL-PaperStudy/HEAD/reviews/200907_A Closer look at Few-Shot Classification.pdf -------------------------------------------------------------------------------- /reviews/200907_DRIT.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mi2rl/MI2RL-PaperStudy/HEAD/reviews/200907_DRIT.pdf -------------------------------------------------------------------------------- /reviews/200914_SIREN.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mi2rl/MI2RL-PaperStudy/HEAD/reviews/200914_SIREN.pdf -------------------------------------------------------------------------------- /reviews/200914_Unsupervised Data Augmentation for Consistency Training.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mi2rl/MI2RL-PaperStudy/HEAD/reviews/200914_Unsupervised Data Augmentation for Consistency Training.pdf -------------------------------------------------------------------------------- /reviews/200921_Lagging inference networks and posterior collapse in variational autoencoders.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mi2rl/MI2RL-PaperStudy/HEAD/reviews/200921_Lagging inference networks and posterior collapse in variational autoencoders.pdf -------------------------------------------------------------------------------- /reviews/200928_Probabilistic U-Net.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mi2rl/MI2RL-PaperStudy/HEAD/reviews/200928_Probabilistic U-Net.pdf -------------------------------------------------------------------------------- /reviews/200928_RAFT.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mi2rl/MI2RL-PaperStudy/HEAD/reviews/200928_RAFT.pdf -------------------------------------------------------------------------------- /reviews/201012_Big Transfer (BiT)_ General Visual Representation Learning.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mi2rl/MI2RL-PaperStudy/HEAD/reviews/201012_Big Transfer (BiT)_ General Visual Representation Learning.pdf -------------------------------------------------------------------------------- /reviews/201012_Regularizing Class-wise Predictions via Self-knowledge Distillation.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mi2rl/MI2RL-PaperStudy/HEAD/reviews/201012_Regularizing Class-wise Predictions via Self-knowledge Distillation.pdf -------------------------------------------------------------------------------- /reviews/201012_VisionTransformer.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mi2rl/MI2RL-PaperStudy/HEAD/reviews/201012_VisionTransformer.pdf -------------------------------------------------------------------------------- /reviews/201019_Semi-Supervised StyleGAN for Disentanglement Learning.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mi2rl/MI2RL-PaperStudy/HEAD/reviews/201019_Semi-Supervised StyleGAN for Disentanglement Learning.pdf -------------------------------------------------------------------------------- /reviews/201026_Learning Visual Context by Comparison.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mi2rl/MI2RL-PaperStudy/HEAD/reviews/201026_Learning Visual Context by Comparison.pdf -------------------------------------------------------------------------------- /reviews/201102_FixMatch. Simplifying Semi-Supervised Learning with Consistency and Confidence.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mi2rl/MI2RL-PaperStudy/HEAD/reviews/201102_FixMatch. Simplifying Semi-Supervised Learning with Consistency and Confidence.pdf -------------------------------------------------------------------------------- /reviews/201109_REpresentation Learning via Invariant Causal mechanisms(RELIC).pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mi2rl/MI2RL-PaperStudy/HEAD/reviews/201109_REpresentation Learning via Invariant Causal mechanisms(RELIC).pdf -------------------------------------------------------------------------------- /reviews/201130_Do Wide and Deep Networks Learn the Same Things. Uncovering How Neural Network Representations Vary with Width and Depth.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mi2rl/MI2RL-PaperStudy/HEAD/reviews/201130_Do Wide and Deep Networks Learn the Same Things. Uncovering How Neural Network Representations Vary with Width and Depth.pdf -------------------------------------------------------------------------------- /reviews/211110_TransGAN.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mi2rl/MI2RL-PaperStudy/HEAD/reviews/211110_TransGAN.pdf -------------------------------------------------------------------------------- /reviews/211110_UNETR.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mi2rl/MI2RL-PaperStudy/HEAD/reviews/211110_UNETR.pdf -------------------------------------------------------------------------------- /reviews/211124_Bert.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mi2rl/MI2RL-PaperStudy/HEAD/reviews/211124_Bert.pdf -------------------------------------------------------------------------------- /reviews/211215_Convit_20211215.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mi2rl/MI2RL-PaperStudy/HEAD/reviews/211215_Convit_20211215.pdf -------------------------------------------------------------------------------- /reviews/211215_GraphFPN.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mi2rl/MI2RL-PaperStudy/HEAD/reviews/211215_GraphFPN.pdf -------------------------------------------------------------------------------- /reviews/220105_Towards Real-World Blind Face Restoration with Generative Facial Prior.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mi2rl/MI2RL-PaperStudy/HEAD/reviews/220105_Towards Real-World Blind Face Restoration with Generative Facial Prior.pdf -------------------------------------------------------------------------------- /reviews/220105_Vision Transformers for Dense Prediction.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mi2rl/MI2RL-PaperStudy/HEAD/reviews/220105_Vision Transformers for Dense Prediction.pdf -------------------------------------------------------------------------------- /reviews/220112_FaceShifter.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mi2rl/MI2RL-PaperStudy/HEAD/reviews/220112_FaceShifter.pdf -------------------------------------------------------------------------------- /reviews/220112_Florence_ A New Foundation Model for Computer Vision.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mi2rl/MI2RL-PaperStudy/HEAD/reviews/220112_Florence_ A New Foundation Model for Computer Vision.pdf -------------------------------------------------------------------------------- /reviews/220126_CoAtNet_ Marrying Convolution and Attention for All Data Sizes_Zihang Dai, Hanxiao Liu, Quoc V. Le, Mingxing Tan Google Research, Brain Team (2021.06).pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mi2rl/MI2RL-PaperStudy/HEAD/reviews/220126_CoAtNet_ Marrying Convolution and Attention for All Data Sizes_Zihang Dai, Hanxiao Liu, Quoc V. Le, Mingxing Tan Google Research, Brain Team (2021.06).pdf -------------------------------------------------------------------------------- /reviews/220126_Instant Neural Graphics Primitives with a Multiresolution Hash Encoding.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mi2rl/MI2RL-PaperStudy/HEAD/reviews/220126_Instant Neural Graphics Primitives with a Multiresolution Hash Encoding.pdf --------------------------------------------------------------------------------