Inspired by Daniel Takeshi
Too many papers in DL/AI. Need some way to keep track of skimmed papers. Highlighting/annotating PDFs don't work too well for me so gonna try this.
This repo holds the notes for papers that I've read. Previously did this in a MS word document but that got too messy and slow when I needed to refer back. Still have yet to port over most of the past readings. Score is a number from (1) to (5) where 1 is just a quick skim through and 5 is complete understanding of the whole paper including all equations and reading chains.
- Deep Learning
- Generative Adversarial Networks
- Domain Adaptation
- Semi-supervised and Self-supervised Learning
- IC focused Deep Learning | IC related stuff
- Reinforcement Learning
- Name[Link to notes], Source/Conf/Journal [link to source], Year, Misc Source(Optional), Score
Generic papers on DL that don't fit into the other categories.
- CADTransformer, CVPR 2022
- CAPTURE the Bot: Using Adversarial Examples to Improve CAPTCHA Robustness to Bot Attacks : IEEE IS 2021 (3)
- DINO
- torch.manual seed(3407) is all you need: On the influence of random seeds in deep learning architectures for computer vision, arXiv 2021
- RepVGG: Making VGG-style ConvNets Great Again, CVPR 2021 (3)
- Rethinking "Batch" in BatchNorm, Review 2021 FacebookAI (1)
- Drawing Multiple Augmentation Samples Per Image During Training Efficiently Decreases Test Error, Preprint 2021 DeepMind (3)
- Once For All: Train one network and specialize it for efficient deployment, ICLR 2020 (2)
- Rethinking Pre-training and Self-training, NIPS 2020 (2)
- Bootstrap Your Own Latent A New Approach to Self-Supervised Learning, NIPS 2020 (3)
- CCNet: Criss-Cross Attention for Semantic Segmentation, ICCV 2019 (4)
- CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Fatures, ICCV 2019 (4)
- The Unreasonable Effectiveness of Deep Features as a Perceptual Metric, CVPR 2018 (4)
- SegAN: Adversarial Network with Multi-scale L1 Loss for Medical Image Segmentation, Neuroinformatics 2018 (4)
- Neural Architecture Search with Reinforcement Learning, ICLR 2017
- Attention is All you need, NIPS 2017 (2)
- Neural Machine Translation by Jointly Learning to Align and Translate, ICLR 2015
Any GAN related stuff. Image 2 Image translations, super-res etc. I put VAE related stuff here too since they are mostly used for generative purposes or thats what I read them for.
- Im2Vec: Synthesizing Vector Graphics without Vector Supervision, CVPR 2021 (4)
- Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation, CVPR 2021 (4)
- SAGAN: Self-Attention Generative Adversarial Networks, PMLR 2019 (4)
- Few-Shot Unsupervised Image-to-Image Translation, ICCV 2019 (2)
- Spectral Normalisation for GANs, ICLR, 2018 (1)
- Multimodal Unsupervised Image-to-Image Translation, ECCV 2018 (3)
- StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation, CVPR 2018 (3)
- Diverse Image-to-Image Translation via Disentangled Representations, ECCV 2018
- Vector Quantized-VAE, Neural Discrete Representation Learning, NIPS 2017 Deepmind (3)
- Wasserstein GAN, PMLR 2017 (2)
- pix2pix: Image-to-Image Translation with Conditional Adversarial Networks, CVPR 2017 (5)
- CycleGAN: Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks, ICCV 2017 (5)
- UNIT, Unsupervised Image-to-Image Translation Networks, NIPS 2017 (3)
- OG GAN from Goodfellow
- DCGAN
- Variational Autoencoders, Paper, 2014 (2)
- Pix2Pix
- CycleGAN
- An introduction to domain adaptation and transfer learning, Review Paper 2018
- Unsupervised Domain Adaptation in Semantic Segmentation: a Review, Review Paper 2020
- A Closer Look at Domain Shift for Deep Learning in Histopathology, MICCAI (WORKSHOP) 2019
- Curriculum Domain Adaptation for Semantic Segmentation of Urban Scenes ICCV 2017 (3)
- ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation, CVPR 2019 (1)
- Simplified unsupervised image translation for semantic segmentation adaptation, Pattern Recognition 2020 (3)
- Scale variance minimization for unsupervised domain adaptation in image segmentation, Pattern Recognition 2021 (1)
- Bidirectional Learning for Domain Adaptation of Semantic Segmentation, CVPR 2019,
- CyCADA: Cycle-Consistent Adversarial Domain Adaptation, PMLR 2018
- Unsupervised Data Augmentation for Consistency Training, NIPS 2020 (4)
- Self-training with Noisy Student improves ImageNet classification, CVPR 2020 (2)
- MixMatch: A Holistic Approach to Semi-Supervised Learning, NIPS 2019 (2)
- Towards Annotation Efficient Segmentation via Image to Image Translation, IEEE T-MI 2020 (1)
- DIVIDEMIX: LEARNING WITH NOISY LABELS AS SEMI-SUPERVISED LEARNING , ICLR 2020 (2)
- Efficient Visual Pretraining with Contrastive Detection, ICCV 2021
- PixPro, Propagate Yourself: Exploring Pixel-Level Consistency for Unsupervised Visual Representation Learning, CVPR 2021
- SimCLR: A Simple Framework for Contrastive Learning of Visual Representations, ICML 2021
- Self-supervised learning: The dark matter of intelligence, FAIR Blog, 2021
- GATO: A Generalist Agent, DeepMind, 2022
- Logo Classification and Data Augmentation Techniques for PCB Assurance and Counterfeit Detection, ISTFA 2021
- PCB Component Detection Using Computer Vision for Hardware Assurance, Big Data and Cognitive Computing 2022
- REFICS: Assimilating Data-Driven Paradigms Into Reverse Engineering and Hardware Assurance on Integrated Circuits, IEEEAccess 2021
- Generative Adversarial Network for Integrated Circuits Physical Assurance Using Scanning Electron Microscopy, IPFA 2021
- IC SynthLogo: A Synthetic Logo Image Dataset for Counterfeit and Recycled IC detection, IPFA 2021
- Segmentation of Integrated Circuit Layouts from Scan Electron Microscopy Images, CCECE 2018
Not really my focus but its a topic I find to be real cool. Somehow this is integrated with alot of DL work in general nowadays also, so better to know abit. Mainly will be reading articles or summaries by other people instead of the actual paper, just to get an intuitive idea and save time.
- An Intuitive Explanation of Policy Gradient , Article on policy gradient rule by Adrien Lucas Ecoffet
- Going Deeper Into Reinforcement Learning: Understanding Deep-Q-Networks, Blog Post from Daniel Taskeshi.