읽은 paper list

(Sort topics alphabetically)

 

- Active Learning

• Learning Loss for Active Learning(CVPR, 2019) https://arxiv.org/pdf/1905.03677.pdf

---

- Anomaly Detection

 -1. Unsupervised

• Towards Total Recall in Industrial Anomaly Detection(, 2021) https://arxiv.org/pdf/2106.08265.pdf
• FastFlow: Unsupervised Anomaly Detection and Localization(, 2021) https://arxiv.org/pdf/2111.07677.pdf

---

- CNN(Convolutional Neural Network) architectures

• Deep Residual Learning for Image Recognition(CVPR, 2016): Resnet https://arxiv.org/pdf/1512.03385.pdf

---

- Continual Learning

• Gradient Episodic Memory for Continual Learning(NeurIPS, 2017) https://arxiv.org/pdf/1706.08840.pdf

---

- Data augmentation

• M2m: Imbalanced Classification via Major-to-minor Translation(CVPR, 2020) https://arxiv.org/pdf/2004.00431.pdf
• Adversarial Examples Improve Image Recognition(CVPR, 2020) https://arxiv.org/pdf/1911.09665.pdf

---

- GNN(Graphical Neural Network)

  - 1. Analysis

• What Graph Neural Networks cannot Learn: Depth vs Width(ICLR, 2020) https://openreview.net/pdf?id=B1l2bp4YwS

  - 2. GCN(Graph Convolutional Network)

• Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering(NIPS, 2016) https://arxiv.org/pdf/1606.09375.pdf

---

- Hyper-parameter optimization

• Random Search for Hyper-parameter optimization(JMLR, 2012) https://www.jmlr.org/papers/volume13/bergstra12a/bergstra12a.pdf

---

- Interpretable Machine Learning

• Getting a CLUE: A Method for Explaining Uncertainty Estimates(ICLR, 2021) https://arxiv.org/pdf/2006.06848.pdf
  

---

- Meta-Learning(/Few-shot learning)

• Model-Agnostic Meta-learning for Fast Adaptation of Deep Networks(ICML, 2017) https://arxiv.org/pdf/1703.03400.pdf
• Prototypical Networks for Few-shot Learning(NIPS, 2017) https://arxiv.org/pdf/1703.05175.pdf
• Meta-Learning with Latent Embedding Optimization(ICLR, 2019) https://arxiv.org/pdf/1807.05960.pdf
• Few-shot Learning via Embedding Adaptation with Set-to-Set Functions(CVPR, 2020) https://arxiv.org/pdf/1812.03664.pdf
• Free Lunch for Few-shot Learning: Distribution Calibration(ICLR, 2021) https://arxiv.org/pdf/2101.06395.pdf

---

- Normalizing Flow

• Glow: Generative Flow with Invertible $1 \times 1$ Convolutions(NIPS, 2018) https://arxiv.org/pdf/1807.03039.pdf

---

- Optimizer

• ADADELTA: An Adaptive Learning Rate Method(CoRR, 2012) https://arxiv.org/pdf/1212.5701.pdf

---

- Out-of-Distribution detection

• A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks(ICLR, 2017) https://arxiv.org/pdf/1610.02136.pdf
• A simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks(NIPS, 2018) https://arxiv.org/pdf/1807.03888.pdf

---

- RNN(Recurrent Neural Network) architectures

• Sequence to Sequence Learning with Neural Networks(NIPS, 2014) https://arxiv.org/pdf/1409.3215.pdf

---

- Self-supervised Learning

• Momentum Contrast for Unsupervised Visual Representation(CVPR, 2020) https://arxiv.org/pdf/1911.05722.pdf
• A Simple Framework for Contrastive Learning of Visual Representation(ICML, 2020) https://arxiv.org/pdf/2002.05709.pdf
• Unsupervised Learning of Visual Features by Contrasting Cluster Assignments(NeurIPS, 2020) https://arxiv.org/pdf/2006.09882.pdf
• SEED: Self-supervised Distillation for Visual Representation(ICLR, 2021) https://arxiv.org/pdf/2101.04731.pdf
• ReSSL: Relational Self-supervised Learning with Weak Augmentation(NIPS, 2021) https://arxiv.org/pdf/2107.09282.pdf
• Emerging Properties in Self-supervised Vision Transformers(ICCV, 2021) https://arxiv.org/pdf/2104.14294.pdf
• Self-supervised Learning by Estimating Twin Class Distributions(, 2022) https://arxiv.org/pdf/2110.07402.pdf

---

- Semi-supervised Learning

• MixMatch: A Holistic Approach to Semi-supervised Learning(NeurIPS, 2019) https://arxiv.org/pdf/1905.02249.pdf

---

- Test Time Adaptation

• TENT: Fully Test-Time Adaptation by Entropy Minimization(ICLR, 2021) https://arxiv.org/pdf/2006.10726.pdf
• MEMO: Test Time Robustness via Adaptation and Augmentation(NeurIPS, 2021) https://arxiv.org/pdf/2110.09506.pdf

---

- Transformer

 - 1. NLP

• Attention is All You Need(NeurIPS, 2017) https://arxiv.org/pdf/1706.03762.pdf

 - 2. Vision

• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale(ICLR, 2021) https://arxiv.org/pdf/2010.11929.pdf
• Training data-efficient image transformers & distillation through attention(ICML, 2021) https://arxiv.org/pdf/2012.12877.pdf

 

---

- Unsupervised Meta-learning(Few-shot learning)

• Unsupervised Learning via Meta-learning(ICLR, 2019) https://arxiv.org/pdf/1810.02334.pdf
• Unsupervised Meta-learning for Few-shot Image Classification(NIPS, 2019) https://arxiv.org/pdf/1811.11819.pdf
• Meta-GMVAE: Mixture of Gaussian VAE for Unsupervised Meta-learning(ICLR, 2021) https://openreview.net/pdf?id=wS0UFjsNYjn