- 這是一個完整的深度學習論文評論和程式碼實踐的儲存庫。
- 我們介紹各種熱門的深度學習論文，並專注於最新論文。
- End-to-End Object Detection with Transformers (ECCV 2020)
- Transformer:進行端對端物件偵測
- Original Paper Link / Paper Review Video / Summary PDF / Code Practice
- Searching for MobileNetV3 (ICCV 2019)
- MobileNetV3:搜尋
- Original Paper Link / Paper Review Video / Summary PDF / Code Practice
- Deep Residual Learning for Image Recognition (CVPR 2016)
- 影像辨識:深度殘差學習
- Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization (ICCV 2017)
- 即時風格轉換:透過歸一化實現
- Image Style Transfer Using Convolutional Neural Networks (CVPR 2016)
- CNN:影像風格遷移
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks (NIPS 2015)Faster R-CNN：
- R-CNN:透過區域提議網路實現即時目標偵測
- Original Paper Link / Paper Review Video / Summary PDF / Code Practice
- Single Headed Attention RNN: Stop Thinking With Your Head (2020)
- 單頭注意力RNN:停止用心思思考
- Original Paper Link / Paper Review Video / Summary PDF / Code Practice
- BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (NAACL 2019)
- BERT:用於語言理解的深度雙向T的預訓練
- Original Paper Link / Paper Review Video / Summary PDF / Code Practice
- Attention is All You Need (NIPS 2017)
- 關注力:就是你所需要的
- Neural Machine Translation by Jointly Learning to Align and Translate (ICLR 2015 Oral)
- 翻譯:聯合學習對齊和翻譯進行神經機器翻譯
- Original Paper Link / Paper Review Video / Summary PDF / Code Practice
- Show and Tell: A Neural Image Caption Generator (CVPR 2015)
- 字幕產生器:展示
- Original Paper Link / Paper Review Video / Summary PDF / Code Practice
- Sequence to Sequence Learning with Neural Networks (NIPS 2014)
- 序列學習:使用神經網路
- Meta-Transfer Learning for Zero-Shot Super-Resolution (CVPR 2020)
- 零樣本超解析度:元遷移學習
- Original Paper Link / Paper Review Video / Summary PDF / Code Practice
- SinGAN: Learning a Generative Model from a Single Natural Image (ICCV 2019)
- SinGAN:從單一自然影像學習生成模型
- Original Paper Link / Paper Review Video / Summary PDF / Code Practice
- A Style-Based Generator Architecture for Generative Adversarial Networks (CVPR 2019)
- 產生對抗網路:基於樣式的生成器架構
- Original Paper Link / Paper Review Video / Summary PDF / Code Practice
- StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation (CVPR 2018 Oral)
- StarGAN：用於多域圖像到圖像翻譯的統一生成對抗網絡
- Image-to-Image Translation with Conditional Adversarial Networks (CVPR 2017)
- 圖圖翻譯:條件對抗網路
- Generative Adversarial Nets (NIPS 2014)
- 生成對抗網路
- Bag of Tricks for Image Classification (CVPR 2019)
- 影像分類:技巧
- Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding (ICLR 2016 Oral)
- 深度壓縮:深度神經網絡:透過剪枝、訓練量化和霍夫曼編碼
- Original Paper Link / Paper Review Video / Summary PDF / Code Practice
- Batch normalization: Accelerating deep network training by reducing internal covariate shift (PMLR 2015)
- 批量歸一化：透過減少內部協變量偏移來加速深度網路訓練
- HopSkipJumpAttack: A Query-Efficient Decision-Based Attack (S&P 2020)
- HopSkipJumpAttack:基於查詢的高效決策攻擊
- Original Paper Link / Paper Review Video/ Summary PDF / Targeted Attack / Untargeted Attack
- Breaking certified defenses: Semantic adversarial examples with spoofed robustness certificates (ICLR 2020)
- 打破經過認證的防禦：具有欺騙性穩健性證書的語義對抗範例
- Sign-OPT: A Query-Efficient Hard-label Adversarial Attack (ICLR 2020)
- Sign-OPT：查詢高效率的硬標籤對抗攻擊
- Original Paper Link / Paper Review Video / Summary PDF / MNIST / CIFAR-10
- Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment (AAAI 2020 Oral)
- BERT:Robust？自然語言攻擊文本分類與蘊涵的強大基線
- Query-Efficient Hard-label Black-box Attack: An Optimization-based Approach (ICLR 2019)
- 查詢高效的硬標籤黑盒攻擊:最佳化的方法
- Original Paper Link / Paper Review Video / Summary PDF / MNIST / CIFAR-10
- Boosting Adversarial Attacks with Momentum (CVPR 2018 Spotlight)
- 對抗性攻擊:增強
- Original Paper Link / Paper Review Video / Summary PDF / CIFAR-10 / ImageNet
- Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networks (NIPS 2018)
- 毒蛙:神經網路的清潔標籤中毒攻擊
- Original Paper Link / Paper Review Video / Summary PDF / ResNet / AlexNet
- Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Models (ICLR 2018)
- 決策的對抗性攻擊:針對黑盒機器學習模型的可靠攻擊
- Original Paper Link / Paper Review Video / Summary PDF / Code Practice
- Explaining and Harnessing Adversarial Examples (ICLR 2015)
- 對抗性:解釋
- Towards Evaluating the Robustness of Neural Networks (S&P 2017)
- 評估穩健性:神經網路
- Towards Deep Learning Models Resistant to Adversarial Attacks (ICLR 2018)
- 深度學習模式:抵抗對抗性攻擊
- Adversarial Examples Are Not Bugs, They Are Features (NIPS 2019)
- 對抗性例子不是錯誤:是特徵
- Certified Robustness to Adversarial Examples with Differential Privacy (S&P 2019)
- 穩健性:差異隱私的對抗性
- Obfuscated Gradients Give a False Sense of Security (ICML 2018)
- 模糊:錯誤的安全感
- Constructing Unrestricted Adversarial Examples with Generative Models (NIPS 2018)
- 對抗性範例:使用生成模型建立
- Adversarial Patch (NIPS 2018)
- 補丁:對抗性