终终终终于放假了= =
寒假可以看点自己感兴趣的论文了，今年大火的对比学习和一些Transformer相关的论文一直存着没看
列个论文清单，有空的话慢慢看过去

Contrastive Learning

综述

• A Survey on Contrastive Self-supervised Learning【20.11】

具体方法

• A Simple Framework for Contrastive Learning of Visual Representations(SimCLR)【ICML2020/20.02】
• Big Self-Supervised Models are Strong Semi-Supervised Learners（SimCLRv2）【NIPS2020/20.06】
• Momentum Contrast for Unsupervised Visual Representation Learning(MoCo)【CVPR2020/19.11】
• Improved Baselines with Momentum Contrastive Learning(MoCov2)【20.03】
• Contrastive Multiview Coding(CMC)【ECCV2020/19.06】
• Representation Learning with Contrastive Predictive Coding(CPC)【18.07】
• Exploring Simple Siamese Representation Learning(SimSiam)【20.11】
• Bootstrap your own latent： A new approach to self-supervised Learning(BYOL)【20.06】
• Unsupervised Learning of Visual Features by Contrasting Cluster Assignments(SwAV)【NIPS2020/20.06】
• Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination【CVPR2018/18.05】
• Data-Efficient Image Recognition with Contrastive Predictive Coding【ICML2020/19.05】
• Learning Deep Representations by Mutual Information Estimation and Maximization【ICLR2019/18.08】
• Propagate Yourself: Exploring Pixel-Level Consistency for Unsupervised Visual Representation Learning【20.11】
• A Theoretical Analysis of Contrastive Unsupervised Representation Learning【ICML2019/19.02】
• Contrastive Transformation for Self-supervised Correspondence Learning【AAAI2021/20.12】
• Supervised Contrastive Learning【20.04】
• Dimensionality Reduction by Learning an Invariant Mapping【CVPR2006】
• Adversarial Self-Supervised Contrastive Learning【NIPS2020/20.06】
• Intriguing Properties of Contrastive Losses【20.11】

应用

• Contrastive Learning for Image Captioning【NIPS2017/17.10】
• Contrastive Learning of Structured World Models【ICLR2020/19.11】
• Cross-Modal Contrastive Learning for Text-to-Image Generation【21.01】

Transformer

综述

• Efficient Transformers: A Survey

NLP

• Attention is All You Need(Transormer)

• Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context

• REFORMER : THE EFFICIENT TRANSFORMER

• BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

• XLNet: Generalized Autoregressive Pretraining for Language Understanding

• RoBERTa: A Robustly Optimized BERT Pretraining Approach

• ALBERT: A Lite BERT For Self-Supervised Learning Of Language Representations

• FastBERT: a Self-distilling BERT with Adaptive Inference Time

• TinyBERT: Distilling BERT for Natural Language Understanding

• Improving Language Understanding by Generative Pre-Training(GPT)

• Language Models are Unsupervised Multitask Learners(GPT-2)

• Language Models are Few-Shot Learners(GPT-3)

CV

• ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks
• On The Relationship Between Self-attention and Convolutional Layers
• an image is worth 16x16 words: Transformers for image recognition at scale
• exploring self-attention for image recognition
• end-to-end object detection with transformers(DETR)
• Deformable DETR: Deformable Transformers for end-to-end object detection
• act(end-to-end object detection with adaptive clustering transformer)
• image transformer
• generating long sequences with sparse transformers
• generative pretraining from pixels
• hamming ocr: a locality sensitive hashing neural network for scene text recognition
• actBERT: learning global-local video-text representations
• max-deeplab: end-to-end panoptic segmentation with mask transformers
• end-to-end dense video captioning with masked transformer
• end-to-end video instance segmentation with transformers
• foley music: learning to generate music from videos
• end-to-end lane shape prediction with transformers