📚 Reading List

Content

0. Surveys
1. Classification
2. Domain Adaptation
3. Meta Learning
4. Detection
5. Segmentation
6. Captioning
7. Visual Question Answering
8. Visual Commonsense
9. Causality
10. Attentions
11. Quantization
12. Metrics

Surveys

• "A Survey of Learning Causality with Data: Problems and Methods," ACM Computing Surveys, 2020.
• "Generalizing from a Few Examples: A Survey on Few-Shot Learning," ACM Computing Surveys, 2020.
• "Overcoming Negative Transfer: A Survey," arXiv, 2020.
• "Image Segmentation using Deep Learning: A Survey," arXiv, 2020.
• "Deep Learning for Generic Object Detection: A Survey," IJCV, 2020.
• "Multimodal Machine Learning: A Survey and Taxonomy," IEEE TPAMI, 2019.
• "An Attentive Survey of Attention Models," arXiv, 2019.
• "A Comprehensive Survey of Deep Learning for Image Captioning," ACM Computing Surveys, 2019.
• "Recent Advances in Zero-shot Recognition," IEEE Signal Processing Magazine, 2018.
• "Deep Visual Domain Adaptation: A Survey," Neurocomputing, 2018.
• "A Comprehensive Survey of Deep Learning for Image Captioning," ACM Computing Surveys, 2018.
• "A Survey on Deep Learning Techniques for Image and Video Semantic Segmentation," Applied Soft Computing, 2018.
• "Visual Question Answering: A Survey of Methods and Datasets," Computer Vision and Image Understanding, 2017.
• "Representation Learning: A Review and New Perspectives," arXiv, 2014.

Classification

• "Searching for MobileNetV3," ICCV, 2019.
• "ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design," ECCV, 2018.
• "SqueezeNext: Hardware-Aware Neural Network Design," CVPR, 2018.
• "Squeeze-and-Excitation Networks," CVPR, 2018.
• "MobileNetV2: Inverted Residuals and Linear Bottlenecks," CVPR, 2018.
• "ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices," CVPR, 2018.
• "Non-local Neural Networks," CVPR, 2018.
• "MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications," CVPR, 2017.
• "Xception: Deep Learning with Depthwise Separable Convolutions," CVPR, 2017.
• "Residual Attention Network for Image Classification," CVPR, 2017.
• "SqueezeNet: AlexNet-Level Accuracy with 50x Fewer Parameters and <0.5MB Model Size," ICLR, 2017.
• "Going Deeper with Convolutions," CVPR, 2015.
• "Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift," arXiv, 2015.
• "Transductive Multi-View Zero-Shot Learning," IEEE TPAMI, 2015.
• "Spatial Transformer Networks," NeurIPS, 2015.
• "Learning To Detect Unseen Object Classes by Between-Class Attribute Transfer," CVPR, 2009.
• "CNN模型之ShuffleNet（PyTorch实现）," 知乎.
• "轻量级神经网络“巡礼”（一）—— ShuffleNetV2," 知乎.
• "轻量级神经网络“巡礼”（二）—— MobileNet，从V1到V3," 知乎.
• "MobileNet v1 和 MobileNet v2（Keras实现）," 知乎.
• "Why MobileNet and Its Variants (e.g. ShuffleNet) are Fast," Medium.

Domain Adaptation

• "Open Compound Domain Adaptation," CVPR, 2020.
• "Delving into Inter-Image Invariance for Unsupervised Visual Representations," arXiv, 2020.
• "Zero-Shot Learning - A Comprehensive Evaluation of the Good, the Bad and the Ugly," IEEE TPAMI, 2019.
• "Large-Scale Long-Tailed Recognition in an OpenWorld," CVPR, 2019.
• "f-VAEGAN-D2: A Feature Generating Framework for Any-Shot Learning," CVPR, 2019.
• "Feature Generating Networks for Zero-Shot Learning," CVPR, 2018.
• "Semantic Autoencoder for Zero-Shot Learning," CVPR, 2017.
• "Latent Embeddings for Zero-shot Classification," CVPR, 2016.
• "Transductive Multi-view Zero-Shot Learning," IEEE TPAMI, 2015.
• "Zero-Shot Learning via Semantic Similarity Embedding," ICCV, 2015.
• "Ridge Regression, Hubness, and Zero-Shot Learning," EMNLP, 2015.
• "Zero-Shot Learning Through Cross-Modal Transfer," NeurIPS, 2013.
• "Learning To Detect Unseen Object Classes by Between-Class Attribute Transfer," CVPR, 2009.

Meta Learning

• "Reptile: A Scalable Meta Learning Algorithm, arxiv, 2018.
• "Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks," ICML, 2017.
• "Fun with Small Image Data-Sets," Medium.
• "Paper repro: Deep Metalearning using “MAML” and “Reptile”," Medium.
• "Paper repro: “Learning to Learn by Gradient Descent by Gradient Descent”," Medium.
• "What is Model-Agnostic Meta-learning(MAML)?," Medium.
• "Advances in Few-Shot Learning: A Guided Tour," Medium.
• "Advances in Few-Shot Learning: Reproducing Results in PyTorch," Medium.
• "元学习: 学习如何学习," Blog.
• "[Meta-Learning]Matching Network详解," 知乎.
• "论文笔记：Matching Networks for One Shot Learning," 知乎.
• "基于匹配网络(Matching Networks)的FSL方法简述（一）," 知乎.
• "基于匹配网络(Matching Networks)的FSL方法简述（二）," 知乎.
• "Model-Agnostic Meta-Learning （MAML）模型介绍及算法详解," 知乎.
• "对MAML的深度解析," 知乎.

Detection

• "YOLOv4: Optimal Speed and Accuracy of Object Detection," arXiv, 2020.
• "Reasoning-RCNN: Unifying Adaptive Global Reasoning into Large-Scale Object Detection," CVPR, 2019.
• "Deformable ConvNets v2: More Deformable, Better Results," CVPR, 2019.
• "Objects as Points," arXiv, 2019.
• "CornerNet: Detecting Objects as Paired Keypoints," ECCV, 2018.
• "YOLOv3: An Incremental Improvement,"" arXiv, 2018.
• "Focal Loss for Dense Object Detection," ICCV, 2017.
• "SqueezeDet: Unified, Small, Low Power Fully Convolutional Neural Networks for Real-Time Object Detection for Autonomous Driving," CVPR, 2017.
• "Feature Pyramid Networks for Object Detection," CVPR, 2017.
• "Deformable Convolutional Networks," ICCV, 2017.
• "R-FCN: Object Detection via Region-based Fully Convolutional Networks," NeurIPS, 2016.
• "SSD: Single Shot MultiBox Detector," ECCV, 2016.
• "You Only Look Once: Unified, Real-Time Object Detection," CVPR, 2016.
• "Faster R-CNN," NeurIPS, 2015.
• "Fast R-CNN," CVPR, 2015.
• "Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition," IEEE TPAMI, 2015.
• "Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation," CVPR, 2014.
• "Selective Search for Object Recognition," IJCV, 2013.

Segmentation

• "Learning to Segment the Tail," CVPR, 2020.
• "Panoptic Feature Pyramid Networks," CVPR, 2019.
• "Panoptic Segmentation," CVPR, 2019.
• "DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs," IEEE TPAMI, 2018.
• "Learning to Segment Every Thing," CVPR, 2018.
• "Mask R-CNN," ICCV, 2017.
• "Rethinking Atrous Convolution for Semantic Image Segmentation," arXiv, 2017.
• "Learning Deconvolution Network for Semantic Segmentation," ICCV, 2015.
• "Fully Convolutional Networks for Semantic Segmentation," CVPR, 2015.
• "Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials," NeurIPS, 2011.

Captioning

• "Attention on Attention for Image Captioning," ICCV, 2019.
• "Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering," CVPR, 2018.
• "Dense-Captioning Events in Videos," ICCV, 2017.
• "DenseCap: Fully Convolutional Localization Networks for Dense Captioning," CVPR, 2016.
• "Deep Visual-Semantic Alignments for Generating Image Descriptions," CVPR, 2015.
• "Show, Attend and Tell: Neural Image Caption Generation with Visual Attention," ICML, 2015.

Visual Question Answering

• "Reasoning on the Relation: Enhancing Visual Representation for Visual Question Answering and Cross-modal Retrieval," IEEE TMM, 2020.
• "Deep Modular Co-Attention Networks for Visual Question Answering," CVPR, 2019.
• "Motion-Appearance Co-Memory Networks for Video Question Answering," CVPR, 2018.
• "Don’t Just Assume; Look and Answer: Overcoming Priors for Visual Question Answering," CVPR, 2018.
• "Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering," CVPR, 2017.
• "Visual Question Answering: A Tutorial," IEEE Signal Processing Magazine, 2017,
• "Uncovering Temporal Context for Video Question and Answering," IJCV, 2017.
• "C-VQA: A Compositional Split of the Visual Question Answering (VQA) v1.0 Dataset," arXiv, 2017.
• "End-to-end Concept Word Detection for Video Captioning, Retrieval, and Question Answering," CVPR, 2017.
• "Ask Me Anything: Free-form Visual Question Answering Based on Knowledge from External Sources," CVPR, 2016.
• "Visual7W: Grounded Question Answering in Images," CVPR, 2016.
• "VQA: Visual Question Answering," ICCV, 2015.

Visual Commonsense

• "VisualCOMET: Reasoning about the Dynamic Context of a Still Image," arXiv, 2020.
• "Give Me Something to Eat: Referring Expression Comprehension with Commonsense Knowledge," ACM MM, 2020.
• "From Recognition to Cognition: Visual Commonsense Reasoning," CVPR, 2019.
• "Heterogeneous Graph Learning for Visual Commonsense Reasoning," NeurIPS, 2019.
• "Stating the Obvious: Extracting Visual Common Sense Knowledge," NAACL, 2016.
• "Don’t Just Listen, Use Your Imagination: Leveraging Visual Common Sense for Non-Visual Tasks," CVPR, 2015.

Causality

• "".
• "Visual Commonsense R-CNN," CVPR, 2020.
• "Counterfactual Samples Synthesizing for Robust Visual Question Answering," CVPR, 2020.
• "Counterfactual VQA: A Cause-Effect Look at Language Bias," arXiv, 2020.
• "Two Causal Principles for Improving Visual Dialog," CVPR, 2020.
• "Unbiased Scene Graph Generation from Biased Training," CVPR, 2020.
• "Deconfounded Image Captioning: A Causal Retrospect," arXiv, 2020.
• "Discovering Causal Signals in Images," CVPR, 2017.

Attentions

• "VL-BERT: Pre-Training of Generic Visuallinguistic Representations," ICLR, 2020.
• "VisualBERT: A Simple and Performant Baseline for Vision and Language," arXiv, 2019.
• "ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks," arXiv, 2019.
• "BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding," EMNLP, 2018.
• "Attention is All You Need," NeurIPS, 2017.
• "Convolutional Sequence to Sequence Learning," arXiv, 2017.
• "Neural Machine Translation by Jointly Learning to Align and Translate," ICLR, 2015.

Quantization

• "VecQ: Minimal Loss DNN Model Compression With Vectorized Weight Quantization," IEEE TC, 2020.
• "uL2Q: An Ultra-Low Loss Quantization Method for DNN Compression, IJCNN, 2019.
• "EIE: Efficient Inference Engine on Compressed Deep Neural Network," ISCA, 2016.
• "Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding," ICLR, 2016.
• "Ternary Weight Networks," NeurIPS Workshop, 2016.
• "Binarized Neural Networks," NeurIPS, 2016.

Metrics

• "CHAIR: Object Hallucination in Image Captioning," EMNLP, 2018.
• "SPICE: Semantic Propositional Image Caption Evaluation," ECCV, 2016.
• "CIDEr: Consensus-based Image Description Evaluation," CVPR, 2015.
• "METEOR: An Automatic Metric for MT Evaluation with Improved Correlation with Human Judgments," ACL Workshop, 2005.
• "Rouge: A Package for Automatic Evaluation of Summaries," Text Summarization Branches Uut, 2004.
• "BLEU: a Method for Automatic Evaluation of Machine Translation," ACL, 2002.