显著性检测
综述
- Salient Object Detection: A Benchmark https://arxiv.org/pdf/1501.02741
Salient Object Detection: A Survey https://arxiv.org/pdf/1411.5878
传统显著性检测
[x] A Model of Saliency-Based Visual Attention for Rapid Scene Analysis
- Saliency Detection: A Spectral Residual Approach
- Learning to Detect A Salient Object
- Visual Saliency Detection Based on Bayesian Model
- Saliency Detection Based on Integration of Boundary and Soft-Segmentation
- Graph-Regularized Saliency Detection With Convex-Hull-Based Center Prior
- Global Contrast based Salient Region Detection
- Bayesian Saliency via Low and Mid Level Cues
- Saliency Detection via Graph-Based Manifold Ranking
- Ranking Saliency
- Saliency Detection via Dense and Sparse Reconstruction
- Saliency Detection with Multi-Scale Superpixels
[x] Dense and Sparse Reconstruction Error Based Saliency Descriptor
基于深度学习的显著性检测
[ ] Deep Visual Attention Prediction TIP2018
- Predicting Human Eye Fixations via an LSTM-based Saliency Attentive Model
- Shallow and Deep Convolutional Networks for Saliency Prediction
- Saliency Detection with GAN (2017)
- https://github.com/batsa003/salgan/ (PyTorch的版本)
- Residual Learning for Saliency Detection
- Deeply Supervised Salient Object Detection with Short Connections
- Saliency Detection with Recurrent Fully Convolutional Networks
- Learning to Detect Salient Objects with Image-level Supervision
- Deep3DSaliency: Deep Stereoscopic Video Saliency Detection Model by 3D Convolutional Networks(Valse 2019)
- Deep Spectral Clustering using Dual Autoencoder Network(Valse 2019)
[x] MEnet: A Metric Expression Network for Salient Object Segmentation(Valse 2019)
图像分类
[x] FishNet
- ShuffleNet(V1/V2)
- MobileNet(V1/V2)
[ ] C3AE: Exploring the Limits of Compact Model for Age Estimation
超分辨重建
[ ] Meta-SR: A Magnification-Arbitrary Network for Super-Resolution
模型压缩/加速/搜索
[ ] A Survey of Model Compression and Acceleration for Deep Neural Networks
- CondenseNet: An Efficient DenseNet using Learned Group Convolutions
[ ] Partial Order Pruning: for Best Speed/Accuracy Trade-off in Neural Architecture Search
[x] Semi-supervised Classification with Graph Convolutional Networks
- Semantic Object Parsing with Graph LSTM
[x] Interpretable Structure-Evolving LSTM
分割
[x] Semantic object parsing with graph lstm
- Interpretable structure-evolving lstm
- Large-scale point cloud semantic segmentation with superpoint graphs
- Dynamic graph cnn for learning on point clouds
- Adaptive Affinity Fields for Semantic Segmentation
- Context Encoding for Semantic Segmentation
- Dual Attention Network for Scene Segmentation
- Dilated Residual Networks
- DenseASPP for Semantic Segmentation in Street Scenes
- Understand Convolution for Semantic Segmentation
- FickleNet: Weakly and Semi-supervised Semantic Image Segmentationusing Stochastic Inference
- DUpsample: Decoders Matter for Semantic Segmentation:Data-Dependent Decoding Enables Flexible Feature Aggregation
- 3DGNN: 3D Graph Neural Networks for RGBD Semantic Segmentation
- GCN: Large Kernel Matters-Improve Semantic Segmentation by Global Convolutional Network
- DFN: Learning a Discriminative Feature Network for Semantic Segmentation
- BiSeNet: BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation
- RFB: Receptive Field Block Net for Accurate and Fast Object Detection
[ ] DFANet: Deep Feature Aggregation for Real-Time Semantic Segmentation
递归网络
- Multi-Dimensional Recurrent Neural Networks
- Mixtures of Conditional Gaussian Scale Mixtures Applied to Multiscale Image Representations
- Generative Image Modeling Using Spatial LSTMs
[x] Convolutional LSTM Network: A Machine LearningApproach for Precipitation Nowcasting
基础理论
[ ] Foundations of Deep Learning: SGD, Overparametrization, and Generalization
可解释人工智能
[ ] Explanation in Human-AI Systems
损失函数
GIOU
- https://blog.csdn.net/touch_dream/article/details/78716507
- https://blog.csdn.net/xbcReal/article/details/53494866
- 程明明老师的建议: https://mmcheng.net/zh/paperreading/
- 目标检测论文集合: https://handong1587.github.io/deep_learning/2015/10/09/object-detection.html