1.CVPR2021接受論文&&代碼&&Post&&PPT (持續更新中，敬請關注)
28.D-NeRF: Neural Radiance Fields for Dynamic Scenes(D-NeRF：動態場景的神經輻射場) project
27.Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation(樣式編碼：用於圖像到圖像翻譯的StyleGAN編碼器)
project
26.A 3D GAN for Improved Large-pose Facial Recognition(用於改善大姿勢面部識別的3D GAN)
paper
25.Multi-Stage Progressive Image Restoration
paper
24.Rotation Equivariant Siamese Networks for Tracking（旋轉等距連體網絡進行跟蹤）
paper
23.Exploring Complementary Strengths of Invariant and Equivariant Representations for Few-Shot Learning(探索少量學習的不變表示形式和等變表示形式的互補強度)
22.Open-world object detection(開放世界中的目標檢測)
code
21.Multi-Stage Progressive Image Restoration(多階段漸進式圖像復原)
paper|code
20.Weakly Supervised Learning of Rigid 3D Scene Flow(剛性3D場景流的弱監督學習)
paper|code|project
19.PREDATOR: Registration of 3D Point Clouds with Low Overlap(預測器：低重疊的3D點雲的注冊)
paper|code|project
18.Sequential Graph Convolutional Network for Active Learning(主動學習的順序圖卷積網絡)
paper
17.Multiresolution Knowledge Distillation for Anomaly Detection(用於異常檢測的多分辨率知識蒸餾)
paper
16.Positive-Unlabeled Data Purification in the Wild for Object Detection
15.Data-Free Knowledge Distillation For Image Super-Resolution(DAFL算法的SR版本)
14.Manifold Regularized Dynamic Network Pruning（動態剪枝的過程中考慮樣本復雜度與網絡復雜度的約束）
13.Distilling Object Detectors via Decoupled Features（前景背景分離的蒸餾技術）
12.Inverting the Inherence of Convolution for Visual Recognition
11.Representative Batch Normalization with Feature Calibration
10.PointFlow: Flowing Semantics Through Points for Aerial Image Segmentation
9.Learning the Superpixel in a Non-iterative and Lifelong Manner
8.RepVGG: Making VGG-style ConvNets Great Again
paper|code
解讀：RepVGG：極簡架構，SOTA性能，讓VGG式模型再次偉大
7.Transformer Interpretability Beyond Attention Visualization
paper
6.UP-DETR: Unsupervised Pre-training for Object Detection with Transformers
paper
解讀：無監督預訓練檢測器
5.Pre-Trained Image Processing Transformer(底層視覺預訓練模型)
paper
4.ReNAS: Relativistic Evaluation of Neural Architecture Search(NAS predictor當中ranking loss的重要性)
paper
3.AdderSR: Towards Energy Efficient Image Super-Resolution(將加法網路應用到圖像超分辨率中)
paper|code
解讀：華為開源加法神經網絡
2.Learning Student Networks in the Wild（一種不需要原始訓練數據的模型壓縮和加速技術）
paper|code
解讀：華為諾亞方舟實驗室提出無需數據網絡壓縮技術
1.HourNAS: Extremely Fast Neural Architecture Search Through an Hourglass Lens（降低NAS的成本）
paper
論文合集下載
鏈接：https://pan.baidu.com/s/1caJ8PKQizDYt1TInEVBjSg
提取碼：uuro
下載鏈接和提取碼已更新（2021-03-02）
PS：整理太累，請盡快收藏或下載，防止過期 ~ -