Closed TCChenlong closed 2 years ago
【队名】:网抑云
【序号】:37
【论文】:XCiT: Cross-Covariance Image Transformers
【状态】:报名
【队名】:网抑云
【序号】:35
【论文】:MLP-Mixer: An all-MLP Architecture for Vision
【状态】:报名
【队名】:EICAS
【序号】:4
【论文】:EfficientDet: Scalable and Efficient Object Detection
【状态】:报名
【队名】: 自动ac机
【序号】:32
【论文】:Wide Residual Networks
【状态】:报名
【队名】:EICAS
【序号】:12
【论文】:YOLOv4: Optimal Speed and Accuracy of Object Detection
【状态】:报名
【队名】:txyugood
【序号】:18
【论文】:Holistically-Nested Edge Detection
【状态】:报名
【repo链接】:https://github.com/txyugood/hed
【队名】:EICAS
【序号】:9
【论文】:YOLOX: Exceeding YOLO Series in 2021
【状态】:报名
【队名】:网抑云
【序号】:36
【论文】:Deep Networks with Stochastic Depth
【状态】:报名
【队名】: 自动ac机
【序号】:36
【论文】:Deep Networks with Stochastic Depth
【状态】:报名
【队名】:网抑云
【序号】:32
【论文】:Wide Residual Networks
【状态】:报名
【队名】:EICAS
【序号】:1
【论文】:YOLO9000: Better, Faster, Stronger
【状态】:报名
【队名】: 自动ac机
【序号】:34
【论文】:Prototypical Networks for Few-shot Learning
【状态】:报名
【队名】: 自动ac机
【序号】:73
【论文】:ConvBERT: Improving BERT with Span-based Dynamic Convolution
【状态】:报名
【队名】:网抑云
【序号】:34
【论文】: Prototypical Networks for Few-shot Learning
【状态】:报名
【repo链接】:https://github.com/jm12138/PrototypicalNetworks-Paddle
【队名】:网抑云
【序号】:38
【论文】:R-Drop: Regularized Dropout for Neural Networks
【状态】:报名
【队名】: 自动ac机
【序号】:90
【论文】:ChineseBERT: Chinese Pretraining Enhanced by Glyph and Pinyin Information
【状态】:报名
【队名】:EICAS
【序号】:14
【论文】:End to End Learning for Self-Driving Cars
【状态】:报名
【repo链接】:https://github.com/nuaaceieyty/Paddle-self-driving-car
【队名】:involute
【序号】:52
【论文】:Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields
【状态】:报名
【队名】: 我们的名字刚好十个字
【序号】:73
【论文】:ConvBERT: Improving BERT with Span-based Dynamic Convolution
【状态】:报名
【队名】:jonny4929的团队
【序号】:17
【论文】:ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation
【状态】:报名
【队名】:fxwispig
【序号】:63
【论文】:Detecting Text in Natural Image with Connectionist Text Proposal Network
【状态】:报名
【队名】:八月与安生 【序号】:39 【论文】:Cream of the Crop: Distilling Prioritized Paths For One-Shot Neural Architecture Search 【状态】:报名 【repo链接】:https://github.com/awsssix/Cream-Paddle
【队名】:开心复现666
【序号】:24
【论文】:YOLACT: Real-time Instance Segmentation
【状态】:报名
【队名】:niu
【序号】:64
【论文】:Real-time Convolutional Neural Networks for Emotion and Gender Classification
【状态】:报名
【repo链接】:https://github.com/yt123123/com.git
【队名】:开心复现666
【序号】:26
【论文】:YOLACT++: Better Real-time Instance Segmentation
【状态】:报名
【队名】:深智源
【序号】:32
【论文】:Wide Residual Networks
【状态】:报名
【队名】:Doctor Who
【序号】:46
【论文】:Semantic Image Synthesis with Spatially-Adaptive Normalization
【状态】:报名
【队名】:蜜雪冰城甜蜜蜜
【序号】:41
【论文】:Image Inpainting for Irregular Holes Using Partial Convolutions
【状态】:报名
【队名】:jonny4929的团队
【序号】:23
【论文】:SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation
【状态】:报名
【repo链接】:https://github.com/jonny4929/segnet
【队名】:写代码的咕噜
【序号】:91
【论文】:Listen, Attend and Spell
【状态】:报名
【repo链接】:https://github.com/fclearner/Listen_and_spell_paper_paddle.git
【队名】:皮蛋瘦肉周
【序号】:65
【论文】:PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models
【状态】:报名
【队名】:愚者
【序号】:43
【论文】:Generative Adversarial Text to Image Synthesis
【状态】:报名
【队名】:角灰大帝硬train一发 【序号】:35
【论文】: MLP-Mixer: An all-MLP Architecture for Vision
【状态】:报名
【队名】:对不队
【序号】:12
【论文】:YOLOv4: Optimal Speed and Accuracy of Object Detection
【状态】:报名
【队名】:对不队
【序号】:11
【论文】:Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering
【状态】:报名
【队名】:角灰大帝硬train一发
【序号】:91
【论文】:Listen, Attend and Spell
【状态】:报名
【队名】:我们的名字刚好十个字
【序号】:75
【论文】:Dense Passage Retrieval for Open-Domain Question Answering
【状态】:报名
【repo链接】:https://github.com/junnyu/dpr_paddle
【队名】:我们的名字刚好十个字
【序号】:75
【论文】:Dense Passage Retrieval for Open-Domain Question Answering
【状态】:提交
【repo链接】:https://github.com/junnyu/dpr_paddle
【队名】:FutureSI
【序号】:46
【论文】:Semantic Image Synthesis with Spatially-Adaptive Normalization
【状态】:报名/提交
【repo链接】:https://github.com/NVlabs/SPADE
【队名】:YOLM
【序号】:6
【论文】: Scaled-YOLOv4: Scaling Cross Stage Partial Network
【状态】:报名
【队名】:不是吧不是吧难道单押也算押
【序号】:42
【论文】:Self-Attention Generative Adversarial Networks
【状态】:报名
【repo链接】:https://github.com/Atmosphere-art/Self-Attention-GAN
【队名】:不是吧不是吧难道专家也算家
【序号】:32
【论文】:Wide Residual Networks
【状态】:报名
【队名】:fuqianya
【序号】:10
【论文】:Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
【状态】:报名
【repo链接】:https://github.com/fuqianya/show-attend-and-tell-paddle
【队名】:fuqianya
【序号】:11
【论文】:Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering
【状态】:报名
【repo链接】:https://github.com/fuqianya/bottom-up-attention-paddle
【队名】:没有服务器
【序号】:34
【论文】:Prototypical Networks for Few-shot Learning
【状态】:报名
【队名】:今晚杀不杀
【序号】:70
【论文】:Convolutional Sequence to Sequence Learning
【状态】:报名
【队名】:A3
【序号】:93
【论文】:Deep Learning Recommendation Model for Personalization and Recommendation Systems
【状态】:报名
【队名】: arbiter
【序号】:73
【论文】:ConvBERT: Improving BERT with Span-based Dynamic Convolution
【状态】:报名
【repo链接】:https://github.com/renmada/convbert
hi,大家好,非常高兴的告诉大家,百度飞桨论文复现赛第四期已经开始了,本次共将有100篇的经典&前沿论文供大家复现,详细信息可以参考AI Studio,大家是否已经迫不及待了呢~
注意: 本次部分赛题与人工智能创新应用大赛重合,如果获奖,会有额外奖励,详情请看这里。
注意: 本次部分赛题与中国软件开源创新大赛重合,如果获奖,会有额外奖励,详情请看这里。
为了帮助大家更好的了解每篇论文的复现进度,本次复现赛将在本帖中汇总信息。如果你报名/提交结果,需要按格式在进行回复,我们每天会汇总所有的信息,并更新在下表中,你可以通过下面的表格中,了解到每一篇论文的相关信息。
回复的格式为:
【队名】:你队伍的名称
【序号】:你队伍想要复现的论文序号
【论文】:你队伍想要复现的论文名称
【状态】:报名/提交
【repo链接】:repo的链接
如:
【队名】:百度飞桨
【序号】:100
【论文】:Paper 1
【状态】:提交
【repo链接】:https://github.com/PaddlePaddle/Paddle
目标检测
1YOLO9000: Better, Faster, Stronger2You Only Look Once: Unified, Real-Time Object Detection4EfficientDet: Scalable and Efficient Object Detection5High Quality Monocular Depth Estimation via Transfer Learning6Scaled-YOLOv4: Scaling Cross Stage Partial Network(人工智能创新应用大赛)8Focal Loss for Dense Object Detection10Show, Attend and Tell: Neural Image Caption Generation with Visual Attention(人工智能创新应用大赛)11Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering12YOLOv4: Optimal Speed and Accuracy of Object Detection13Hybrid Task Cascade for Instance Segmentation图像分割
14End to End Learning for Self-Driving Cars15PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation1617ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation18Holistically-Nested Edge Detection19Unified Perceptual Parsing for Scene Understanding21DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs22Real-Time High-Resolution Background Matting(人工智能创新应用大赛)23SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation24YOLACT: Real-time Instance Segmentation(中国软件开源创新大赛)25CheXNet: Radiologist-Level Pneumonia Detection on Chest X-Rays with Deep Learning26YOLACT++: Better Real-time Instance Segmentation(中国软件开源创新大赛)27PointRend: Image Segmentation as Rendering28Context Prior for Scene Segmentation29Rethinking BiSeNet For Real-time Semantic Segmentation30ESPNetv2: A Light-weight, Power Efficient, and General Purpose Convolutional Neural Network31Progressive Growing of GANs for Improved Quality, Stability, and Variation图像分类
32Wide Residual Networks33Colorful Image Colorization34Prototypical Networks for Few-shot Learning35MLP-Mixer: An all-MLP Architecture for Vision36Deep Networks with Stochastic Depth38R-Drop: Regularized Dropout for Neural Networks图像生成
41Image Inpainting for Irregular Holes Using Partial Convolutions43Generative Adversarial Text to Image Synthesis44Conditional Image Synthesis With Auxiliary Classifier GANs45SinGAN: Learning a Generative Model from a Single Natural Image46Semantic Image Synthesis with Spatially-Adaptive Normalization47Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation(中国软件开源创新大赛)48Only a Matter of Style: Age Transformation Using a Style-Based Regression Model其他CV任务
49Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecasting51TabNet: Attentive Interpretable Tabular Learning52Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields53Towards Deep Learning Models Resistant to Adversarial Attacks54Stacked Hourglass Networks for Human Pose Estimation56Learning to See in the Dark57Deep Image Prior60Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks(中国软件开源创新大赛)61RetinaFace: Single-stage Dense Face Localisation in the Wild(人工智能创新应用大赛)63Detecting Text in Natural Image with Connectionist Text Proposal Network64Real-time Convolutional Neural Networks for Emotion and Gender Classification65PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models自然语言处理&语音
68A Structured Self-attentive Sentence Embedding69End-To-End Memory Networks71Character-level Convolutional Networks for Text Classification72Recipes for building an open-domain chatbot73ConvBERT: Improving BERT with Span-based Dynamic Convolution81MobileBERT: a Compact Task-Agnostic BERT for Resource-Limited Devices(中国软件开源创新大赛)82MPNet: Masked and Permuted Pre-training for Language Understanding85Reformer: The Efficient Transformer86SqueezeBERT: What can computer vision teach NLP about efficient neural networks?87Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer88VisualBERT: A Simple and Performant Baseline for Vision and Language90ChineseBERT: Chinese Pretraining Enhanced by Glyph and Pinyin Information推荐
92Field-Embedded Factorization Machines for Click-through rate prediction93Deep Learning Recommendation Model for Personalization and Recommendation Systems94A Dual Input-aware Factorization Machine for CTR Prediction(中国软件开源创新大赛)96FAT-DeepFFM: Field Attentive Deep Field-aware Factorization Machine97BERT4Rec:Sequential Recommendation with Bidirectional Encoder Representations from Transformer(中国软件开源创新大赛)98Personalized Top-N Sequential Recommendation via Convolutional Sequence Embedding99SASRec:Self-Attentive Sequential Recommendation人工智能创新应用大赛
101Panoptic Feature Pyramid Networks103ClassSR: A General Framework to Accelerate Super-Resolution Networks by Data Characteristic104Neural Collaborative Reasoning105Weight Uncertainty in Neural Networks中国软件开源创新大赛
109Supervised Contrastive Learning110CTRL: A Conditional Transformer Language Model for Controllable Generation《飞桨开发者说》- 论文分享专题
111Exploring Cross-Image Pixel Contrast for Semantic Segmentation113Category-Level Adversarial Adaptation for Semantic Segmentation using Purified Features