合集下载：点我跳转
1、神经网络结构设计
[1]Boundary Unlearning
[Code]None
[2]Equiangular Basis Vectors
[Code]GitHub - NJUST-VIPGroup/Equiangular-Basis-Vectors
[3]LargeKernel3D: Scaling up Kernels in 3D Sparse CNNs
[4]Run, Don't Walk: Chasing Higher FLOPS for Faster Neural Networks
[Code]GitHub - JierunChen/FasterNet: [CVPR 2023] Code for PConv and FasterNet
[5]ALOFT: A Lightweight MLP-like Architecture with Dynamic Low-frequency Transform for Domain Generalization
[Code]https://github.com/lingeringlight/ALOFT/
[Area]MLP
[6]Learning 3D Representations from 2D Pre-trained Models via Image-to-Point Masked Autoencoders
[Area]MAE
[7]Compacting Binary Neural Networks by Sparse Kernel Selection
[Code]None
[8]Bridging Precision and Confidence: A Train-Time Loss for Calibrating Object Detection
[9]SMPConv: Self-moving Point Representations for Continuous Convolution
2、CNN
[1]Randomized Adversarial Training via Taylor Expansion
[Code]GitHub - Alexkael/Randomized-Adversarial-Training
[2]Alias-Free Convnets: Fractional Shift Invariance via Polynomial Activations
[Code]https://github.com/hmichaeli/alias_free_convnets/
[3]DeepMAD: Mathematical Architecture Design for Deep Convolutional Neural Network
[4]Demystify Transformers & Convolutions in Modern Image Deep Networks
[Code]GitHub - OpenGVLab/STM-Evaluation
[5]InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions
[6]VNE: An Effective Method for Improving Deep Representation by Manipulating Eigenvalue Distribution
3、Transformer
[1]POTTER: Pooling Attention Transformer for Efficient Human Mesh Recovery
[Code]POTTER: Pooling Attention Transformer for Efficient Human Mesh Recovery
[2]FeatER: An Efficient Network for Human Reconstruction via Feature Map-Based TransformER
[Code]https://zczcwh.github.io/feater_page/
[3]Spherical Transformer for LiDAR-based 3D Recognition
[4]MELTR: Meta Loss Transformer for Learning to Fine-tune Video Foundation Models
[Code]https://github.com/mlvlab/MELTR
[5]Top-Down Visual Attention from Analysis by Synthesis
[Code]https://sites.google.com/view/absvit
[6]BiFormer: Vision Transformer with Bi-Level Routing Attention
[7]Making Vision Transformers Efficient from A Token Sparsification View
[Code]None
[8]Visual Atoms: Pre-training Vision Transformers with Sinusoidal Waves
[Code]None
[9]Learning Imbalanced Data with Vision Transformers
[Code]https://github.com/XuZhengzhuo/LiVT
[10]SAP-DETR: Bridging the Gap Between Salient Points and Queries-Based Transformer Detector for Fast Model Convergency
[Code]https://github.com/liuyang-ict/SAP-DETR.
[11]Masked Jigsaw Puzzle: A Versatile Position Embedding for Vision Transformers
[12]Lite DETR : An Interleaved Multi-Scale Encoder for Efficient DETR
[Code]https://github.com/IDEA-Research/Lite-DETR
[13]Integrally Pre-Trained Transformer Pyramid Networks
[Code]GitHub - sunsmarterjie/iTPN: (CVPR2023) Integrally Pre-Trained Transformer Pyramid Networks
[14]Sparsifiner: Learning Sparse Instance-Dependent Attention for Efficient Vision Transformers
[Code]None
[15]CAT: LoCalization and IdentificAtion Cascade Detection Transformer for Open-World Object Detection
[Code]GitHub - xiaomabufei/CAT
[16]Learning Anchor Transformations for 3D Garment Animation
[Code]AnchorDEF
[17]Generalized Relation Modeling for Transformer Tracking
[Code]https://github.com/Little-Podi/GRM
[18]One-Stage 3D Whole-Body Mesh Recovery with Component Aware Transformer
[Code]One-Stage 3D Whole-Body Mesh Recovery with Component Aware Transformer
[19]Transferable Adversarial Attacks on Vision Transformers with Token Gradient Regularization
[Code]None
[20]Learning Expressive Prompting With Residuals for Vision Transformers
[Code]None
[21]Visual Dependency Transformers: Dependency Tree Emerges from Reversed Attention
[22]MethaneMapper: Spectral Absorption aware Hyperspectral Transformer for Methane Detection
[23]METransformer: Radiology Report Generation by Transformer with Multiple Learnable Expert Tokens
[Code]None
[24]Slide-Transformer: Hierarchical Vision Transformer with Local Self-Attention
[Code]GitHub - LeapLabTHU/Slide-Transformer: Official repository of Slide-Transformer (CVPR2023)
4、图神经网络(GNN)
[1]Turning Strengths into Weaknesses: A Certified Robustness Inspired Attack Framework against Graph Neural Networks
[Code]None
[2]From Node Interaction to Hop Interaction: New Effective and Scalable Graph Learning Paradigm
[Code]GitHub - JC-202/HopGNN
[3]Mind the Label Shift of Augmentation-based Graph OOD Generalization
[Code]GitHub - Samyu0304/LiSA: LiSA (CVPR 2023) is a model-agnostic Graph OOD framework.
[4]Adversarially Robust Neural Architecture Search for Graph Neural Networks
[Code]None
5、神经网络架构搜索(NAS)
[1]Polynomial Implicit Neural Representations For Large Diverse Datasets
[2]PA&DA: Jointly Sampling PAth and DAta for Consistent NAS
[Code]GitHub - ShunLu91/PA-DA: [CVPR '23] PA&DA: Jointly Sampling PAth and DAta for Consistent NAS
[3]Stitchable Neural Networks