123456789asdfjkl

open_clip

An open source implementation of CLIP.

learning_research

本人的科研经验

mitsuba3

Mitsuba 3: A Retargetable Forward and Inverse Renderer

pytorch_classification

利用pytorch实现图像分类的一个完整的代码，训练，预测，TTA，模型融合，模型部署，cnn提取特征，svm或者随机森林等进行分类，模型蒸馏，一个完整的代码

LibFewShot

LibFewShot: A Comprehensive Library for Few-shot Learning. TPAMI 2023.

SimpleAICV_pytorch_training_examples

SimpleAICV:pytorch training and testing examples.

PonderV2

PonderV2: Pave the Way for 3D Foundation Model with A Universal Pre-training Paradigm

PointMamba

PointMamba: A Simple State Space Model for Point Cloud Analysis

logit-standardization-KD

[CVPR 2024 Highlight] Logit Standardization in Knowledge Distillation

Rewrite-the-Stars

[CVPR 2024] Rewrite the Stars

PointGPT

[NeurIPS 2023] PointGPT: Auto-regressively Generative Pre-training from Point Clouds

DAPT

[CVPR 2024] Dynamic Adapter Meets Prompt Tuning: Parameter-Efficient Transfer Learning for Point Cloud Analysis

TransMix

[CVPR 2022] This repository includes the official project for the paper: TransMix: Attend to Mix for Vision Transformers.

rethinking_bottleneck_design

ddae

[ICCV 2023 Oral] Official Implementation of "Denoising Diffusion Autoencoders are Unified Self-supervised Learners"

MaskPoint

[ECCV 2022] Masked Discrimination for Self-Supervised Learning on Point Clouds

UV-SAM

UV-SAM

pa-sam

PA-SAM: Prompt Adapter SAM for High-quality Image Segmentation

PCM

Point Could Mamba: Point Cloud Learning via State Space Model

UniPT

[CVPR2024] The code of "UniPT: Universal Parallel Tuning for Transfer Learning with Efficient Parameter and Memory"

XMFnet

Code for "Cross-modal Learning for Image-Guided Point Cloud Shape Completion" (NeurIPS 2022)

DTN

Official code for "Dynamic Token Normalization Improves Vision Transformer", ICLR 2022.

WeakSAM

WeakSAM: Segment Anything Meets Weakly-supervised Instance-level Recognition

CRA-PCN

[AAAI'24] CRA-PCN: Point Cloud Completion with Intra- and Inter-level Cross-Resolution Transformers

StructViT

The official repository of the paper "Learning Correlation Structures for Vision Transformers" accepted to CVPR 2024.

EViT

Official code release of our paper "EViT: An Eagle Vision Transformer with Bi-Fovea Self-Attention"

EfficientMod

[ICLR 2024 poster] Efficient Modulation for Vision Networks

HSViT

HSViT: Horizontally Scalable Vision Transformer

RLRR

Low-Rank Rescaled Vision Transformer Fine-Tuning: A Residual Design Approach, CVPR 2024

spiralmlp