Benjay77
Follow
Stars
Collection of notebooks for time series analysis
【三年面试五年模拟】算法工程师秘籍。涵盖AIGC、传统深度学习、自动驾驶、机器学习、计算机视觉、自然语言处理、SLAM、具身智能、元宇宙、AGI等AI行业面试笔试经验与干货知识。
[ECCV 2022] Source code of "EdgeFormer: Improving Light-weight ConvNets by Learning from Vision Transformers"
DA-TransUNet: Combining Dual Attention of Position and Channel with Transformer U-net for Medical Image Segmentation
Implementation Code for the ICCASSP 2023 paper " Efficient Multi-Scale Attention Module with Cross-Spatial Learning" and is available at: https://arxiv.org/abs/2305.13563v2
最新版本yolov5+deepsort目标检测和追踪，能够显示目标类别，支持5.0版本可训练自己数据集
A PyTorch implementation for exploring deep and shallow knowledge distillation (KD) experiments with flexibility
The official implementation of LumiNet: The Bright Side of Perceptual Knowledge Distillation https://arxiv.org/abs/2310.03669
[ICML 2024] Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model
This is the pytorch implement of the paper "RSMamba: Remote Sensing Image Classification with State Space Model"
CV-CUDA™ is an open-source, GPU accelerated library for cloud-scale image processing and computer vision.
PyTorch code and checkpoints release for OFA-KD: https://arxiv.org/abs/2310.19444
A PyTorch implementation of Sharpness-Aware Minimization for Efficiently Improving Generalization
Code for paper SENetV2 Aggregated dense layer for channelwise and global representations
Official repository for "Rethinking Transformers Pre-training for Multi-Spectral Satellite Imagery" (CVPR 2024)
Orthogonal Channel Attentions Networks
A batched offline inference oriented version of segment-anything
Effortless data labeling with AI support from Segment Anything and other awesome models.
[NeurIPS2023] Parameter-efficient Tuning of Large-scale Multimodal Foundation Model
[CVPR-2023] Primitive Generation and Semantic-related Alignment for Universal Zero-Shot Segmentation
MedSeg: Medical Image Segmentation GUI Toolbox 可视化医学图像分割工具箱
General AI methods for Anything: AnyObject, AnyGeneration, AnyModel, AnyTask, AnyX
EntitySeg Toolbox: Towards Open-World and High-Quality Image Segmentation