Stars
Stable Diffusion web UI
Use ChatGPT to summarize the arXiv papers. 全流程加速科研，利用chatgpt进行论文全文总结+专业翻译+润色+审稿+审稿回复
WebUI extension for ControlNet
Common used path planning algorithms with animations.
Track-Anything is a flexible and interactive tool for video object tracking and segmentation, based on Segment Anything, XMem, and E2FGVI.
a state-of-the-art-level open visual language model | 多模态预训练模型
A Python package for segmenting geospatial data with the Segment Anything Model (SAM)
CCNet: Criss-Cross Attention for Semantic Segmentation (TPAMI 2020 & ICCV 2019).
[NeurIPS 2022 Spotlight] VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training
Adapting Meta AI's Segment Anything to Downstream Tasks with Adapters and Prompts
[ECCV 2024] The official code of paper "Open-Vocabulary SAM".
[CVPR 2024 Highlight🔥] Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding
[ICML 2024] SqueezeLLM: Dense-and-Sparse Quantization
The implementation of the technical report: "Customized Segment Anything Model for Medical Image Segmentation"
Official code of "EVF-SAM: Early Vision-Language Fusion for Text-Prompted Segment Anything Model"
[ICCV2023] Segment Every Reference Object in Spatial and Temporal Spaces
RS5M: a large-scale vision language dataset for remote sensing [TGRS]
Reorder-based post-training quantization for large language model
My implementation of "Patch n’ Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution"
Make your models invariant to changes in scale.
Object detection and instance segmentation dataset for VHR remote sensing images further marked on the NWPU VHR-10 dataset and SSDD dataset according to the standard coco dataset.
Rotated Multi-Scale Interaction Network for Referring Remote Sensing Image Segmentation
[ICLR 2022] "Anti-Oversmoothing in Deep Vision Transformers via the Fourier Domain Analysis: From Theory to Practice" by Peihao Wang, Wenqing Zheng, Tianlong Chen, Zhangyang Wang
It's All In the Teacher: Zero-Shot Quantization Brought Closer to the Teacher [CVPR 2022 Oral]