JuneDylan

llama-models

Utilities intended for use with Llama models.

InCTRL

Official implementation of CVPR'24 paper 'Toward Generalist Anomaly Detection via In-context Residual Learning with Few-shot Sample Prompts'.

AnomalyGPT

[AAAI 2024 Oral] AnomalyGPT: Detecting Industrial Anomalies Using Large Vision-Language Models

VisionTS

Code for our paper "VisionTS: Visual Masked Autoencoders Are Free-Lunch Zero-Shot Time Series Forecasters".

CFWD

CLIPSelf

[ICLR2024 Spotlight] Code Release of CLIPSelf: Vision Transformer Distills Itself for Open-Vocabulary Dense Prediction

ovsam

[ECCV 2024] The official code of paper "Open-Vocabulary SAM".

LLNs-for-Early-Breast-Cancer-Detection

This repo introduces a novel approach utilizing Liquid Neural Networks (LNNs) for early breast cancer diagnosis.

cross_modal_adaptation

Cross-modal few-shot adaptation with CLIP

LNN-cancer-classification

Liquid neural networks for cancer image classification

LFTDet

[ISJ] Official code for "A Fourier-Transform-Based Framework with Asymptotic Attention for Mobile Thermal InfraRed Object Detection"

Mamba-YOLO

the official pytorch implementation of “Mamba-YOLO：SSMs-based for Object Detection”

ultralyticsPro

🔥🔥🔥专注于改进YOLOv8模型，NEW - YOLOv8 🚀 RT-DETR 🥇 in PyTorch >, Support to improve backbone, neck, head, loss, IoU, NMS and other modules🚀

pykan

Kolmogorov Arnold Networks

CSNorm

[ICCV 2023] Official Implementation of "Generalized Lightness Adaptation with Channel Selective Normalization"

nd-Mamba2-torch

Only implemented through torch: "bi - mamba2" , "vision- mamba2 -torch". support 1d/2d/3d/nd and support export by jit.script/onnx;

flux

Official inference repo for FLUX.1 models

flux

Application Architecture for Building User Interfaces

Track-Anything

Track-Anything is a flexible and interactive tool for video object tracking and segmentation, based on Segment Anything, XMem, and E2FGVI.

ChangeCLIP

omnimotion

T-Rex

[ECCV2024] API code for T-Rex2: Towards Generic Object Detection via Text-Visual Prompt Synergy

OV-DINO

Official implementation of OV-DINO: Unified Open-Vocabulary Detection with Language-Aware Selective Fusion

YOLOv8-multi-task

CLAP

CLAP: Isolating Content from Style through Contrastive Learning with Augmented Prompts

AnomalyCLIP

Official implementation for AnomalyCLIP (ICLR 2024)

LightenDiffusion

Official pytorch implementation for "LightenDiffusion: Unsupervised Low-Light Image Enhancement with Latent-Retinex Diffusion Models"

V2L-Tokenizer

Defect_Spectrum

Defect Spectrum: A Granular Look of Large-Scale Defect Datasets with Rich Semantics [ECCV2024]

masa

Official Implementation of CVPR24 highligt paper: Matching Anything by Segmenting Anything