mrbulb

A_Hybrid_Bandit_Model_with_Visual_Priors_for_Creative_Ranking

A Hybrid Bandit Model with Visual Priors for Creative Ranking in Display Advertising

GenerateU

[CVPR2024] Generative Region-Language Pretraining for Open-Ended Object Detection

veScale

A PyTorch Native LLM Training Framework

ovsam

[arXiv preprint] The official code of paper "Open-Vocabulary SAM".

tokenize-anything

[ECCV 2024] Tokenize Anything via Prompting

mmyolo

OpenMMLab YOLO series toolbox and benchmark. Implemented RTMDet, RTMDet-Rotated,YOLOv5, YOLOv6, YOLOv7, YOLOv8,YOLOX, PPYOLOE, etc.

RepViT

RepViT: Revisiting Mobile CNN From ViT Perspective [CVPR 2024] and RepViT-SAM: Towards Real-Time Segmenting Anything

PoseAnything

RecSysPapers

推荐/广告/搜索领域工业界经典以及最前沿论文集合。A collection of industry classics and cutting-edge papers in the field of recommendation/advertising/search.

SATrans

The source code for our paper "Scenario-Adaptive Feature Interaction for Click-Through Rate Prediction" (accepted by KDD2023 Applied Science Track), which proposes a model for Multi-Scenario/Multi-Domain Recommendation.

imsearch

基于特征点匹配的相似图片搜索

ACG2vec

ACG2vec (Anime Comics Games to vector) are committed to creating a playground that combines ACG and Deep learning.（文本语义检索、以图搜图、语义搜图、图片超分辨率、推荐系统）

aliproduct-BLIP-cvpr2023

Aliproduct competition solution

Awesome-Open-Vocabulary

(TPAMI 2024) A Survey on Open Vocabulary Learning

anylabeling

Effortless AI-assisted data labeling with AI support from YOLO, Segment Anything, MobileSAM!!

MobileSAM

This is the official code for MobileSAM project that makes SAM lightweight for mobile applications and beyond!

FastSAM

Fast Segment Anything

OvarNet

OvarNet official implement of the paper "OvarNet: Towards Open-vocabulary Object Attribute Recognition"

autodistill

Images to inference with no labeling (use foundation models to train supervised models).

OFA

Official repository of OFA (ICML 2022). Paper: OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework

mPLUG-Owl

mPLUG-Owl & mPLUG-Owl2: Modularized Multimodal Large Language Model

CVPR2023-FMC-workshop

aliproduct_challenge_cvpr2022

sam-hq

Segment Anything in High Quality [NeurIPS 2023]

zozo-shift15m

SHIFT15M: Fashion-specific dataset for set-to-set matching with several distribution shifts

DeepFashion2

DeepFashion2 Dataset https://arxiv.org/pdf/1901.07973.pdf

Grounded-Segment-Anything

Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything

recognize-anything

Open-source and strong foundation image recognition models.

Awesome-Anything

General AI methods for Anything: AnyObject, AnyGeneration, AnyModel, AnyTask, AnyX

styledrop.github.io