visual-layer / fastdup
fastdup is a powerful, free tool designed to rapidly generate valuable insights from image and video datasets. It helps enhance the quality of both images and labels, while significantly reducing data operation costs, all with unmatched scalability.
☆1,602Updated 2 months ago
Related projects ⓘ
Alternatives and complementary repositories for fastdup
- Images to inference with no labeling (use foundation models to train supervised models).☆1,974Updated last week
- Easily compute clip embeddings and build a clip retrieval system with them☆2,406Updated 6 months ago
- Code release for "Cut and Learn for Unsupervised Object Detection and Instance Segmentation" and "VideoCutLER: Surprisingly Simple Unsupe…☆941Updated 8 months ago
- Automatically find issues in image datasets and practice data-centric computer vision.☆1,030Updated 6 months ago
- [NeurIPS 2023] Official implementation of the paper "Segment Everything Everywhere All at Once"☆4,378Updated 2 months ago
- Segment Anything in High Quality [NeurIPS 2023]☆3,700Updated 4 months ago
- Personalize Segment Anything Model (SAM) with 1 shot in 10 seconds☆1,519Updated 3 months ago
- Easily turn large sets of image urls to an image dataset. Can download, resize and package 100M urls in 20h on one machine.☆3,704Updated 3 months ago
- [ECCV 2024] Official implementation of the paper "Semantic-SAM: Segment and Recognize Anything at Any Granularity"☆2,349Updated 3 months ago
- MetaSeg: Packaged version of the Segment Anything repository☆953Updated this week
- OneFormer: One Transformer to Rule Universal Image Segmentation, arxiv 2022 / CVPR 2023☆1,493Updated last month
- [CVPR 2023] Official Implementation of X-Decoder for generalized decoding for pixel, image and language☆1,288Updated last year
- Hiera: A fast, powerful, and simple hierarchical vision transformer.☆893Updated 8 months ago
- Automated dense category annotation engine that serves as the initial semantic labeling for the Segment Anything dataset (SA-1B).☆2,144Updated last year
- Official codebase used to develop Vision Transformer, SigLIP, MLP-Mixer, LiT and more.☆2,327Updated 2 months ago
- SAM with text prompt☆1,696Updated 3 weeks ago
- ICLR2024 Spotlight: curation/training code, metadata, distribution and pre-trained models for MetaCLIP; CVPR 2024: MoDE: CLIP Data Expert…☆1,249Updated 3 weeks ago
- Segment Anything Labelling Tool☆1,022Updated 8 months ago
- [ECCV 2024] Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"☆6,714Updated 3 months ago
- SAM-PT: Extending SAM to zero-shot video segmentation with point-based tracking.☆972Updated 9 months ago
- Robust fine-tuning of zero-shot models☆647Updated 2 years ago
- A fast, easy-to-use, production-ready inference server for computer vision supporting deployment of many popular model architectures and …☆1,357Updated this week
- A python library for self-supervised learning on images.☆3,161Updated this week
- Interactively explore unstructured datasets from your dataframe.☆1,120Updated this week
- 🦘 Explore multimedia datasets at scale☆1,042Updated last month
- This repository contains the code of the CVPR 2022 paper "Image Segmentation Using Text and Image Prompts".☆1,125Updated 10 months ago
- Official code for "FeatUp: A Model-Agnostic Frameworkfor Features at Any Resolution" ICLR 2024☆1,371Updated 4 months ago
- Grounded Language-Image Pre-training☆2,222Updated 9 months ago
- Tracking and collecting papers/projects/others related to Segment Anything.☆1,537Updated 2 months ago
- [ICCV 2023] Tracking Anything with Decoupled Video Segmentation☆1,263Updated 3 months ago