visual-layer / fastdupLinks
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.
☆1,696Updated 5 months ago
Alternatives and similar repositories for fastdup
Users that are interested in fastdup are comparing it to the libraries listed below
Sorting:
- Images to inference with no labeling (use foundation models to train supervised models).☆2,300Updated last month
- SAM with text prompt☆2,257Updated last month
- Automatically find issues in image datasets and practice data-centric computer vision.☆1,098Updated 2 months ago
- FFCV: Fast Forward Computer Vision (and other ML workloads!)☆2,942Updated last year
- [NeurIPS 2023] Official implementation of the paper "Segment Everything Everywhere All at Once"☆4,624Updated 10 months ago
- Framework agnostic sliced/tiled inference + interactive ui + error analysis plots☆4,615Updated this week
- MetaSeg: Packaged version of the Segment Anything repository☆983Updated this week
- Segment Anything in High Quality [NeurIPS 2023]☆3,999Updated 6 months ago
- SAM-PT: Extending SAM to zero-shot video segmentation with point-based tracking.☆1,005Updated last year
- [ECCV 2024] Official implementation of the paper "Semantic-SAM: Segment and Recognize Anything at Any Granularity"☆2,649Updated 11 months ago
- Code release for "Detecting Twenty-thousand Classes using Image-level Supervision".☆1,953Updated last year
- Code release for "Cut and Learn for Unsupervised Object Detection and Instance Segmentation" and "VideoCutLER: Surprisingly Simple Unsupe…☆1,015Updated 3 weeks ago
- Official code for "FeatUp: A Model-Agnostic Frameworkfor Features at Any Resolution" ICLR 2024☆1,530Updated 11 months ago
- [ECCV 2024] Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"☆8,289Updated 10 months ago
- Hiera: A fast, powerful, and simple hierarchical vision transformer.☆997Updated last year
- Personalize Segment Anything Model (SAM) with 1 shot in 10 seconds☆1,587Updated 11 months ago
- Dataset Management Framework, a Python library and a CLI tool to build, analyze and manage Computer Vision datasets.☆624Updated last week
- Interactively explore unstructured datasets from your dataframe.☆1,183Updated 2 weeks ago
- [ICCV 2023] Tracking Anything with Decoupled Video Segmentation☆1,397Updated 2 months ago
- [CVPR 2023] OneFormer: One Transformer to Rule Universal Image Segmentation☆1,625Updated 8 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.☆4,070Updated 10 months ago
- Open-source and strong foundation image recognition models.☆3,296Updated 4 months ago
- Mask-Free Video Instance Segmentation [CVPR 2023]☆367Updated last year
- ICLR2024 Spotlight: curation/training code, metadata, distribution and pre-trained models for MetaCLIP; CVPR 2024: MoDE: CLIP Data Expert…☆1,463Updated 3 months ago
- Automated dense category annotation engine that serves as the initial semantic labeling for the Segment Anything dataset (SA-1B).☆2,247Updated 2 years ago
- Grounded Language-Image Pre-training☆2,439Updated last year
- [CVPR 2023] Official Implementation of X-Decoder for generalized decoding for pixel, image and language☆1,319Updated last year
- Official codebase used to develop Vision Transformer, SigLIP, MLP-Mixer, LiT and more.☆2,964Updated last month
- [CVPR 2023] Official implementation of the paper "Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segme…☆1,349Updated last year
- The toolkit to test, validate, and evaluate your models and surface, curate, and prioritize the most valuable data for labeling.☆450Updated last month