voxel51 / reconstruction-error-ratios
Estimate dataset difficulty and detect label mistakes using reconstruction error ratios!
☆23Updated 2 months ago
Alternatives and similar repositories for reconstruction-error-ratios:
Users that are interested in reconstruction-error-ratios are comparing it to the libraries listed below
- Code for experiments for "ConvNet vs Transformer, Supervised vs CLIP: Beyond ImageNet Accuracy"☆101Updated 6 months ago
- ☆66Updated 2 months ago
- ☆64Updated 5 months ago
- Simplify Your Visual Data Ops. Find and visualize issues with your computer vision datasets such as duplicates, anomalies, data leakage, …☆67Updated last year
- [NeurIPS2022] This is the official implementation of the paper "Expediting Large-Scale Vision Transformer for Dense Prediction without Fi…☆83Updated last year
- 4th place solution for the Google Universal Image Embedding Kaggle Challenge. Instance-Level Recognition workshop at ECCV 2022☆42Updated last year
- Timm model explorer☆38Updated 11 months ago
- Official code repository for paper: "ExPLoRA: Parameter-Efficient Extended Pre-training to Adapt Vision Transformers under Domain Shifts"☆31Updated 5 months ago
- [NeurIPS 2023] HASSOD: Hierarchical Adaptive Self-Supervised Object Detection☆55Updated last year
- Continuation of an abandoned project fast-coco-eval☆92Updated 2 months ago
- Multi-Class Few-Shot Semantic Segmentation with Visual Prompts☆49Updated 2 months ago
- Run zero-shot prediction models on your data☆31Updated 3 months ago
- ☆12Updated 9 months ago
- [ECCV 2024] Official Release of SILC: Improving vision language pretraining with self-distillation☆40Updated 5 months ago
- auto_labeler - An all-in-one library to automatically label vision data☆14Updated 2 months ago
- RO-ViT CVPR 2023 "Region-Aware Pretraining for Open-Vocabulary Object Detection with Vision Transformers"☆17Updated last year
- Supercharge Your PyTorch Image Models: Bag of Tricks to 8x Faster Inference with ONNX Runtime & Optimizations☆23Updated 5 months ago
- (CVPR 2024) Point, Segment and Count: A Generalized Framework for Object Counting☆109Updated 4 months ago
- GroundedSAM Base Model plugin for Autodistill☆49Updated 11 months ago
- Evaluate the performance of computer vision models and prompts for zero-shot models (Grounding DINO, CLIP, BLIP, DINOv2, ImageBind, model…☆35Updated last year
- ☆58Updated last year
- MobileSAM already integrated into Personalize Segment Anything Model (SAM) with 1 shot in 10 seconds☆36Updated last year
- Repository for the paper: "TiC-CLIP: Continual Training of CLIP Models".☆102Updated 9 months ago
- EfficientViT is a new family of vision models for efficient high-resolution vision.☆24Updated last year
- Visualizer for PyTorch image models☆44Updated 3 years ago
- A Contrastive Learning Boost from Intermediate Pre-Trained Representations☆41Updated 6 months ago
- ☆200Updated last year