microsoft / ORBIT-Dataset
The ORBIT dataset is a collection of videos of objects in clean and cluttered scenes recorded by people who are blind/low-vision on a mobile phone. The dataset is presented with a teachable object recognition benchmark task which aims to drive few-shot learning on challenging real-world data.
☆102Updated 7 months ago
Alternatives and similar repositories for ORBIT-Dataset:
Users that are interested in ORBIT-Dataset are comparing it to the libraries listed below
- Repository providing a wide range of self-supervised pretrained models for computer vision tasks.☆62Updated 4 years ago
- [NeurIPS 2021] ORL: Unsupervised Object-Level Representation Learning from Scene Images☆58Updated 3 years ago
- Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities☆78Updated 3 years ago
- Localized Narratives☆82Updated 3 years ago
- ☆47Updated 4 years ago
- This repository provides data for the VAW dataset as described in the CVPR 2021 paper titled "Learning to Predict Visual Attributes in th…☆63Updated 2 years ago
- A task-agnostic vision-language architecture as a step towards General Purpose Vision☆92Updated 3 years ago
- Official implementation of "Towards Good Practices for Efficiently Annotating Large-Scale Image Classification Datasets" (CVPR2021)☆54Updated 3 years ago
- [NeurIPS 2022] Official PyTorch implementation of Optimizing Relevance Maps of Vision Transformers Improves Robustness. This code allows …☆127Updated 2 years ago
- Filtering, Distillation, and Hard Negatives for Vision-Language Pre-Training☆136Updated 2 years ago
- [NeurIPS 2022] The official implementation of "Learning to Discover and Detect Objects".☆110Updated last year
- ☆32Updated 3 years ago
- Introduction and scripts for the paper "PartImageNet: A Large, High-Quality Dataset of Parts" (Ju He, Shuo Yang, Shaokang Yang, Adam Kort…☆123Updated 2 weeks ago
- Object-aware Contrastive Learning for Debiased Scene Representation (NeurIPS 2021)☆45Updated 3 years ago
- ☆8Updated 2 years ago
- [ECCV2022] New benchmark for evaluating pre-trained model; New supervised contrastive learning framework.☆107Updated last year
- CLIP-Art: Contrastive Pre-training for Fine-Grained Art Classification - 4th Workshop on Computer Vision for Fashion, Art, and Design☆27Updated 2 years ago
- MetaShift: A Dataset of Datasets for Evaluating Contextual Distribution Shifts and Training Conflicts (ICLR 2022)☆109Updated 2 years ago
- Official repository for "Revisiting Weakly Supervised Pre-Training of Visual Perception Models". https://arxiv.org/abs/2201.08371.☆179Updated 2 years ago
- State-of-the-art pretrained vision model from Bing Multimedia☆18Updated last year
- ☆66Updated 3 years ago
- Patching open-vocabulary models by interpolating weights☆91Updated last year
- Code associated with paper "Wandering Within a World: Online Contextualized Few-Shot Learning"☆25Updated 3 years ago
- [ICCV 2021] Official Pytorch implementation for Discriminative Region-based Multi-Label Zero-Shot Learning SOTA results on NUS-WIDE and …☆62Updated 3 years ago
- Official repository for the General Robust Image Task (GRIT) Benchmark☆54Updated 2 years ago
- HIRL: A General Framework for Hierarchical Image Representation Learning (http://arxiv.org/abs/2205.13159)☆40Updated 2 years ago
- Simple library to automatically visualize graph structures, especially scene graphs.☆47Updated 5 years ago
- A unified framework to jointly model images, text, and human attention traces.☆78Updated 3 years ago
- Command-line tool for downloading and extending the RedCaps dataset.☆46Updated last year
- Compressing Representations for Self-Supervised Learning☆78Updated 4 years ago