ObjectNet

Dataset Information
Modalities
Images
Introduced
2019
License
Creative Commons Attribution 4.0
Homepage
Official Website
Contents

Overview

ObjectNet is a test set of images collected directly using crowd-sourcing. ObjectNet is unique as the objects are captured at unusual poses in cluttered, natural scenes, which can severely degrade recognition performance. There are 50,000 images in the test set which controls for rotation, background and viewpoint. There are 313 object classes with 113 overlapping ImageNet.

Source: On Robustness and Transferability of Convolutional Neural Networks
Image Source: https://objectnet.dev/

Variants: ObjectNet, ObjectNet (Bounding Box)

Associated Benchmarks

This dataset is used in 2 benchmarks:

Recent Benchmark Submissions

Task Model Paper Date
Zero-Shot Transfer Image Classification EVA-CLIP-18B EVA-CLIP-18B: Scaling CLIP to 18 … 2024-02-06
Zero-Shot Transfer Image Classification InternVL-C InternVL: Scaling up Vision Foundation … 2023-12-21
Image Classification EVA-02-CLIP-E/14+ EVA-CLIP: Improved Training Techniques for … 2023-03-27
Zero-Shot Transfer Image Classification EVA-CLIP-E/14+ EVA-CLIP: Improved Training Techniques for … 2023-03-27
Image Classification MAWS (ViT-H) The effectiveness of MAE pre-pretraining … 2023-03-23
Image Classification MAWS (ViT-2B) The effectiveness of MAE pre-pretraining … 2023-03-23
Image Classification MAWS (ViT-6.5B) The effectiveness of MAE pre-pretraining … 2023-03-23
Zero-Shot Transfer Image Classification LiT-22B Scaling Vision Transformers to 22 … 2023-02-10
Image Classification LLE (ViT-H/14, MAE, Edge Aug) A Whac-A-Mole Dilemma: Shortcuts Come … 2022-12-09
Image Classification ViT-e PaLI: A Jointly-Scaled Multilingual Language-Image … 2022-09-14
Zero-Shot Transfer Image Classification LiT ViT-e PaLI: A Jointly-Scaled Multilingual Language-Image … 2022-09-14
Zero-Shot Transfer Image Classification PaLI PaLI: A Jointly-Scaled Multilingual Language-Image … 2022-09-14
Image Classification ViT-B (Opt Relevance) Optimizing Relevance Maps of Vision … 2022-06-02
Image Classification ViT-L Optimizing Relevance Maps of Vision … 2022-06-02
Image Classification AR-B Optimizing Relevance Maps of Vision … 2022-06-02
Image Classification AR-S Optimizing Relevance Maps of Vision … 2022-06-02
Image Classification DeiT-S (Opt Relevance) Optimizing Relevance Maps of Vision … 2022-06-02
Image Classification DeiT-L (Opt Relevance) Optimizing Relevance Maps of Vision … 2022-06-02
Image Classification AR-L (Opt Relevance) Optimizing Relevance Maps of Vision … 2022-06-02
Image Classification AR-B (Opt Relevance) Optimizing Relevance Maps of Vision … 2022-06-02

Research Papers

Recent papers with results on this dataset:

External Links: