ObjectNet: A large-scale bias-controlled dataset for pushing the limits of object recognition models

We collect a large real-world test set, ObjectNet, for object recognition with controls where object backgrounds, rotations, and imaging viewpoints are random. Most scientific experiments have controls, confounds which are removed from the data, to ensure that subjects cannot perform a task by exploiting trivial correlations in the data. Historically, large machine learning and computer vision datasets have lacked such controls. This has resulted in models that must be fine-tuned for new datasets and perform better on datasets than in real-world applications. When tested on ObjectNet, object detectors show a 40-45% drop in performance, with respect to their performance on other benchmarks, due to the controls for biases. Controls make ObjectNet robust to fine-tuning showing only small performance increases. We develop a highly automated platform that enables gathering datasets with controls by crowdsourcing image capturing and annotation. ObjectNet is the same size as the ImageNet test set (50,000 images), and by design does not come paired with a training set in order to encourage generalization. The dataset is both easier than ImageNet (objects are largely centered and unoccluded) and harder (due to the controls). Although we focus on object recognition here, data with controls can be gathered at scale using automated tools throughout machine learning to generate datasets that exercise models in new ways thus providing valuable feedback to researchers. This work opens up new avenues for research in generalizable, robust, and more human-like computer vision and in creating datasets where results are predictive of real-world performance.

PDF Abstract


Introduced in the Paper:


Used in the Paper:


Results from the Paper

Ranked #50 on Image Classification on ObjectNet (using extra training data)

     Get a GitHub badge
Task Dataset Model Metric Name Metric Value Global Rank Uses Extra
Training Data
Image Classification ObjectNet ResNet-152 Top-5 Accuracy 49.4 # 23
Top-1 Accuracy 29.59 # 66
Image Classification ObjectNet VGG-14 Top-5 Accuracy 37.15 # 31
Top-1 Accuracy 19.13 # 92
Image Classification ObjectNet AlexNet Top-5 Accuracy 17.6 # 36
Top-1 Accuracy 6.78 # 103
Image Classification ObjectNet Inception-v4 Top-5 Accuracy 51.98 # 20
Top-1 Accuracy 32.24 # 58
Image Classification ObjectNet PNASNet-5L Top-5 Accuracy 54.95 # 18
Top-1 Accuracy 35.63 # 51
Image Classification ObjectNet NASNet-A Top-5 Accuracy 56.05 # 16
Top-1 Accuracy 35.77 # 50