Imagenet

It took five years, for example, before AI systems surpassed humans on the ImageNet Large Scale Visual Recognition Challenge, established by Professor and her team in 2010.

In experiments, the researchers say they uncovered evidence iGPT and SimCLRv2 contain “significant” biases likely attributable to ImageNet’s data imbalance.

The researchers focused on three models — VGG, ResNet, and InceptionNet — that were pretrained on 1.2 million images from the open source ImageNet dataset.

The researchers used the ImageNet database to train the system with labeled images, then to test its ability to classify novel ones.

Unlike humans, ImageNet-trained CNNs tend to classify images by texture rather than by shape.

ImageNet is one of many data sets that have been extensively used by tech giants, start-ups and academic labs when they train new forms of artificial intelligence.

An illustration of their capabilities is given by the ImageNet Large Scale Visual Recognition Challenge ; this is a benchmark in object classification and detection, with millions of images and hundreds of object classes.

Performance of convolutional neural networks, on the ImageNet tests, is now close to that of humans.