Do ImageNet Classifiers Generalize to ImageNet? (Paper Explained)

Has the world overfitted to ImageNet? What if we collect another dataset in exactly the same fashion? This paper gives a surprising answer! Paper: https://ift.tt/3cUM847 Data: https://ift.tt/3cMvDqs Abstract: We build new test sets for the CIFAR-10 and ImageNet datasets. Both benchmarks have been the focus of intense research for almost a decade, raising the danger of overfitting to excessively re-used test sets. By closely following the original dataset creation processes, we test to what extent current classification models generalize to new data. We evaluate a broad range of models and find accuracy drops of 3% - 15% on CIFAR-10 and 11% - 14% on ImageNet. However, accuracy gains on the original test sets translate to larger gains on the new test sets. Our results suggest that the accuracy drops are not caused by adaptivity, but by the models' inability to generalize to slightly "harder" images than those found in the original test sets. Authors: Benjamin Recht, Rebecca Roelofs, Ludwig Schmidt, Vaishaal Shankar Links: YouTube: https://www.youtube.com/c/yannickilcher Twitter: https://twitter.com/ykilcher BitChute: https://ift.tt/38iX6OV Minds: https://ift.tt/37igBpB