2023
ImageNet-Hard: The Hardest Images Remaining from a Study of the Power of Zoom and Spatial Biases in Image Classification
NeurIPS 2023poster
Image classifiers are information-discarding machines, by design. Yet, how these models discard information remains mysterious. We hypothesize that one way for image classifiers to reach high accuracy is to first zoom to the most discriminative region in the image and then extract features from ther…