Challenging Images For Minds and Machines

TL;DR

This paper highlights challenging visual tasks that current machine learning models and humans find difficult, arguing that simply increasing data, capacity, or computation is insufficient, and calls for new research directions.

Contribution

It identifies limitations of current models in solving certain vision problems and advocates for innovative approaches beyond scaling data and resources.

Findings

Certain vision challenges remain difficult for machines and humans.

Increasing data and capacity alone does not solve all problems.

Encourages new research directions for difficult vision tasks.

Abstract

There is no denying the tremendous leap in the performance of machine learning methods in the past half-decade. Some might even say that specific sub-fields in pattern recognition, such as machine-vision, are as good as solved, reaching human and super-human levels. Arguably, lack of training data and computation power are all that stand between us and solving the remaining ones. In this position paper we underline cases in vision which are challenging to machines and even to human observers. This is to show limitations of contemporary models that are hard to ameliorate by following the current trend to increase training data, network capacity or computational power. Moreover, we claim that attempting to do so is in principle a suboptimal approach. We provide a taster of such examples in hope to encourage and challenge the machine learning community to develop new directions to solve the said difficulties.