CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning
This work addresses the need for better diagnostic tools in visual question answering to identify model weaknesses without biases, though it is incremental as it builds on existing benchmarks.
The authors tackled the problem of evaluating visual reasoning in AI by creating CLEVR, a diagnostic dataset with minimal biases and detailed annotations to test compositional language and elementary visual reasoning. They used this dataset to analyze modern visual reasoning systems, providing insights into their abilities and limitations.
When building artificial intelligence systems that can reason and answer questions about visual data, we need diagnostic tests to analyze our progress and discover shortcomings. Existing benchmarks for visual question answering can help, but have strong biases that models can exploit to correctly answer questions without reasoning. They also conflate multiple sources of error, making it hard to pinpoint model weaknesses. We present a diagnostic dataset that tests a range of visual reasoning abilities. It contains minimal biases and has detailed annotations describing the kind of reasoning each question requires. We use this dataset to analyze a variety of modern visual reasoning systems, providing novel insights into their abilities and limitations.