Interpreting Visual Question Answering Models

12 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Explanation in Human-AI Systems: A Literature Meta-Review, Synopsis of Key Ideas and Publications, and Bibliography for Explainable AI (2019, methodology): “…have focused on visualizing, comparing, and understanding the operation of deep learning networks, with an audience of other researchers (e.g., Goyal et al., 2016abc; Karpathy et al., 2015; Kim, et al., 2016; Moeyersoms, et. al., 2016; Sadeghi, et al., 2015; Selvaraju, et al., 2017; Yosinski,…”
Nothing Else Matters: Model-Agnostic Explanations By Identifying Prediction Invariance (2016, background): “While this choice of distribution produces images that look nothing like real images (Figure 5c), it makes for more robust explanations than distributions that only hide parts of the image with gray or dark patches ([5, 11]).”
Taking a HINT: Leveraging Explanations to Make Vision and Language Models More Grounded (2019, background): “For deep networks, several works propose explanations based on internal states of the network [37, 12, 40, 26].”
Choose Your Neuron: Incorporating Domain Knowledge through Neuron-Importance (2018, background): “For deep networks, several works propose explanations based on internal states or structures of the network [34,12,37,26].”