Search Results for author:
Found 11 papers, 3 papers with code
Measuring the Importance of Temporal Features in Video Saliency
Where people look when watching videos is believed to be heavily influenced by temporal patterns.
A psychophysical evaluation of techniques for Mooney image generation
Therefore, in this study we investigated how the choice of different thresholding techniques and amount of smoothing affects the interpretability of Mooney images for human participants.
How Well do Feature Visualizations Support Causal Understanding of CNN Activations?
A precise understanding of why units in an artificial network respond to certain stimuli would constitute a big step towards explainable artificial intelligence.
Exemplary natural images explain CNN activations better than synthetic feature visualizations
Using a well-controlled psychophysical paradigm, we compare the informativeness of synthetic images \citep{olah2017feature} with a simple baseline visualization, namely exemplary natural images that also strongly activate a specific feature map.
Exemplary Natural Images Explain CNN Activations Better than State-of-the-Art Feature Visualization
Even if only a single reference image is given, synthetic images provide less information than natural images ($65\pm5\%$ vs. $73\pm4\%$).
Natural Images are More Informative for Interpreting CNN Activations than State-of-the-Art Synthetic Feature Visualizations
Using a well-controlled psychophysical paradigm, we compare the informativeness of synthetic images by Olah et al. [45] with a simple baseline visualization, namely natural images that also strongly activate a specific feature map.
Five Points to Check when Comparing Visual Perception in Humans and Machines
In the second case study, we highlight the difference between necessary and sufficient mechanisms in visual reasoning tasks.
Guiding human gaze with convolutional neural networks
Thus, manipulating fixation patterns to guide human attention is an exciting challenge in digital image processing.
Understanding Low- and High-Level Contributions to Fixation Prediction
This model achieves better performance than all models not using features pre-trained on object recognition, making it a strong baseline to assess the utility of high-level features.
Saliency Benchmarking Made Easy: Separating Models, Maps and Metrics
Here we show that no single saliency map can perform well under all metrics.
DeepGaze II: Reading fixations from deep features trained on object recognition
Here we present DeepGaze II, a model that predicts where people look in images.
