Exemplary Natural Images Explain CNN Activations Better than State-of-the-Art Feature Visualization | 0 | 0.34 | 2021 |
How Well do Feature Visualizations Support Causal Understanding of CNN Activations? | 0 | 0.34 | 2021 |
Exemplary Natural Images Explain CNN Activations Better than State-of-the-Art Feature Visualization. | 0 | 0.34 | 2021 |
Partial success in closing the gap between human and machine vision. | 0 | 0.34 | 2021 |
Shortcut Learning In Deep Neural Networks | 10 | 0.62 | 2020 |
Beyond accuracy: quantifying trial-by-trial behaviour of CNNs and humans by measuring error consistency | 1 | 0.35 | 2020 |
ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness. | 0 | 0.34 | 2019 |
Generalisation in humans and deep neural networks. | 6 | 0.45 | 2018 |
ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness. | 33 | 0.75 | 2018 |
Comparing deep neural networks against humans: object recognition when the signal gets weaker. | 16 | 0.65 | 2017 |
Methods and measurements to compare men against machines. | 1 | 0.36 | 2017 |
An Automatized Heider-Simmel Story Generation Tool. | 0 | 0.34 | 2015 |