Interpretable R-CNN

By Tianfu Wu, Xilai Li, Xi Song, Liang Dong, Bo Li. 2017

18 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.

1. Song-Chun Zhu
2. Quanshi Zhang
3. Ying Nian Wu
4. Han Hu
5. Wenguan Wang
6. Alan L. Yuille
7. Erik Nijkamp
8. Jifeng Dai

Citations in the corpus

• Unsupervised Learning of Neural Networks to Explain Neural Networks (2018, background): “For example, capsule nets [25] and interpretable RCNN [37] learned interpretable middle-layer features.”
• Explanation Methods in Deep Learning: Users, Values, Concerns and Challenges (2018, background): “, 2017), or as part of the architecture structure, in terms of operations between layers (Li et al., 2017; Wu et al., 2017; Louizos et al., 2017; Goudet et al., 2017).”
• Network Transplanting (2018, background): “In comparisons, other studies of enhancing network interpretability mainly focus on either learning disentangled, interpretable representations for filters/capsules in middle layers [27, 25, 19] or unsupervisedly learning meaningful input codes of generative networks [3, 9].”
• Learning Region Features for Object Detection (2018, methodology): “Pooling using Non-grid Bins [17,18] These methods are similar to regular pooling but change the definition of R bk in Eq.”