What has my classifier learned? Visualizing the classification rules of bag-of-feature model by support region detection

27 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.

HOGgles: Visualizing Object Detection Features (2013, background): “2 [21] S. Wang, L. Zhang, Y. Liang, and Q. Pan.”
Analyzing Classifiers: Fisher Vectors and Deep Neural Networks (2015, background): “So do [28] explain predictions for Bag of Word (BoW) features with hard mapping (Vector Quantization) and Histogram Intersection kernels, and [16] identifies image regions critical for the prediction of a linear SVM classifier with max-pooling feature aggregation algorithm.”
Self-taught object localization with deep networks (2014, background): “Liu and Wang [20] have also analyzed what a classifier has learned but for the specific case of bag of features and SVM.”
Explainable Artificial Intelligence: a Systematic Review (2020, methodology): “Similarly, the Restricted Support Region Set (RSRS) Detection method [171] visualizes a set of size-restricted and non-overlapping regions of an image that are critical to classification.”
Interpretable human action recognition in compressed domain (2017, background): “[14] – describing a system to explain models incorporating vector quantization, histogram intersection kernels and SVMs – or the work of [15] – presenting an algorithm for identifying connected image regions (support regions) critical for the prediction of a linear classifier on top of a max-pooling”