Guided Zoom: Questioning Network Evidence for Fine-grained Classification
Abstract
We propose Guided Zoom, an approach that utilizes spatial grounding of a model's decision to make more informed predictions. It does so by making sure the model has "the right reasons" for a prediction, defined as reasons that are coherent with those used to make similar correct decisions at training time. The reason/evidence upon which a deep convolutional neural network makes a prediction is defined to be the spatial grounding, in the pixel space, for a specific class conditional probability in the model output. Guided Zoom examines how reasonable such evidence is for each of the top-k predicted classes, rather than solely trusting the top-1 prediction. We show that Guided Zoom improves the classification accuracy of a deep convolutional neural network model and obtains state-of-the-art results on three fine-grained classification benchmark datasets.
- Publication:
-
arXiv e-prints
- Pub Date:
- December 2018
- DOI:
- 10.48550/arXiv.1812.02626
- arXiv:
- arXiv:1812.02626
- Bibcode:
- 2018arXiv181202626A
- Keywords:
-
- Computer Science - Computer Vision and Pattern Recognition
- E-Print:
- BMVC 2019 Camera Ready Version