Bilinear Convolutional Neural Networks for Fine-grained Visual Recognition
We present a simple and effective architecture for fine-grained recognition called Bilinear Convolutional Neural Networks (B-CNNs). These networks represent an image as a pooled outer product of features derived from two CNNs and capture localized feature interactions in a translationally invariant...
Veröffentlicht in: | IEEE transactions on pattern analysis and machine intelligence. - 1979. - 40(2018), 6 vom: 01. Juni, Seite 1309-1322 |
---|---|
1. Verfasser: | |
Weitere Verfasser: | , |
Format: | Online-Aufsatz |
Sprache: | English |
Veröffentlicht: |
2018
|
Zugriff auf das übergeordnete Werk: | IEEE transactions on pattern analysis and machine intelligence |
Schlagworte: | Journal Article Research Support, U.S. Gov't, Non-P.H.S. Research Support, Non-U.S. Gov't |
Zusammenfassung: | We present a simple and effective architecture for fine-grained recognition called Bilinear Convolutional Neural Networks (B-CNNs). These networks represent an image as a pooled outer product of features derived from two CNNs and capture localized feature interactions in a translationally invariant manner. B-CNNs are related to orderless texture representations built on deep features but can be trained in an end-to-end manner. Our most accurate model obtains 84.1%, 79.4%, 84.5% and 91.3% per-image accuracy on the Caltech-UCSD birds [66], NABirds [63], FGVC aircraft [42], and Stanford cars [33] dataset respectively and runs at 30 frames-per-second on a NVIDIA Titan X GPU. We then present a systematic analysis of these networks and show that (1) the bilinear features are highly redundant and can be reduced by an order of magnitude in size without significant loss in accuracy, (2) are also effective for other image classification tasks such as texture and scene recognition, and (3) can be trained from scratch on the ImageNet dataset offering consistent improvements over the baseline architecture. Finally, we present visualizations of these models on various datasets using top activations of neural units and gradient-based inversion techniques. The source code for the complete system is available at http://vis-www.cs.umass.edu/bcnn |
---|---|
Beschreibung: | Date Completed 04.04.2019 Date Revised 04.04.2019 published: Print-Electronic Citation Status PubMed-not-MEDLINE |
ISSN: | 1939-3539 |
DOI: | 10.1109/TPAMI.2017.2723400 |