Part-Stacked CNN for Fine-Grained Visual Categorization

12/26/2015
by   Shaoli Huang, et al.
0

In the context of fine-grained visual categorization, the ability to interpret models as human-understandable visual manuals is sometimes as important as achieving high classification accuracy. In this paper, we propose a novel Part-Stacked CNN architecture that explicitly explains the fine-grained recognition process by modeling subtle differences from object parts. Based on manually-labeled strong part annotations, the proposed architecture consists of a fully convolutional network to locate multiple object parts and a two-stream classification network that en- codes object-level and part-level cues simultaneously. By adopting a set of sharing strategies between the computation of multiple object parts, the proposed architecture is very efficient running at 20 frames/sec during inference. Experimental results on the CUB-200-2011 dataset reveal the effectiveness of the proposed architecture, from both the perspective of classification accuracy and model interpretability.

READ FULL TEXT

page 8

page 10

research
10/04/2016

Real Time Fine-Grained Categorization with Accuracy and Interpretability

A well-designed fine-grained categorization system usually has three con...
research
05/23/2016

Mask-CNN: Localizing Parts and Selecting Descriptors for Fine-Grained Image Recognition

Fine-grained image recognition is a challenging computer vision problem,...
research
06/22/2017

Fine-Grained Categorization via CNN-Based Automatic Extraction and Integration of Object-Level and Part-Level Features

Fine-grained categorization can benefit from part-based features which r...
research
01/27/2018

Fine-grained Visual Categorization using PAIRS: Pose and Appearance Integration for Recognizing Subcategories

In Fine-grained Visual Categorization (FGVC), the differences between si...
research
12/11/2019

Fine-grained Classification of Rowing teams

Fine-grained classification tasks such as identifying different breeds o...
research
06/21/2013

Fine-Grained Visual Classification of Aircraft

This paper introduces FGVC-Aircraft, a new dataset containing 10,000 ima...
research
10/27/2019

L*ReLU: Piece-wise Linear Activation Functions for Deep Fine-grained Visual Categorization

Deep neural networks paved the way for significant improvements in image...

Please sign up or login with your details

Forgot password? Click here to reset