Unsupervised learning of object semantic parts from internal states of CNNs by population encoding
Preprint
Abstract
We address the key question of how object part representations can be found from the internal states of CNNs that are trained for high-level tasks, such as object classification. This work provides a new unsupervised method to learn semantic parts and gives new understanding of the internal representations of CNNs. Our technique is based on the hypothesis that semantic parts are represented by populations of neurons rather than by single filters. We propose a clustering technique to extract part representations, which we call Visual Concepts. We show that visual concepts are semantically coherent in that they represent semantic parts, and visually coherent in that corresponding image patches appear very similar. Also, visual concepts provide full spatial coverage of the parts of an object, rather than a few sparse parts as is typically found in keypoint annotations. Furthermore, We treat single visual concept as part detector and evaluate it for keypoint detection using the PASCAL3D+ dataset and for part detection using our newly annotated ImageNetPart dataset. The experiments demonstrate that visual concepts can be used to detect parts. We also show that some visual concepts respond to several semantic parts, provided these parts are visually similar. Thus visual concepts have the essential properties: semantic meaning and detection capability. Note that our ImageNetPart dataset gives rich part annotations which cover the whole object, making it useful for other part-related applications.Keywords
All Related Versions
This publication has 13 references indexed in Scilit:
- Holistically-Nested Edge DetectionInternational Journal of Computer Vision, 2017
- Neural Activation Constellations: Unsupervised Part Model Discovery with Convolutional Networks2015
- The application of two-level attention models in deep convolutional neural network for fine-grained image classification2015
- Mid-level deep pattern mining2015
- Understanding deep image representations by inverting them2015
- Detect What You Can: Detecting and Representing Objects Using Holistic Models and Body Parts2014
- Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation2014
- Analyzing the Performance of Multilayer Neural Networks for Object Recognition2014
- Adaptive deconvolutional networks for mid and high level feature learning2011
- Learning a Hierarchical Deformable Template for Rapid Deformable Object ParsingIEEE Transactions on Pattern Analysis and Machine Intelligence, 2009