Skip to Main content Skip to Navigation
Conference papers

Verification of Size Invariance in DNN Activations Using Concept Embeddings

Abstract : The benefits of deep neural networks (DNNs) have become of interest for safety critical applications like medical ones or automated driving. Here, however, quantitative insights into the DNN inner representations are mandatory [10]. One approach to this is concept analysis, which aims to establish a mapping between the internal representation of a DNN and intuitive semantic concepts. Such can be sub-objects like human body parts that are valuable for validation of pedestrian detection. To our knowledge, concept analysis has not yet been applied to large object detectors, specifically not for sub-parts. Therefore, this work first suggests a substantially improved version of the Net2Vec approach [5] for post-hoc segmentation of sub-objects. Its practical applicability is then demonstrated on a new concept dataset by two exemplary assessments of three standard networks, including the larger Mask R-CNN model [9]: (1) the consistency of body part similarity, and (2) the invariance of internal representations of body parts with respect to the size in pixels of the depicted person. The findings show that the representation of body parts is mostly size invariant, which may suggest an early intelligent fusion of information in different size categories.
Document type :
Conference papers
Complete list of metadata
Contributor : Hal Ifip Connect in order to contact the contributor
Submitted on : Thursday, July 15, 2021 - 6:12:24 PM
Last modification on : Friday, August 13, 2021 - 4:29:53 PM
Long-term archiving on: : Saturday, October 16, 2021 - 7:10:52 PM


 Restricted access
To satisfy the distribution rights of the publisher, the document is embargoed until : 2024-01-01

Please log in to resquest access to the document


Distributed under a Creative Commons Attribution 4.0 International License



Gesina Schwalbe. Verification of Size Invariance in DNN Activations Using Concept Embeddings. 17th IFIP International Conference on Artificial Intelligence Applications and Innovations (AIAI), Jun 2021, Hersonissos, Crete, Greece. pp.374-386, ⟨10.1007/978-3-030-79150-6_30⟩. ⟨hal-03287709⟩



Record views