Superpixel-based Refinement for Object Proposal Generation
- Resource Type
- Conference
- Authors
- Wilms, Christian; Frintrop, Simone
- Source
- 2020 25th International Conference on Pattern Recognition (ICPR) Pattern Recognition (ICPR), 2020 25th International Conference on. :4965-4972 Jan, 2021
- Subject
- Computing and Processing
Signal Processing and Analysis
Image segmentation
Statistical analysis
Measurement uncertainty
Object segmentation
Feature extraction
Pattern recognition
Proposals
- Language
Precise segmentation of objects is an important problem in tasks like class-agnostic object proposal generation or instance segmentation. Deep learning-based systems usually generate segmentations of objects based on coarse feature maps, due to the inherent downsampling in CNNs. This leads to segmentation boundaries not adhering well to the object boundaries in the image. To tackle this problem, we introduce a new superpixel-based refinement approach 1 1 Code is available at: https://www.inf.uni-hamburg.de/spxrefinement on top of the state-of-the-art object proposal system AttentionMask. The refinement utilizes superpixel pooling for feature extraction and a novel superpixel classifier to determine if a high precision superpixel belongs to an object or not. Our experiments show an improvement of up to 26.0% in terms of average recall compared to original AttentionMask. Furthermore, qualitative and quantitative analyses of the segmentations reveal significant improvements in terms of boundary adherence for the proposed refinement compared to various deep learning-based state-of-the-art object proposal generation systems.