On the Texture Bias for Few-Shot CNN Segmentation
Authors:
- 1 January 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2673-2682
Abstract
Despite the initial belief that Convolutional Neural Networks (CNNs) are driven by shapes to perform visual recognition tasks, recent evidence suggests that texture bias in CNNs provides higher performing models when learning on large labeled training datasets. This contrasts with the perceptual bias in the human visual cortex, which has a stronger preference towards shape components. Perceptual differences may explain why CNNs achieve human-level performance when large labeled datasets are available, but their performance significantly degrades in low-labeled data scenarios, such as few-shot semantic segmentation. To remove the texture bias in the context of few-shot learning, we propose a novel architecture that integrates a set of Difference of Gaussians (DoG) to attenuate high-frequency local components in the feature space. This produces a set of modified feature maps, whose high-frequency components are diminished at different standard deviation values of the Gaussian distribution in the spatial domain. As this results in multiple feature maps for a single image, we employ a bi-directional convolutional long-short-term-memory to efficiently merge the multi scale-space representations. We perform extensive experiments on three well-known few-shot segmentation benchmarks –Pascal i5, COCO-20i and FSS-1000– and demonstrate that our method outperforms state-of-the-art approaches in two datasets under the same conditions.Keywords
All Related Versions
This publication has 23 references indexed in Scilit:
- Meta-Seg: A Generalized Meta-Learning Framework for Multi-Class Few-Shot Semantic SegmentationIEEE Access, 2019
- Attention-Based Multi-Context Guiding for Few-Shot Semantic SegmentationProceedings of the AAAI Conference on Artificial Intelligence, 2019
- Multi-scale Discriminative Location-Aware Network for Few-Shot Semantic Segmentation2019
- Referring Image Segmentation via Recurrent Refinement Networks2018
- A multi-level convolutional LSTM model for the segmentation of left ventricle myocardium in infarcted porcine cine MR images2018
- Recurrent Fully Convolutional Networks for Video Segmentation2017
- Fully convolutional networks for semantic segmentation2015
- The Pascal Visual Object Classes (VOC) ChallengeInternational Journal of Computer Vision, 2009
- Distinctive Image Features from Scale-Invariant KeypointsInternational Journal of Computer Vision, 2004
- The importance of shape in early lexical learningCognitive Development, 1988