On the Texture Bias for Few-Shot CNN Segmentation

Reza Azad, Abdur R. Fayjie, Claude Kauffmann, Ismail Ben Ayed, Marco Pedersoli, Jose Dolz; Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2021, pp. 2674-2683


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 and more robust models. 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.

Related Material

[pdf] [supp]
@InProceedings{Azad_2021_WACV, author = {Azad, Reza and Fayjie, Abdur R. and Kauffmann, Claude and Ben Ayed, Ismail and Pedersoli, Marco and Dolz, Jose}, title = {On the Texture Bias for Few-Shot CNN Segmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2021}, pages = {2674-2683} }