# On the Texture Bias for Few-Shot CNN Segmentation

arXiv: https://arxiv.org/abs/2003.04052 · HTML: https://mlsanity.com/paper/2003.04052/

## Key facts

- Cited by 38 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Mar 2020.

## Built on by (most cited first, 30 of 38)

- [Hypercorrelation Squeeze for Few-Shot Segmentation](https://mlsanity.com/paper/2104.01538/) (2021)
- [Simpler is Better: Few-shot Semantic Segmentation with Classifier Weight Transformer](https://mlsanity.com/paper/2108.03032/) (2021)
- [Self-Support Few-Shot Semantic Segmentation](https://mlsanity.com/paper/2207.11549/) (2022)
- [HiFormer: Hierarchical Multi-scale Representations Using Transformers for Medical Image Segmentation](https://mlsanity.com/paper/2207.08518/) (2022)
- [Self-Guided and Cross-Guided Learning for Few-Shot Segmentation](https://mlsanity.com/paper/2103.16129/) (2021)
- [Mining Latent Classes for Few-shot Segmentation](https://mlsanity.com/paper/2103.15402/) (2021)
- [Dense Cross-Query-and-Support Attention Weighted Mask Aggregation for Few-Shot Segmentation](https://mlsanity.com/paper/2207.08549/) (2022)
- [TransDeepLab: Convolution-Free Transformer-based DeepLab v3+ for Medical Image Segmentation](https://mlsanity.com/paper/2208.00713/) (2022)
- [Few-shot Segmentation with Optimal Transport Matching and Message Flow](https://mlsanity.com/paper/2108.08518/) (2021)
- [TransNorm: Transformer Provides a Strong Spatial Normalization Mechanism for a Deep Segmentation Model](https://mlsanity.com/paper/2207.13415/) (2022)
- [SMU-Net: Style matching U-Net for brain tumor segmentation with missing modalities](https://mlsanity.com/paper/2204.02961/) (2022)
- [Beyond Self-Attention: Deformable Large Kernel Attention for Medical Image Segmentation](https://mlsanity.com/paper/2309.00121/) (2023)
- [DAE-Former: Dual Attention-guided Efficient Transformer for Medical Image Segmentation](https://mlsanity.com/paper/2212.13504/) (2022)
- [Attention Swin U-Net: Cross-Contextual Attention Mechanism for Skin Lesion Segmentation](https://mlsanity.com/paper/2210.16898/) (2022)
- [Medical Image Segmentation on MRI Images with Missing Modalities: A Review](https://mlsanity.com/paper/2203.06217/) (2022)
- [Dense Gaussian Processes for Few-Shot Segmentation](https://mlsanity.com/paper/2110.03674/) (2021)
- [Surpassing the Human Accuracy: Detecting Gallbladder Cancer from USG Images with Curriculum Learning](https://mlsanity.com/paper/2204.11433/) (2022)
- [CSWin-UNet: Transformer UNet with Cross-Shaped Windows for Medical Image Segmentation](https://mlsanity.com/paper/2407.18070/) (2024)
- [MFNet: Multi-class Few-shot Segmentation Network with Pixel-wise Metric Learning](https://mlsanity.com/paper/2111.00232/) (2021)
- [Laplacian-Former: Overcoming the Limitations of Vision Transformers in Local Texture Detection](https://mlsanity.com/paper/2309.00108/) (2023)
- [CRCNet: Few-shot Segmentation with Cross-Reference and Region-Global Conditional Networks](https://mlsanity.com/paper/2208.10761/) (2022)
- [Rethinking Layer-Wise Information Allocation for Vision Foundation Model Adaptation](https://mlsanity.com/paper/2607.21973/) (2026)
- [MetaMedSeg: Volumetric Meta-learning for Few-Shot Organ Segmentation](https://mlsanity.com/paper/2109.09734/) (2021)
- [Self-supervised Few-shot Learning for Semantic Segmentation: An Annotation-free Approach](https://mlsanity.com/paper/2307.14446/) (2023)
- [Large-kernel Attention for Efficient and Robust Brain Lesion Segmentation](https://mlsanity.com/paper/2308.07251/) (2023)
- [Deep Shape-Texture Statistics for Completely Blind Image Quality Evaluation](https://mlsanity.com/paper/2401.08107/) (2024)
- [PoissonSeg: Semi-Supervised Few-Shot Medical Image Segmentation via Poisson Learning](https://mlsanity.com/paper/2108.11694/) (2021)
- [LSFSL: Leveraging Shape Information in Few-shot Learning](https://mlsanity.com/paper/2304.06672/) (2023)
- [Intervertebral Disc Labeling With Learning Shape Information, A Look Once Approach](https://mlsanity.com/paper/2204.02943/) (2022)
- [Few Shot Semantic Segmentation: a review of methodologies, benchmarks, and open challenges](https://mlsanity.com/paper/2304.05832/) (2023)

## Abstract (arXiv)

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 lowlabeled 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. The code is available at: https://github.com/rezazad68/fewshot-segmentation