Teaching CNNs to Mimic Human Visual Cognitive Process &amp; Regularise Texture-Shape Bias

Mohla, Satyam; Nasery, Anshul; Banerjee, Biplab

doi:10.1109/icassp43922.2022.9747796

Cited by 3 publications

(1 citation statement)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In contrast, changes in architecture (e.g., using an attention layer or the biologically inspired CORnet model) did not have a clear effect. Other methods to improve the shape bias include mixing in edge maps as training stimuli and to steer the stylization of training images (Mummadi et al, 2021), applying separate textures to the foreground object and the background (Lee et al, 2022), penalizing reliance on texture with adversarial learning (Nam et al, 2021), training on a mix of sharp and blurry images (Yoshihara et al, 2021), adding a custom drop-out layer that removes activations in homogeneous areas (Shi et al, 2020), or adding new network branches that receive preprocessed input like edge-maps (Mohla et al, 2022;Ye et al, 2022).…”

Section: Classification Of Cue Conflict Stimulimentioning

confidence: 99%

Shape-selective processing in deep networks: integrating the evidence on perceptual integration

Jarvers

Neumann

2023

Front. Comput. Sci.

View full text Add to dashboard Cite

Understanding how deep neural networks resemble or differ from human vision becomes increasingly important with their widespread use in Computer Vision and as models in Neuroscience. A key aspect of human vision is shape: we decompose the visual world into distinct objects, use cues to infer their 3D geometries, and can group several object parts into a coherent whole. Do deep networks use the shape of objects similarly when they classify images? Research on this question has yielded conflicting results, with some studies showing evidence for shape selectivity in deep networks, while others demonstrated clear deficiencies. We argue that these conflicts arise from differences in experimental methods: whether studies use custom images in which only some features are available, images in which different features compete, image pairs that vary along different feature dimensions, or large sets of images to assess how representations vary overall. Each method offers a different, partial view of shape processing. After comparing their advantages and pitfalls, we propose two hypotheses that can reconcile previous results. Firstly, deep networks are sensitive to local, but not global shape. Secondly, the higher layers of deep networks discard some of the shape information that the lower layers are sensitive to. We test these hypotheses by comparing network representations for natural images and silhouettes in which local or global shape is degraded. The results support both hypotheses, but for different networks. Purely feed-forward convolutional networks are unable to integrate shape globally. In contrast, networks with residual or recurrent connections show a weak selectivity for global shape. This motivates further research into recurrent architectures for perceptual integration.

show abstract

Section: Classification Of Cue Conflict Stimulimentioning

confidence: 99%

Shape-selective processing in deep networks: integrating the evidence on perceptual integration

Jarvers

Neumann

2023

Front. Comput. Sci.

View full text Add to dashboard Cite

show abstract

Learning Shape-Invariant Representation for Generalizable Semantic Segmentation

Zhang

Tian

Liao

et al. 2023

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

Quantifying Shape and Texture Biases for Enhancing Transfer Learning in Convolutional Neural Networks

Iwata,

Okuda

2024

Signals

View full text Add to dashboard Cite

Neural networks have inductive biases owing to the assumptions associated with the selected learning algorithm, datasets, and network structure. Specifically, convolutional neural networks (CNNs) are known for their tendency to exhibit textural biases. This bias is closely related to image classification accuracy. Aligning the model’s bias with the dataset’s bias can significantly enhance performance in transfer learning, leading to more efficient learning. This study aims to quantitatively demonstrate that increasing shape bias within the network by varying kernel sizes and dilation rates improves accuracy on shape-dominant data and enables efficient learning with less data. Furthermore, we propose a novel method for quantitatively evaluating the balance between texture bias and shape bias. This method enables efficient learning by aligning the biases of the transfer learning dataset with those of the model. Systematically adjusting these biases allows CNNs to better fit data with specific biases. Compared to the original model, an accuracy improvement of up to 9.9% was observed. Our findings underscore the critical role of bias adjustment in CNN design, contributing to developing more efficient and effective image classification models.

show abstract

Teaching CNNs to Mimic Human Visual Cognitive Process & Regularise Texture-Shape Bias

Cited by 3 publications

References 14 publications

Shape-selective processing in deep networks: integrating the evidence on perceptual integration

Shape-selective processing in deep networks: integrating the evidence on perceptual integration

Learning Shape-Invariant Representation for Generalizable Semantic Segmentation

Quantifying Shape and Texture Biases for Enhancing Transfer Learning in Convolutional Neural Networks

Contact Info

Product

Resources

About