Texture Representations in Deep Vision Models: Comparing CNNs, Vision Transformers, and Human Perception
Department of Neuroscience International School for Advanced Studies (SISSA) Trieste Italy（神经科学系国际先进研究学院（SISSA）特里埃斯特意大利）；Department of Language and Translation Sciences Pompeu Fabra University Barcelona Spain（语言与翻译科学系庞培法布拉大学巴塞罗那西班牙）；ICREA Barcelona Spain（ICREA巴塞罗那西班牙）；Department of Data Science International School for Advanced Studies (SISSA) Trieste Italy（数据科学系国际先进研究学院（SISSA）特里埃斯特意大利）
Ludovica de Paolis, Marco Baroni, Alessandro Laio, Eugenio Piasini
In computational vision science, Convolutional Neural Networks (CNNs) have emerged as a popular model of biological vision because of the alignment they can exhibit with neural and behavioral data in humans and animals. However, it remains unclear to what extent this alignment persists for visual tasks that extend beyond the canonical object recognition paradigm based on well defined semantic content. In this study, we diverge from the common object-centric view by focusing on another aspect of vision: texture perception. We consider textures of different complexity generated with three different algorithms from the same source images. Using a rank-based statistic, we quantify the information encoded in the internal representations of a CNN and three Vision Transformers (ViTs), and we compare the similarity of these representations to those inferred from human psychophysics data. We find that the representation of textures is aligned in different ViTs, but not between the ViTs and the CNN; that ViTs form similar representations for textures of different complexity; that human performance in recognizing textures can be better predicted from ViTs representations rather than CNN representations. Taken together, these results suggest that ViTs may capture more faithfully than CNNs how texture patterns are visually processed by humans, and that the representations of texture stimuli in computational models may be driven by the network architecture.
Lausanne University Hospital（洛桑大学医院）；University of Applied Sciences Western Switzerland (HES-SO)（瑞士西部应用科学大学（HES-SO））
Convolutional Neural Networks (CNNs) traditionally encode translation equivariance via the convolution operation. Generalization to other transformations has recently received attraction to encode the knowledge of the data geometry in group convolution operations. Equivariance to rotation is particularly important for 3D image analysis due to the large diversity of possible pattern orientations. 3D texture is a particularly important cue for the analysis of medical images such as CT and MRI scans as it describes different types of tissues and lesions. In this paper, we evaluate the use of 3D g…
Ryerson University（瑞尔森大学）；Vector Institute for AI（矢量人工智能研究所）；Heidelberg University（海德堡大学）；University of Waterloo（滑铁卢大学）；University of Guelph（圭尔夫大学）；Samsung AI Centre Toronto（三星多伦多人工智能中心）
Contrasting the previous evidence that neurons in the later layers of a Convolutional Neural Network (CNN) respond to complex object shapes, recent studies have shown that CNNs actually exhibit a `texture bias': given an image with both texture and shape cues (e.g., a stylized image), a CNN is biased towards predicting the category corresponding to the texture. However, these previous studies conduct experiments on the final classification output of the network, and fail to robustly evaluate the bias contained (i) in the latent representations, and (ii) on a per-pixel level. In this paper, we …
The University of Tokyo（东京大学）；Digital Frontier Inc.（数字前沿公司）
Texture classification is an important and challenging problem in many image processing applications. While convolutional neural networks (CNNs) achieved significant successes for image classification, texture classification remains a difficult problem since textures usually do not contain enough information regarding the shape of object. In image processing, texture classification has been traditionally studied well with spectral analyses which exploit repeated structures in many textures. Since CNNs process images as-is in the spatial domain whereas spectral analyses process images in the fr…
Accurate image classification given small amounts of labelled data (few-shot classification) remains an open problem in computer vision. In this work we examine how the known texture bias of Convolutional Neural Networks (CNNs) affects few-shot classification performance. Although texture bias can help in standard image classification, in this work we show it significantly harms few-shot classification performance. After correcting this bias we demonstrate state-of-the-art performance on the competitive miniImageNet task using a method far simpler than the current best performing few-shot lear…
University of Applied Sciences Western Switzerland (HES-SO)（瑞士西部应用科学大学）；CHUV（洛桑大学医院）；Harvard School of Engineering and Applied Sciences（哈佛工程与应用科学学院）
Locally Rotation Invariant (LRI) operators have shown great potential in biomedical texture analysis where patterns appear at random positions and orientations. LRI operators can be obtained by computing the responses to the discrete rotation of local descriptors, such as Local Binary Patterns (LBP) or the Scale Invariant Feature Transform (SIFT). Other strategies achieve this invariance using Laplacian of Gaussian or steerable wavelets for instance, preventing the introduction of sampling errors during the discretization of the rotations. In this work, we obtain LRI operators via the local pr…
University of Tübingen（蒂宾根大学）；Bernstein Center for Computational Neuroscience（伯恩斯坦计算神经科学中心）；Max Planck Institute for Biological Cybernetics（马克斯·普朗克生物控制论研究所）
Here we demonstrate that the feature space of random shallow convolutional neural networks (CNNs) can serve as a surprisingly good model of natural textures. Patches from the same texture are consistently classified as being more similar then patches from different textures. Samples synthesized from the model capture spatial correlations on scales much larger then the receptive field size, and sometimes even rival or surpass the perceptual quality of state of the art texture models (but show less variability). The current state of the art in parametric texture synthesis relies on the multi-lay…
Arizona State University（亚利桑那州立大学）；Lebanese American University（黎巴嫩美国大学）
Given the outstanding progress that convolutional neural networks (CNNs) have made on natural image classification and object recognition problems, it is shown that deep learning methods can achieve very good recognition performance on many texture datasets. However, while CNNs for natural image classification/object recognition tasks have been revealed to be highly vulnerable to various types of adversarial attack methods, the robustness of deep learning methods for texture recognition is yet to be examined. In our paper, we show that there exist small image-agnostic/univesal perturbations th…
This paper presents a significant improvement for the synthesis of texture images using convolutional neural networks (CNNs), making use of constraints on the Fourier spectrum of the results. More precisely, the texture synthesis is regarded as a constrained optimization problem, with constraints conditioning both the Fourier spectrum and statistical features learned by CNNs. In contrast with existing methods, the presented method inherits from previous CNN approaches the ability to depict local structures and fine scale details, and at the same time yields coherent large scale structures, eve…
On the Relationship Between Double Descent of CNNs and Shape/Texture Bias Under Learning Process
Tokyo Denki University（东京电机大学）；Tokyo Institute of Technology（东京工业大学）；Tenchijin Inc.（天进公司）；National Institute of Advanced Industrial Science and Technology（国立先进工业技术研究所）
Perceptual misalignment of texture representations in convolutional neural networks
Neuroscience area International School for Advanced Studies (SISSA) Trieste Italy（国际先进研究学院（SISSA）神经科学部，特里埃斯特，意大利）；Department of Mathematics Informatics and Geosciences Università degli Studi di Trieste Trieste Italy（特里埃斯特大学数学、信息学和地球科学系，特里埃斯特，意大利）；Department of Data Engineering Area Science Park Trieste Italy（数据工程系，Area Science Park，特里埃斯特，意大利）
University of Tübingen（蒂宾根大学）；IMPRS-IS（国际马克斯·普朗克智能系统研究学院）
Convolutional Neural Networks (CNNs) are commonly thought to recognise objects by learning increasingly complex representations of object shapes. Some recent studies suggest a more important role of image textures. We here put these conflicting hypotheses to a quantitative test by evaluating CNNs and human observers on images with a texture-shape cue conflict. We show that ImageNet-trained CNNs are strongly biased towards recognising textures rather than shapes, which is in stark contrast to human behavioural evidence and reveals fundamentally different classification strategies. We then demon…
University of California, Los Angeles（加利福尼亚大学洛杉矶分校）；NVIDIA（英伟达）
Textures and edges contribute different information to image recognition. Edges and boundaries encode shape information, while textures manifest the appearance of regions. Despite the success of Convolutional Neural Networks (CNNs) in computer vision and medical image analysis applications, predominantly only texture abstractions are learned, which often leads to imprecise boundary delineations. In medical imaging, expert manual segmentation often relies on organ boundaries; for example, to manually segment a liver, a medical practitioner usually identifies edges first and subsequently fills i…
VORTEX: Challenging CNNs at Texture Recognition by using Vision Transformers with Orderless and Randomized Token Encodings
São Carlos Institute of Physics, University of São Paulo（圣保罗大学圣卡洛斯物理研究所）；KTH Royal Institute of Technology（瑞典皇家理工学院）；São Paulo State University（圣保罗州立大学）
University of Electronic Science and Technology of China（电子科技大学）
Many works have concentrated on visualizing and understanding the inner mechanism of convolutional neural networks (CNNs) by generating images that activate some specific neurons, which is called deep visualization. However, it is still unclear what the filters extract from images intuitively. In this paper, we propose a modified code inversion algorithm, called feature map inversion, to understand the function of filter of interest in CNNs. We reveal that every filter extracts a specific texture. The texture from higher layer contains more colours and more intricate structures. We also demons…
Evaluating Graphical Perception Capabilities of Vision Transformers
Viscom Group, Institute of Media Informatics, Ulm University（Viscom集团，媒体信息学研究所，乌尔姆大学）；ViRVIG Group, Universitat Politècnica de Catalunya - BarcelonaTech（ViRVIG集团，巴塞罗那技术大学-加泰罗尼亚理工大学）；Ulm University（乌尔姆大学）
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 s…
Recent work has indicated that, unlike humans, ImageNet-trained CNNs tend to classify images by texture rather than by shape. How pervasive is this bias, and where does it come from? We find that, when trained on datasets of images with conflicting shape and texture, CNNs learn to classify by shape at least as easily as by texture. What factors, then, produce the texture bias in CNNs trained on ImageNet? Different unsupervised training objectives and different architectures have small but significant and largely independent effects on the level of texture bias. However, all objectives and arch…
Albert Einstein College of Medicine（阿尔伯特·爱因斯坦医学院）；École Normale Supérieure（巴黎高等师范学院）；PSL University（巴黎文理研究大学）
Texture synthesis models are important tools for understanding visual processing. In particular, statistical approaches based on neurally relevant features have been instrumental in understanding aspects of visual perception and of neural coding. New deep learning-based approaches further improve the quality of synthetic textures. Yet, it is still unclear why deep texture synthesis performs so well, and applications of this new framework to probe visual perception are scarce. Here, we show that distributions of deep convolutional neural network (CNN) activations of a texture are well described…
Autonomous driving is a challenging topic that requires complex solutions in perception tasks such as recognition of road, lanes, traffic signs or lights, vehicles and pedestrians. Through years of research, computer vision has grown capable of tackling these tasks with monocular detectors that can provide remarkable detection rates with relatively low processing times. However, the recent appearance of Convolutional Neural Networks (CNNs) has revolutionized the computer vision field and has made possible approaches to perform full pixel-wise semantic segmentation in times close to real time (…
CTP-Net: Character Texture Perception Network for Document Image Forgery Localization
The College of Computer Science and Electronic Engineering, Hunan University（湖南大学计算机与电子工程学院）；The Department of Computer Science, The University of Hong Kong（香港大学计算机科学系）
Technische Universität Braunschweig（布伦瑞克工业大学）；Volkswagen Group Automation（大众汽车集团自动驾驶部门）
Enabling autonomous driving (AD) can be considered one of the biggest challenges in today's technology. AD is a complex task accomplished by several functionalities, with environment perception being one of its core functions. Environment perception is usually performed by combining the semantic information captured by several sensors, i.e., lidar or camera. The semantic information from the respective sensor can be extracted by using convolutional neural networks (CNNs) for dense prediction. In the past, CNNs constantly showed state-of-the-art performance on several vision-related tasks, such…
Taiyuan University of Technology（太原理工大学）；Durham University（杜伦大学）
Next-generation ground-based solar observations require good image quality metrics for post-facto processing techniques. Based on the assumption that texture features in solar images are multi-fractal which can be extracted by a trained deep neural network as feature maps, a new reduced-reference objective image quality metric, the perception evaluation is proposed. The perception evaluation is defined as cosine distance of Gram matrix between feature maps extracted from high resolution reference image and that from blurred images. We evaluate performance of the perception evaluation with simu…
A Comparative Survey of Vision Transformers for Feature Extraction in Texture Analysis
São Carlos Institute of Physics, University of São Paulo（圣保罗大学圣卡洛斯物理学院）；Institute of Mathematics and Computer Sciences, University of São Paulo（圣保罗大学数学与计算机科学研究所）；Institute of Biosciences, Humanities and Exact Sciences, São Paulo State University（圣保罗州立大学生物科学、人文与精确科学研究所）；Ghent University（根特大学）
本文系统比较了21种预训练视觉Transformer在纹理特征提取上的表现，发现ViTs在鲁棒性、颜色/材料纹理和属性识别等任务中普遍优于CNNs和手工模型，并指出ViT-B with DINO、BeiTv2、Swin及EfficientFormer为有前景的模型。
Aalto University School of Science（阿尔托大学科学学院）；Linköping University（林雪平大学）；Universitat Autonoma de Barcelona（巴塞罗那自治大学）；VTT Technical Research Centre of Finland Ltd（芬兰VTT技术研究中心有限公司）
Designing discriminative powerful texture features robust to realistic imaging conditions is a challenging computer vision problem with many applications, including material recognition and analysis of satellite or aerial imagery. In the past, most texture description approaches were based on dense orderless statistical distribution of local features. However, most recent approaches to texture recognition and remote sensing scene classification are based on Convolutional Neural Networks (CNNs). The d facto practice when learning these CNN models is to use RGB patches as input with training per…
École Normale Supérieure（巴黎高等师范学院）；Institut de Neurosciences de la Timone（蒂莫纳神经科学研究所）；Bournemouth University（伯恩茅斯大学）；UNIC；CNRS（法国国家科学研究中心）
A common practice to account for psychophysical biases in vision is to frame them as consequences of a dynamic process relying on optimal inference with respect to a generative model. The present study details the complete formulation of such a generative model intended to probe visual motion perception with a dynamic texture model. It is first derived in a set of axiomatic steps constrained by biological plausibility. We extend previous contributions by detailing three equivalent formulations of this texture model. First, the composite dynamic textures are constructed by the random aggregatio…
Ocean University of China（中国海洋大学）；Qingdao Agricultural University（青岛农业大学）
This paper investigates a novel task of generating texture images from perceptual descriptions. Previous work on texture generation focused on either synthesis from examples or generation from procedural models. Generating textures from perceptual attributes have not been well studied yet. Meanwhile, perceptual attributes, such as directionality, regularity and roughness are important factors for human observers to describe a texture. In this paper, we propose a joint deep network model that combines adversarial training and perceptual feature regression for texture generation, while only rand…
CNRS（法国国家科学研究中心）；UNIC（神经信息与复杂性实验室）；Ceremade（Ceremade研究中心）；Univ. Paris-Dauphine（巴黎第九大学）；Institut de Neurosciences de la Timone（蒂莫内神经科学研究所）；UMR 7289 CNRS/Aix-Marseille Université（法国国家科学研究中心/艾克斯-马赛大学 UMR 7289 联合研究单位）
Perception is often described as a predictive process based on an optimal inference with respect to a generative model. We study here the principled construction of a generative model specifically crafted to probe motion perception. In that context, we first provide an axiomatic, biologically-driven derivation of the model. This model synthesizes random dynamic textures which are defined by stationary Gaussian distributions obtained by the random aggregation of warped patterns. Importantly, we show that this model can equivalently be described as a stochastic partial differential equation. Usi…
University of Applied Sciences Constance（康斯坦茨应用技术大学）
Deep neural networks have been successfully applied to problems such as image segmentation, image super-resolution, coloration and image inpainting. In this work we propose the use of convolutional neural networks (CNN) for image inpainting of large regions in high-resolution textures. Due to limited computational resources processing high-resolution images with neural networks is still an open problem. Existing methods separate inpainting of global structure and the transfer of details, which leads to blurry results and loss of global coherence in the detail transfer step. Based on advances i…
Advanced Research Lab, NavInfo Europe（NavInfo Europe 高级研究实验室）
Convolutional Neural Networks (CNNs), architectures consisting of convolutional layers, have been the standard choice in vision tasks. Recent studies have shown that Vision Transformers (VTs), architectures based on self-attention modules, achieve comparable performance in challenging tasks such as object detection and semantic segmentation. However, the image processing mechanism of VTs is different from that of conventional CNNs. This poses several questions about their generalizability, robustness, reliability, and texture bias when used to extract features for complex tasks. To address the…
University of Massachusetts, Amherst（马萨诸塞大学阿默斯特分校）
We analyze how categories from recent FGVC challenges can be described by their textural content. The motivation is that subtle differences between species of birds or butterflies can often be described in terms of the texture associated with them and that several top-performing networks are inspired by texture-based representations. These representations are characterized by orderless pooling of second-order filter activations such as in bilinear CNNs and the winner of the iNaturalist 2018 challenge. Concretely, for each category we (i) visualize the "maximal images" by obtaining inputs x tha…
Indian Institute of Technology Madras（印度理工学院马德拉斯分校）；The University of Queensland（昆士兰大学）
Texture-based studies and designs have been in focus recently. Whisker-based multidimensional surface texture data is missing in the literature. This data is critical for robotics and machine perception algorithms in the classification and regression of textural surfaces. In this study, we present a novel sensor design to acquire multidimensional texture information. The surface texture's roughness and hardness were measured experimentally using sweeping and dabbing. Three machine learning models (SVM, RF, and MLP) showed excellent classification accuracy for the roughness and hardness of surf…
State of the art magnetic resonance (MR) image super-resolution methods (ISR) using convolutional neural networks (CNNs) leverage limited contextual information due to the limited spatial coverage of CNNs. Vision transformers (ViT) learn better global context that is helpful in generating superior quality HR images. We combine local information of CNNs and global information from ViTs for image super resolution and output super resolved images that have superior quality than those produced by state of the art methods. We include extra constraints through multiple novel loss functions that pres…
University of Massachusetts, Amherst（马萨诸塞大学阿默斯特分校）
A number of recent approaches have used deep convolutional neural networks (CNNs) to build texture representations. Nevertheless, it is still unclear how these models represent texture and invariances to categorical variations. This work conducts a systematic evaluation of recent CNN-based texture descriptors for recognition and attempts to understand the nature of invariances captured by these representations. First we show that the recently proposed bilinear CNN model [25] is an excellent general-purpose texture descriptor and compares favorably to other CNN-based descriptors on various text…
University of Michigan（密歇根大学）；Brown University（布朗大学）
Recent advancements have led to a proliferation of machine learning systems used to assist humans in a wide range of tasks. However, we are still far from accurate, reliable, and resource-efficient operations of these systems. For robot perception, convolutional neural networks (CNNs) for object detection and pose estimation are recently coming into widespread use. However, neural networks are known to suffer overfitting during training process and are less robust within unseen conditions, which are especially vulnerable to adversarial scenarios. In this work, we propose Generative Robust Infe…
Recent evidence shows that convolutional neural networks (CNNs) are biased towards textures so that CNNs are non-robust to adversarial perturbations over textures, while traditional robust visual features like SIFT (scale-invariant feature transforms) are designed to be robust across a substantial range of affine distortion, addition of noise, etc with the mimic of human perception nature. This paper aims to leverage good properties of SIFT to renovate CNN architectures towards better accuracy and robustness. We borrow the scale-space extreme value idea from SIFT, and propose extreme value pre…
Convolutional Neural Networks (CNNs) for visual tasks are believed to learn both the low-level textures and high-level object attributes, throughout the network depth. This paper further investigates the `texture bias' in CNNs. To this end, we regenerate multiple instances of training examples from each original image, through a process we call `repainting'. The repainted examples preserve the shape and structure of the regions and objects within the scenes, but diversify their texture and color. Our method can regenerate a same image at different daylight, season, or weather conditions, can h…
We study the finger vein (FV) sensor model identification task using a deep learning approach. So far, for this biometric modality, only correlation-based PRNU and texture descriptor-based methods have been applied. We employ five prominent CNN architectures covering a wide range of CNN family models, including VGG16, ResNet, and the Xception model. In addition, a novel architecture termed FV2021 is proposed in this work, which excels by its compactness and a low number of parameters to be trained. Original samples, as well as the region of interest data from eight publicly accessible FV datas…
Numerous significant progress on fisheye image rectification has been achieved through CNN. Nevertheless, constrained by a fixed receptive field, the global distribution and the local symmetry of the distortion have not been fully exploited. To leverage these two characteristics, we introduced Fishformer that processes the fisheye image as a sequence to enhance global and local perception. We tuned the Transformer according to the structural properties of fisheye images. First, the uneven distortion distribution in patches generated by the existing square slicing method confuses the network, r…
École de Technologie Supérieure (ÉTS), Université du Québec（魁北克大学高等技术学院）；Universidade Estadual de Ponta Grossa (UEPG)（蓬塔格罗萨州立大学）；Universidade Federal do Paraná (UFPR)（巴拉那联邦大学）；Pontificia Universidade Catolica do Paraná (PUCPR)（巴拉那天主教大学）
This paper presents a novel approach combining convolutional layers (CLs) and large-margin metric learning for training supervised models on small datasets for texture classification. The core of such an approach is a loss function that computes the distances between instances of interest and support vectors. The objective is to update the weights of CLs iteratively to learn a representation with a large margin between classes. Each iteration results in a large-margin discriminant model represented by support vectors based on such a representation. The advantage of the proposed approach w.r.t.…
University of Freiburg（弗莱堡大学）；Bosch Center for Artificial Intelligence（博世人工智能中心）；TU Chemnitz（开姆尼茨工业大学）
Convolutional neural networks (CNNs) learn to extract representations of complex features, such as object shapes and textures to solve image recognition tasks. Recent work indicates that CNNs trained on ImageNet are biased towards features that encode textures and that these alone are sufficient to generalize to unseen test data from the same distribution as the training data but often fail to generalize to out-of-distribution data. It has been shown that augmenting the training data with different image styles decreases this texture bias in favor of increased shape bias while at the same time…
University of Oxford（牛津大学）；University of Massachusetts, Amherst（马萨诸塞大学阿默斯特分校）
Research in texture recognition often concentrates on the problem of material recognition in uncluttered conditions, an assumption rarely met by applications. In this work we conduct a first study of material and describable texture at- tributes recognition in clutter, using a new dataset derived from the OpenSurface texture repository. Motivated by the challenge posed by this problem, we propose a new texture descriptor, D-CNN, obtained by Fisher Vector pooling of a Convolutional Neural Network (CNN) filter bank. D-CNN substantially improves the state-of-the-art in texture, mate- rial and sce…
City University of Hong Kong（香港城市大学）；Microsoft Cloud + AI（微软云与人工智能部门）
Image completion has made tremendous progress with convolutional neural networks (CNNs), because of their powerful texture modeling capacity. However, due to some inherent properties (e.g., local inductive prior, spatial-invariant kernels), CNNs do not perform well in understanding global structures or naturally support pluralistic completion. Recently, transformers demonstrate their power in modeling the long-term relationship and generating diverse results, but their computation complexity is quadratic to input length, thus hampering the application in processing high-resolution images. This…
University of California, Los Angeles（加利福尼亚大学洛杉矶分校）
This paper proposes a method to modify traditional convolutional neural networks (CNNs) into interpretable CNNs, in order to clarify knowledge representations in high conv-layers of CNNs. In an interpretable CNN, each filter in a high conv-layer represents a certain object part. We do not need any annotations of object parts or textures to supervise the learning process. Instead, the interpretable CNN automatically assigns each filter in a high conv-layer with an object part during the learning process. Our method can be applied to different types of CNNs with different structures. The clear k…
University of Glasgow（格拉斯哥大学）；University of Oxford（牛津大学）；University of California, Los Angeles（加利福尼亚大学洛杉矶分校）
Deep Convolutional Neural Networks (CNNs) have been one of the most influential recent developments in computer vision, particularly for categorization. There is an increasing demand for explainable AI as these systems are deployed in the real world. However, understanding the information represented and processed in CNNs remains in most cases challenging. Within this paper, we explore the use of new information theoretic techniques developed in the field of neuroscience to enable novel understanding of how a CNN represents information. We trained a 10-layer ResNet architecture to identify 2,0…
Universitat Pompeu Fabra（庞培法布拉大学）；University of East Anglia（东英吉利大学）
Visual illusions teach us that what we see is not always what it is represented in the physical world. Its special nature make them a fascinating tool to test and validate any new vision model proposed. In general, current vision models are based on the concatenation of linear convolutions and non-linear operations. In this paper we get inspiration from the similarity of this structure with the operations present in Convolutional Neural Networks (CNNs). This motivated us to study if CNNs trained for low-level visual tasks are deceived by visual illusions. In particular, we show that CNNs train…
Hybrid images is a technique to generate images with two interpretations that change as a function of viewing distance. It has been utilized to study multiscale processing of images by the human visual system. Using 63,000 hybrid images across 10 fruit categories, here we show that predictions of deep learning vision models qualitatively matches with the human perception of these images. Our results provide yet another evidence in support of the hypothesis that Convolutional Neural Networks (CNNs) and Transformers are good at modeling the feedforward sweep of information in the ventral stream …
