Explorations in Texture Learning

• URL: http://arxiv.org/abs/2403.09543v1
• Date: Thu, 14 Mar 2024 16:30:52 GMT
• Title: Explorations in Texture Learning
• Authors: Blaine Hoak, Patrick McDaniel,
• Abstract summary: We build texture-object associations that uncover new insights about the relationships between texture and object classes in CNNs. Our analysis demonstrates that investigations in texture learning enable new methods for interpretability and have the potential to uncover unexpected biases.
• Score: 1.9567015559455132
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In this work, we investigate \textit{texture learning}: the identification of textures learned by object classification models, and the extent to which they rely on these textures. We build texture-object associations that uncover new insights about the relationships between texture and object classes in CNNs and find three classes of results: associations that are strong and expected, strong and not expected, and expected but not present. Our analysis demonstrates that investigations in texture learning enable new methods for interpretability and have the potential to uncover unexpected biases.

Related papers

• On Synthetic Texture Datasets: Challenges, Creation, and Curation [1.9567015559455132]
  We create a dataset of 362,880 texture images that span 56 textures. During the process of generating images, we find that NSFW safety filters in image generation pipelines are highly sensitive to texture.
  arXiv  Detail & Related papers  (2024-09-16T14:02:18Z)
• TextureDreamer: Image-guided Texture Synthesis through Geometry-aware Diffusion [64.49276500129092]
  TextureDreamer is an image-guided texture synthesis method. It can transfer relightable textures from a small number of input images to target 3D shapes across arbitrary categories.
  arXiv  Detail & Related papers  (2024-01-17T18:55:49Z)
• TexPose: Neural Texture Learning for Self-Supervised 6D Object Pose Estimation [55.94900327396771]
  We introduce neural texture learning for 6D object pose estimation from synthetic data. We learn to predict realistic texture of objects from real image collections. We learn pose estimation from pixel-perfect synthetic data.
  arXiv  Detail & Related papers  (2022-12-25T13:36:32Z)
• Artificial Text Detection via Examining the Topology of Attention Maps [58.46367297712477]
  We propose three novel types of interpretable topological features for this task based on Topological Data Analysis (TDA) We empirically show that the features derived from the BERT model outperform count- and neural-based baselines up to 10% on three common datasets. The probing analysis of the features reveals their sensitivity to the surface and syntactic properties.
  arXiv  Detail & Related papers  (2021-09-10T12:13:45Z)
• Unsupervised Learning of 3D Object Categories from Videos in the Wild [75.09720013151247]
  We focus on learning a model from multiple views of a large collection of object instances. We propose a new neural network design, called warp-conditioned ray embedding (WCR), which significantly improves reconstruction. Our evaluation demonstrates performance improvements over several deep monocular reconstruction baselines on existing benchmarks.
  arXiv  Detail & Related papers  (2021-03-30T17:57:01Z)
• Deep Texture-Aware Features for Camouflaged Object Detection [69.84122372541506]
  This paper formulates texture-aware refinement modules to learn the texture-aware features in a deep convolutional neural network. We evaluate our network on the benchmark dataset for camouflaged object detection both qualitatively and quantitatively.
  arXiv  Detail & Related papers  (2021-02-05T04:38:32Z)
• Describing Textures using Natural Language [32.076605062485605]
  Textures in natural images can be characterized by color, shape, periodicity of elements within them, and other attributes that can be described using natural language. We study the problem of describing visual attributes of texture on a novel dataset containing rich descriptions of textures. We present visualizations of several fine-grained domains and show that texture attributes learned on our dataset offer improvements over expert-designed attributes on the Caltech-UCSD Birds dataset.
  arXiv  Detail & Related papers  (2020-08-03T20:37:35Z)
• Reverse Engineering Configurations of Neural Text Generation Models [86.9479386959155]
  The study of artifacts that emerge in machine generated text as a result of modeling choices is a nascent research area. We conduct an extensive suite of diagnostic tests to observe whether modeling choices leave detectable artifacts in the text they generate. Our key finding, which is backed by a rigorous set of experiments, is that such artifacts are present and that different modeling choices can be inferred by observing the generated text alone.
  arXiv  Detail & Related papers  (2020-04-13T21:02:44Z)
• Fabric Surface Characterization: Assessment of Deep Learning-based Texture Representations Using a Challenging Dataset [12.747154890227721]
  We introduce a new, large-scale challenging microscopic material surface dataset (CoMMonS) We then conduct a comprehensive evaluation of state-of-the-art deep learning-based methods for texture classification using CoMMonS. Our results show that, in comparison with the state-of-the-art deep texture descriptors, MuLTER yields higher accuracy not only on our CoMMonS dataset for material characterization, but also on established datasets such as MINC-2500 and GTOS-mobile for material recognition.
  arXiv  Detail & Related papers  (2020-03-16T05:37:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.