A Spitting Image: Modular Superpixel Tokenization in Vision Transformers

• URL: http://arxiv.org/abs/2408.07680v2
• Date: Thu, 15 Aug 2024 12:07:00 GMT
• Title: A Spitting Image: Modular Superpixel Tokenization in Vision Transformers
• Authors: Marius Aasan, Odd Kolbjørnsen, Anne Schistad Solberg, Adín Ramirez Rivera,
• Abstract summary: Vision Transformer (ViT) architectures traditionally employ a grid-based approach to tokenization independent of the semantic content of an image. We propose a modular superpixel tokenization strategy which decouples tokenization and feature extraction.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Vision Transformer (ViT) architectures traditionally employ a grid-based approach to tokenization independent of the semantic content of an image. We propose a modular superpixel tokenization strategy which decouples tokenization and feature extraction; a shift from contemporary approaches where these are treated as an undifferentiated whole. Using on-line content-aware tokenization and scale- and shape-invariant positional embeddings, we perform experiments and ablations that contrast our approach with patch-based tokenization and randomized partitions as baselines. We show that our method significantly improves the faithfulness of attributions, gives pixel-level granularity on zero-shot unsupervised dense prediction tasks, while maintaining predictive performance in classification tasks. Our approach provides a modular tokenization framework commensurable with standard architectures, extending the space of ViTs to a larger class of semantically-rich models.

Related papers

• CoC-GAN: Employing Context Cluster for Unveiling a New Pathway in Image Generation [12.211795836214112]
  We propose a unique image generation process premised on the perspective of converting images into a set of point clouds. Our methodology leverages simple clustering methods named Context Clustering (CoC) to generate images from unordered point sets. We introduce this model with the novel structure as the Context Clustering Generative Adversarial Network (CoC-GAN)
  arXiv  Detail & Related papers  (2023-08-23T01:19:58Z)
• ACSeg: Adaptive Conceptualization for Unsupervised Semantic Segmentation [17.019848796027485]
  Self-supervised visual pre-training models have shown great promise in representing pixel-level semantic relationships. In this work, we investigate the pixel-level semantic aggregation in self-trained models as image encodes and design concepts. We propose the Adaptive Concept Generator (ACG) which adaptively maps these prototypes to informative concepts for each image.
  arXiv  Detail & Related papers  (2022-10-12T06:16:34Z)
• DynaST: Dynamic Sparse Transformer for Exemplar-Guided Image Generation [56.514462874501675]
  We propose a dynamic sparse attention based Transformer model to achieve fine-level matching with favorable efficiency. The heart of our approach is a novel dynamic-attention unit, dedicated to covering the variation on the optimal number of tokens one position should focus on. Experiments on three applications, pose-guided person image generation, edge-based face synthesis, and undistorted image style transfer, demonstrate that DynaST achieves superior performance in local details.
  arXiv  Detail & Related papers  (2022-07-13T11:12:03Z)
• Semantic Image Synthesis via Diffusion Models [159.4285444680301]
  Denoising Diffusion Probabilistic Models (DDPMs) have achieved remarkable success in various image generation tasks. Recent work on semantic image synthesis mainly follows the emphde facto Generative Adversarial Nets (GANs)
  arXiv  Detail & Related papers  (2022-06-30T18:31:51Z)
• Modeling Image Composition for Complex Scene Generation [77.10533862854706]
  We present a method that achieves state-of-the-art results on layout-to-image generation tasks. After compressing RGB images into patch tokens, we propose the Transformer with Focal Attention (TwFA) for exploring dependencies of object-to-object, object-to-patch and patch-to-patch.
  arXiv  Detail & Related papers  (2022-06-02T08:34:25Z)
• Adaptive Single Image Deblurring [43.02281823557039]
  We propose an efficient pixel adaptive and feature attentive design for handling large blur variations within and across different images. We also propose an effective content-aware global-local filtering module that significantly improves the performance.
  arXiv  Detail & Related papers  (2022-01-01T10:10:19Z)
• Bi-level Feature Alignment for Versatile Image Translation and Manipulation [88.5915443957795]
  Generative adversarial networks (GANs) have achieved great success in image translation and manipulation. High-fidelity image generation with faithful style control remains a grand challenge in computer vision. This paper presents a versatile image translation and manipulation framework that achieves accurate semantic and style guidance.
  arXiv  Detail & Related papers  (2021-07-07T05:26:29Z)
• Less is More: Pay Less Attention in Vision Transformers [61.05787583247392]
  Less attention vIsion Transformer builds upon the fact that convolutions, fully-connected layers, and self-attentions have almost equivalent mathematical expressions for processing image patch sequences. The proposed LIT achieves promising performance on image recognition tasks, including image classification, object detection and instance segmentation.
  arXiv  Detail & Related papers  (2021-05-29T05:26:07Z)
• Self-supervised Augmentation Consistency for Adapting Semantic Segmentation [56.91850268635183]
  We propose an approach to domain adaptation for semantic segmentation that is both practical and highly accurate. We employ standard data augmentation techniques $-$ photometric noise, flipping and scaling $-$ and ensure consistency of the semantic predictions. We achieve significant improvements of the state-of-the-art segmentation accuracy after adaptation, consistent both across different choices of the backbone architecture and adaptation scenarios.
  arXiv  Detail & Related papers  (2021-04-30T21:32:40Z)
• Deep Transformation-Invariant Clustering [24.23117820167443]
  We present an approach that does not rely on abstract features but instead learns to predict image transformations. This learning process naturally fits in the gradient-based training of K-means and Gaussian mixture model. We demonstrate that our novel approach yields competitive and highly promising results on standard image clustering benchmarks.
  arXiv  Detail & Related papers  (2020-06-19T13:43:08Z)
• Multi-Granularity Canonical Appearance Pooling for Remote Sensing Scene Classification [0.34376560669160383]
  We propose a novel Multi-Granularity Canonical Appearance Pooling (MG-CAP) to automatically capture the latent ontological structure of remote sensing datasets. For each specific granularity, we discover the canonical appearance from a set of pre-defined transformations and learn the corresponding CNN features through a maxout-based Siamese style architecture. We provide a stable solution for training the eigenvalue-decomposition function (EIG) in a GPU and demonstrate the corresponding back-propagation using matrix calculus.
  arXiv  Detail & Related papers  (2020-04-09T11:24:00Z)

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.