HEAL-SWIN: A Vision Transformer On The Sphere

• URL: http://arxiv.org/abs/2307.07313v2
• Date: Wed, 8 May 2024 15:49:58 GMT
• Title: HEAL-SWIN: A Vision Transformer On The Sphere
• Authors: Oscar Carlsson, Jan E. Gerken, Hampus Linander, Heiner Spieß, Fredrik Ohlsson, Christoffer Petersson, Daniel Persson,
• Abstract summary: High-resolution wide-angle fisheye images are becoming more important for robotics applications such as autonomous driving. We introduce the HEAL-SWIN transformer, which combines the highly uniform Hierarchical Equal Area iso-Latitude Pixelation grid used in astrophysics and cosmology. In HEAL-SWIN, the nested structure of the HEALPix grid is used to perform the patching and windowing operations of the SWIN transformer, enabling the network to process spherical representations with minimal computational overhead.
• Score: 4.379414115481346
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: High-resolution wide-angle fisheye images are becoming more and more important for robotics applications such as autonomous driving. However, using ordinary convolutional neural networks or vision transformers on this data is problematic due to projection and distortion losses introduced when projecting to a rectangular grid on the plane. We introduce the HEAL-SWIN transformer, which combines the highly uniform Hierarchical Equal Area iso-Latitude Pixelation (HEALPix) grid used in astrophysics and cosmology with the Hierarchical Shifted-Window (SWIN) transformer to yield an efficient and flexible model capable of training on high-resolution, distortion-free spherical data. In HEAL-SWIN, the nested structure of the HEALPix grid is used to perform the patching and windowing operations of the SWIN transformer, enabling the network to process spherical representations with minimal computational overhead. We demonstrate the superior performance of our model on both synthetic and real automotive datasets, as well as a selection of other image datasets, for semantic segmentation, depth regression and classification tasks. Our code is publicly available at https://github.com/JanEGerken/HEAL-SWIN.

Related papers

• Unifying Dimensions: A Linear Adaptive Approach to Lightweight Image Super-Resolution [6.857919231112562]
  Window-based transformers have demonstrated outstanding performance in super-resolution tasks. They exhibit higher computational complexity and inference latency than convolutional neural networks. We construct a convolution-based Transformer framework named the linear adaptive mixer network (LAMNet)
  arXiv  Detail & Related papers  (2024-09-26T07:24:09Z)
• DarSwin-Unet: Distortion Aware Encoder-Decoder Architecture [13.412728770638465]
  We present an encoder-decoder model that adapts to distortions in wide-angle lenses by leveraging the physical characteristics defined by the radial distortion profile. In contrast to the original model, which only performs classification tasks, we introduce a U-Net architecture, DarSwin-Unet, designed for pixel level tasks. Our approach enhances the model capability to handle pixel-level tasks in wide-angle fisheye images, making it more effective for real-world applications.
  arXiv  Detail & Related papers  (2024-07-24T14:52:18Z)
• Self-Supervised Pre-Training for Table Structure Recognition Transformer [25.04573593082671]
  We propose a self-supervised pre-training (SSP) method for table structure recognition transformers. We discover that the performance gap between the linear projection transformer and the hybrid CNN-transformer can be mitigated by SSP of the visual encoder in the TSR model.
  arXiv  Detail & Related papers  (2024-02-23T19:34:06Z)
• 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)
• Cross-receptive Focused Inference Network for Lightweight Image Super-Resolution [64.25751738088015]
  Transformer-based methods have shown impressive performance in single image super-resolution (SISR) tasks. Transformers that need to incorporate contextual information to extract features dynamically are neglected. We propose a lightweight Cross-receptive Focused Inference Network (CFIN) that consists of a cascade of CT Blocks mixed with CNN and Transformer.
  arXiv  Detail & Related papers  (2022-07-06T16:32:29Z)
• PnP-DETR: Towards Efficient Visual Analysis with Transformers [146.55679348493587]
  Recently, DETR pioneered the solution vision tasks with transformers, it directly translates the image feature map into the object result. Recent transformer-based image recognition model andTT show consistent efficiency gain.
  arXiv  Detail & Related papers  (2021-09-15T01:10:30Z)
• Conditional Generation of Synthetic Geospatial Images from Pixel-level and Feature-level Inputs [0.0]
  We present a conditional generative model, called VAE-Info-cGAN, for synthesizing semantically rich images simultaneously conditioned on a pixel-level condition (PLC) and a feature-level condition (FLC) The proposed model can accurately generate various forms of macroscopic aggregates across different geographic locations while conditioned only on atemporal representation of the road network.
  arXiv  Detail & Related papers  (2021-09-11T06:58:19Z)
• Global Filter Networks for Image Classification [90.81352483076323]
  We present a conceptually simple yet computationally efficient architecture that learns long-term spatial dependencies in the frequency domain with log-linear complexity. Our results demonstrate that GFNet can be a very competitive alternative to transformer-style models and CNNs in efficiency, generalization ability and robustness.
  arXiv  Detail & Related papers  (2021-07-01T17:58:16Z)
• Analogous to Evolutionary Algorithm: Designing a Unified Sequence Model [58.17021225930069]
  We explain the rationality of Vision Transformer by analogy with the proven practical Evolutionary Algorithm (EA) We propose a more efficient EAT model, and design task-related heads to deal with different tasks more flexibly. Our approach achieves state-of-the-art results on the ImageNet classification task compared with recent vision transformer works.
  arXiv  Detail & Related papers  (2021-05-31T16:20:03Z)
• Transformers Solve the Limited Receptive Field for Monocular Depth Prediction [82.90445525977904]
  We propose TransDepth, an architecture which benefits from both convolutional neural networks and transformers. This is the first paper which applies transformers into pixel-wise prediction problems involving continuous labels.
  arXiv  Detail & Related papers  (2021-03-22T18:00:13Z)
• VAE-Info-cGAN: Generating Synthetic Images by Combining Pixel-level and Feature-level Geospatial Conditional Inputs [0.0]
  We present a conditional generative model for synthesizing semantically rich images simultaneously conditioned on a pixellevel (PLC) and a featurelevel condition (FLC) Experiments on a GPS dataset show that the proposed model can accurately generate various forms of macroscopic aggregates across different geographic locations.
  arXiv  Detail & Related papers  (2020-12-08T03:46:19Z)

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.