Self-supervised pretraining for an iterative image size agnostic vision transformer

• URL: http://arxiv.org/abs/2604.20392v1
• Date: Wed, 22 Apr 2026 09:53:28 GMT
• Title: Self-supervised pretraining for an iterative image size agnostic vision transformer
• Abstract summary: Vision Transformers (ViTs) dominate self-supervised learning (SSL)<n>We introduce a novel sequential-to-global SSL framework based on DINO's self-distillation objective.<n>We achieve competitive performance on ImageNet-1K and downstream classification tasks.
• Score: 60.09702846704075
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Vision Transformers (ViTs) dominate self-supervised learning (SSL). While they have proven highly effective for large-scale pretraining, they are computationally inefficient and scale poorly with image size. Consequently, foundational models like DINO are constrained to low-resolution processing. A recent foveal-inspired transformer achieves resolution agnosticism by iteratively processing a fixed-size context of multi-zoom patches. This model demonstrated promising results via supervised learning, utilizing a sequential, recurrent-like process without backpropagation through time. To unlock its potential as a foundational backbone, we introduce a novel sequential-to-global SSL framework based on DINO's self-distillation objective. Supported by an efficient integral-image patch extraction method, our approach enables large-scale pretraining for image-size agnostic vision encoders. We achieve competitive performance on ImageNet-1K and downstream classification tasks, maintaining a constant computational budget regardless of input resolution.

Related papers

• ScaleDiff: Higher-Resolution Image Synthesis via Efficient and Model-Agnostic Diffusion [7.233066974580282]
  Text-to-image diffusion models often exhibit degraded performance when generating images beyond their training resolution.<n>Recent training-free methods can mitigate this limitation, but they often require substantial computation or are incompatible with recent Diffusion Transformer models.<n>We propose ScaleDiff, a model-agnostic and highly efficient framework for extending the resolution of pretrained diffusion models without any additional training.
  arXiv  Detail & Related papers  (2025-10-29T17:17:32Z)
• Look-Around Before You Leap: High-Frequency Injected Transformer for Image Restoration [46.96362010335177]
  In this paper, we propose HIT, a simple yet effective High-frequency Injected Transformer for image restoration. Specifically, we design a window-wise injection module (WIM), which incorporates abundant high-frequency details into the feature map, to provide reliable references for restoring high-quality images. In addition, we introduce a spatial enhancement unit (SEU) to preserve essential spatial relationships that may be lost due to the computations carried out across channel dimensions in the BIM.
  arXiv  Detail & Related papers  (2024-03-30T08:05:00Z)
• HAT: Hybrid Attention Transformer for Image Restoration [59.69448362233234]
  Transformer-based methods have shown impressive performance in image restoration tasks, such as image super-resolution and denoising.<n>We propose a new Hybrid Attention Transformer (HAT) to activate more input pixels for better restoration.<n>Our HAT achieves state-of-the-art performance both quantitatively and qualitatively.
  arXiv  Detail & Related papers  (2023-09-11T05:17:55Z)
• Effective Invertible Arbitrary Image Rescaling [77.46732646918936]
  Invertible Neural Networks (INN) are able to increase upscaling accuracy significantly by optimizing the downscaling and upscaling cycle jointly. A simple and effective invertible arbitrary rescaling network (IARN) is proposed to achieve arbitrary image rescaling by training only one model in this work. It is shown to achieve a state-of-the-art (SOTA) performance in bidirectional arbitrary rescaling without compromising perceptual quality in LR outputs.
  arXiv  Detail & Related papers  (2022-09-26T22:22:30Z)
• Unsupervised Domain-Specific Deblurring using Scale-Specific Attention [0.25797036386508543]
  We propose unsupervised domain-specific deblurring using a scale-adaptive attention module (SAAM) Our network does not require supervised pairs for training, and the deblurring mechanism is primarily guided by adversarial loss. Different ablation studies show that our coarse-to-fine mechanism outperforms end-to-end unsupervised models and SAAM is able to attend better compared to attention models used in literature.
  arXiv  Detail & Related papers  (2021-12-12T07:47:45Z)
• 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)
• Scalable Visual Transformers with Hierarchical Pooling [61.05787583247392]
  We propose a Hierarchical Visual Transformer (HVT) which progressively pools visual tokens to shrink the sequence length. It brings a great benefit by scaling dimensions of depth/width/resolution/patch size without introducing extra computational complexity. Our HVT outperforms the competitive baselines on ImageNet and CIFAR-100 datasets.
  arXiv  Detail & Related papers  (2021-03-19T03:55:58Z)
• Learning to Learn Parameterized Classification Networks for Scalable Input Images [76.44375136492827]
  Convolutional Neural Networks (CNNs) do not have a predictable recognition behavior with respect to the input resolution change. We employ meta learners to generate convolutional weights of main networks for various input scales. We further utilize knowledge distillation on the fly over model predictions based on different input resolutions.
  arXiv  Detail & Related papers  (2020-07-13T04:27:25Z)

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.