ProgResViT: Progressive Resolution and Width for Adaptive Vision Transformers

• URL: http://arxiv.org/abs/2609.03216v1
• Date: Wed, 02 Sep 2026 23:10:56 GMT
• Title: ProgResViT: Progressive Resolution and Width for Adaptive Vision Transformers
• Abstract summary: Vision Transformers (ViTs) typically process every image using a fixed input resolution and model width.<n>We introduce ProgResViT, an input-adaptive ViT that performs inference progressively across multiple rounds.<n>We show that a DeiT-based ProgResViT achieves 84.9% top-1 accuracy, slightly exceeding the reported DeiT-III-S accuracy.
• Score: 6.551757376525797
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Vision Transformers (ViTs) typically process every image using a fixed input resolution and model width, even though many images can be classified with substantially less computation. We introduce ProgResViT, an input-adaptive ViT that performs inference progressively across multiple rounds. The first round processes a low-resolution image with a narrow subnetwork. Inference terminates when the prediction is sufficiently confident; otherwise, the model reuses the representations produced in the current round and proceeds with a higher-resolution input and a wider subnetwork to refine its prediction. As all rounds share a single backbone, we propose Progress-Conditioned Soft Gating (PSG), which conditions token fusion and layer outputs on the current round, block, and input resolution. On image classification, applying ProgResViT to DeiT yields better accuracy-compute trade-offs than adaptive-width, adaptive-depth, and dynamic-token baselines. With knowledge distillation, a DeiT-based ProgResViT achieves 84.9% top-1 accuracy, slightly exceeding the reported DeiT-III-S accuracy under a comparable evaluation setting. We show that the same design also provides favorable accuracy-compute trade-offs for self-supervised DINO representations and downstream semantic segmentation. Code is available at https://github.com/ds-kiel/ProgResViT.

Related papers

• Fusion: A Framework for Unified Sequential Token AdaptatIon in VisiOn TraNsformers [2.604903535691346]
  Vision Transformers achieve strong image classification accuracy but process all image regions with nearly the same computation.<n>Recent adaptive inference methods reduce this cost by selectively compressing tokens or terminating inference early.<n>We introduce Fusion, a unified adaptive inference framework that coordinates token merging, early exiting, and token pruning.
  arXiv  Detail & Related papers  (2026-07-01T15:51:25Z)
• Self-supervised pretraining for an iterative image size agnostic vision transformer [60.09702846704075]
  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.
  arXiv  Detail & Related papers  (2026-04-22T09:53:28Z)
• AdaPerceiver: Transformers with Adaptive Width, Depth, and Tokens [6.989655731780402]
  We present AdaPerceiver, the first transformer architecture with unified adaptivity across depth, width, and tokens within a single model.<n>AdaPerceiver achieves 85.4% accuracy while yielding 36% higher throughput than FlexiViT-L.
  arXiv  Detail & Related papers  (2025-11-22T16:09:14Z)
• Towards Generalizable AI-Generated Image Detection via Image-Adaptive Prompt Learning [33.269644831847636]
  Image-Adaptive Prompt Learning (IAPL) is a novel paradigm that adjusts the prompts according to each input image, rather than fixing them after training.<n>IAPL achieves state-of-the-art performance, with mean accuracies of 95.61% and 96.7% on the widely used UniversalFakeDetect and GenImage datasets.
  arXiv  Detail & Related papers  (2025-08-03T05:41:24Z)
• Patch n' Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution [34.05028995319689]
  Vision Transformer (ViT) models offer flexible sequence-based modeling. Native Resolution ViT uses sequence packing during training to process inputs of arbitrary resolutions and aspect ratios. NaViT can be efficiently transferred to standard tasks such as image and video classification, object detection, and semantic segmentation.
  arXiv  Detail & Related papers  (2023-07-12T17:01:03Z)
• Getting ViT in Shape: Scaling Laws for Compute-Optimal Model Design [84.34416126115732]
  Scaling laws have been recently employed to derive compute-optimal model size (number of parameters) for a given compute duration. We advance and refine such methods to infer compute-optimal model shapes, such as width and depth, and successfully implement this in vision transformers. Our shape-optimized vision transformer, SoViT, achieves results competitive with models that exceed twice its size, despite being pre-trained with an equivalent amount of compute.
  arXiv  Detail & Related papers  (2023-05-22T13:39:28Z)
• Vision Transformer with Progressive Sampling [73.60630716500154]
  We propose an iterative and progressive sampling strategy to locate discriminative regions. When trained from scratch on ImageNet, PS-ViT performs 3.8% higher than the vanilla ViT in terms of top-1 accuracy.
  arXiv  Detail & Related papers  (2021-08-03T18:04:31Z)
• Transformer-Based Deep Image Matching for Generalizable Person Re-identification [114.56752624945142]
  We investigate the possibility of applying Transformers for image matching and metric learning given pairs of images. We find that the Vision Transformer (ViT) and the vanilla Transformer with decoders are not adequate for image matching due to their lack of image-to-image attention. We propose a new simplified decoder, which drops the full attention implementation with the softmax weighting, keeping only the query-key similarity.
  arXiv  Detail & Related papers  (2021-05-30T05:38:33Z)
• 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)
• RAIN: A Simple Approach for Robust and Accurate Image Classification Networks [156.09526491791772]
  It has been shown that the majority of existing adversarial defense methods achieve robustness at the cost of sacrificing prediction accuracy. This paper proposes a novel preprocessing framework, which we term Robust and Accurate Image classificatioN(RAIN) RAIN applies randomization over inputs to break the ties between the model forward prediction path and the backward gradient path, thus improving the model robustness. We conduct extensive experiments on the STL10 and ImageNet datasets to verify the effectiveness of RAIN against various types of adversarial attacks.
  arXiv  Detail & Related papers  (2020-04-24T02:03:56Z)

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.