Dynamic Pre-training: Towards Efficient and Scalable All-in-One Image Restoration

• URL: http://arxiv.org/abs/2404.02154v2
• Date: Sun, 13 Oct 2024 14:26:56 GMT
• Title: Dynamic Pre-training: Towards Efficient and Scalable All-in-One Image Restoration
• Authors: Akshay Dudhane, Omkar Thawakar, Syed Waqas Zamir, Salman Khan, Fahad Shahbaz Khan, Ming-Hsuan Yang,
• Abstract summary: All-in-one image restoration tackles different types of degradations with a unified model instead of having task-specific, non-generic models for each degradation. We propose DyNet, a dynamic family of networks designed in an encoder-decoder style for all-in-one image restoration tasks. Our DyNet can seamlessly switch between its bulkier and lightweight variants, thereby offering flexibility for efficient model deployment.
• Score: 100.54419875604721
• License:
• Abstract: All-in-one image restoration tackles different types of degradations with a unified model instead of having task-specific, non-generic models for each degradation. The requirement to tackle multiple degradations using the same model can lead to high-complexity designs with fixed configuration that lack the adaptability to more efficient alternatives. We propose DyNet, a dynamic family of networks designed in an encoder-decoder style for all-in-one image restoration tasks. Our DyNet can seamlessly switch between its bulkier and lightweight variants, thereby offering flexibility for efficient model deployment with a single round of training. This seamless switching is enabled by our weights-sharing mechanism, forming the core of our architecture and facilitating the reuse of initialized module weights. Further, to establish robust weights initialization, we introduce a dynamic pre-training strategy that trains variants of the proposed DyNet concurrently, thereby achieving a 50% reduction in GPU hours. Our dynamic pre-training strategy eliminates the need for maintaining separate checkpoints for each variant, as all models share a common set of checkpoints, varying only in model depth. This efficient strategy significantly reduces storage overhead and enhances adaptability. To tackle the unavailability of large-scale dataset required in pre-training, we curate a high-quality, high-resolution image dataset named Million-IRD, having 2M image samples. We validate our DyNet for image denoising, deraining, and dehazing in all-in-one setting, achieving state-of-the-art results with 31.34\% reduction in GFlops and a 56.75\% reduction in parameters compared to baseline models. The source codes and trained models are available at https://github.com/akshaydudhane16/DyNet.

Related papers

• Any Image Restoration with Efficient Automatic Degradation Adaptation [132.81912195537433]
  We propose a unified manner to achieve joint embedding by leveraging the inherent similarities across various degradations for efficient and comprehensive restoration. Our network sets new SOTA records while reducing model complexity by approximately -82% in trainable parameters and -85% in FLOPs.
  arXiv  Detail & Related papers  (2024-07-18T10:26:53Z)
• Dynamic Encoder Size Based on Data-Driven Layer-wise Pruning for Speech Recognition [24.71497121634708]
  Varying-size models are often required to deploy ASR systems under different hardware and/or application constraints. We present the dynamic encoder size approach, which jointly trains multiple performant models within one supernet from scratch.
  arXiv  Detail & Related papers  (2024-07-10T08:35:21Z)
• DyCE: Dynamically Configurable Exiting for Deep Learning Compression and Real-time Scaling [1.8350044465969415]
  DyCE can adjust the performance-complexity trade-off of a deep learning model at runtime without requiring re-initialization or redeployment on inference hardware. DyCE significantly reduces computational complexity by 23.5% for ResNet152 and 25.9% for ConvNextv2-tiny on ImageNet, with accuracy reductions of less than 0.5%.
  arXiv  Detail & Related papers  (2024-03-04T03:09:28Z)
• SortedNet: A Scalable and Generalized Framework for Training Modular Deep Neural Networks [30.069353400127046]
  We propose SortedNet to harness the inherent modularity of deep neural networks (DNNs) SortedNet enables the training of sub-models simultaneously along with the training of the main model. It is able to train 160 sub-models at once, achieving at least 96% of the original model's performance.
  arXiv  Detail & Related papers  (2023-09-01T05:12:25Z)
• Iterative Soft Shrinkage Learning for Efficient Image Super-Resolution [91.3781512926942]
  Image super-resolution (SR) has witnessed extensive neural network designs from CNN to transformer architectures. This work investigates the potential of network pruning for super-resolution iteration to take advantage of off-the-shelf network designs and reduce the underlying computational overhead. We propose a novel Iterative Soft Shrinkage-Percentage (ISS-P) method by optimizing the sparse structure of a randomly network at each and tweaking unimportant weights with a small amount proportional to the magnitude scale on-the-fly.
  arXiv  Detail & Related papers  (2023-03-16T21:06:13Z)
• 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)
• DS-Net++: Dynamic Weight Slicing for Efficient Inference in CNNs and Transformers [105.74546828182834]
  We show a hardware-efficient dynamic inference regime, named dynamic weight slicing, which adaptively slice a part of network parameters for inputs with diverse difficulty levels. We present dynamic slimmable network (DS-Net) and dynamic slice-able network (DS-Net++) by input-dependently adjusting filter numbers of CNNs and multiple dimensions in both CNNs and transformers.
  arXiv  Detail & Related papers  (2021-09-21T09:57:21Z)
• Manifold Regularized Dynamic Network Pruning [102.24146031250034]
  This paper proposes a new paradigm that dynamically removes redundant filters by embedding the manifold information of all instances into the space of pruned networks. The effectiveness of the proposed method is verified on several benchmarks, which shows better performance in terms of both accuracy and computational cost.
  arXiv  Detail & Related papers  (2021-03-10T03:59:03Z)
• Glance and Focus: a Dynamic Approach to Reducing Spatial Redundancy in Image Classification [46.885260723836865]
  Deep convolutional neural networks (CNNs) generally improve when fueled with high resolution images. Inspired by the fact that not all regions in an image are task-relevant, we propose a novel framework that performs efficient image classification. Our framework is general and flexible as it is compatible with most of the state-of-the-art light-weighted CNNs.
  arXiv  Detail & Related papers  (2020-10-11T17:55:06Z)

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.