Networks are Slacking Off: Understanding Generalization Problem in Image Deraining

• URL: http://arxiv.org/abs/2305.15134v2
• Date: Thu, 26 Oct 2023 11:53:27 GMT
• Title: Networks are Slacking Off: Understanding Generalization Problem in Image Deraining
• Authors: Jinjin Gu, Xianzheng Ma, Xiangtao Kong, Yu Qiao, Chao Dong
• Abstract summary: Deep deraining networks consistently encounter substantial generalization issues when deployed in real-world applications. Our research offers a valuable perspective and methodology for better understanding the generalization problem in low-level vision tasks.
• Score: 47.47762916146673
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deep deraining networks consistently encounter substantial generalization issues when deployed in real-world applications, although they are successful in laboratory benchmarks. A prevailing perspective in deep learning encourages using highly complex data for training, with the expectation that richer image background content will facilitate overcoming the generalization problem. However, through comprehensive and systematic experimentation, we discover that this strategy does not enhance the generalization capability of these networks. On the contrary, it exacerbates the tendency of networks to overfit specific degradations. Our experiments reveal that better generalization in a deraining network can be achieved by simplifying the complexity of the training background images. This is because that the networks are ``slacking off'' during training, that is, learning the least complex elements in the image background and degradation to minimize training loss. When the background images are less complex than the rain streaks, the network will prioritize the background reconstruction, thereby suppressing overfitting the rain patterns and leading to improved generalization performance. Our research offers a valuable perspective and methodology for better understanding the generalization problem in low-level vision tasks and displays promising potential for practical application.

Related papers

• Revisiting the Generalization Problem of Low-level Vision Models Through the Lens of Image Deraining [26.95998539949823]
  Generalization remains a significant challenge for low-level vision models. Image deraining is selected as a case study due to its well-defined and easily decoupled structure. Our findings show that guiding networks to focus on learning the underlying image content, rather than the degradation patterns, is key to improving generalization.
  arXiv  Detail & Related papers  (2025-02-18T07:23:22Z)
• Generalization and Estimation Error Bounds for Model-based Neural Networks [78.88759757988761]
  We show that the generalization abilities of model-based networks for sparse recovery outperform those of regular ReLU networks. We derive practical design rules that allow to construct model-based networks with guaranteed high generalization.
  arXiv  Detail & Related papers  (2023-04-19T16:39:44Z)
• Deep Generalized Unfolding Networks for Image Restoration [16.943609020362395]
  We propose a Deep Generalized Unfolding Network (DGUNet) for image restoration. We integrate a gradient estimation strategy into the gradient descent step of the Proximal Gradient Descent (PGD) algorithm. Our method is superior in terms of state-of-the-art performance, interpretability, and generalizability.
  arXiv  Detail & Related papers  (2022-04-28T08:39:39Z)
• Low-light Image Enhancement by Retinex Based Algorithm Unrolling and Adjustment [50.13230641857892]
  We propose a new deep learning framework for the low-light image enhancement (LIE) problem. The proposed framework contains a decomposition network inspired by algorithm unrolling, and adjustment networks considering both global brightness and local brightness sensitivity. Experiments on a series of typical LIE datasets demonstrated the effectiveness of the proposed method, both quantitatively and visually, as compared with existing methods.
  arXiv  Detail & Related papers  (2022-02-12T03:59:38Z)
• Attention based Broadly Self-guided Network for Low light Image Enhancement [0.0]
  We propose Attention based Broadly self-guided network (ABSGN) for real world low-light image Enhancement. The proposed network is validated by many mainstream benchmark. Additional experimental results show that the proposed network outperforms most of state-of-the-art low-light image Enhancement solutions.
  arXiv  Detail & Related papers  (2021-12-12T13:11:29Z)
• Is Deep Image Prior in Need of a Good Education? [57.3399060347311]
  Deep image prior was introduced as an effective prior for image reconstruction. Despite its impressive reconstructive properties, the approach is slow when compared to learned or traditional reconstruction techniques. We develop a two-stage learning paradigm to address the computational challenge.
  arXiv  Detail & Related papers  (2021-11-23T15:08:26Z)
• Towards robust vision by multi-task learning on monkey visual cortex [6.9014416935919565]
  We jointly trained a deep network to perform image classification and to predict neural activity in macaque primary visual cortex (V1) We found that co-training on monkey V1 data leads to increased robustness despite the absence of those distortions during training. Our results also demonstrated that the network's representations become more brain-like as their robustness improves.
  arXiv  Detail & Related papers  (2021-07-29T21:55:48Z)
• Embracing the Dark Knowledge: Domain Generalization Using Regularized Knowledge Distillation [65.79387438988554]
  Lack of generalization capability in the absence of sufficient and representative data is one of the challenges that hinder their practical application. We propose a simple, effective, and plug-and-play training strategy named Knowledge Distillation for Domain Generalization (KDDG) We find that both the richer dark knowledge" from the teacher network, as well as the gradient filter we proposed, can reduce the difficulty of learning the mapping.
  arXiv  Detail & Related papers  (2021-07-06T14:08:54Z)
• LEUGAN:Low-Light Image Enhancement by Unsupervised Generative Attentional Networks [4.584570928928926]
  We propose an unsupervised generation network with attention-guidance to handle the low-light image enhancement task. Specifically, our network contains two parts: an edge auxiliary module that restores sharper edges and an attention guidance module that recovers more realistic colors. Experiments validate that our proposed algorithm performs favorably against state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-12-24T16:49:19Z)
• Single image reflection removal via learning with multi-image constraints [50.54095311597466]
  We propose a novel learning-based solution that combines the advantages of the aforementioned approaches and overcomes their drawbacks. Our algorithm works by learning a deep neural network to optimize the target with joint constraints enhanced among multiple input images. Our algorithm runs in real-time and state-of-the-art reflection removal performance on real images.
  arXiv  Detail & Related papers  (2019-12-08T06:10:49Z)

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.