A 7K Parameter Model for Underwater Image Enhancement based on Transmission Map Prior
- URL: http://arxiv.org/abs/2405.16197v1
- Date: Sat, 25 May 2024 11:58:24 GMT
- Title: A 7K Parameter Model for Underwater Image Enhancement based on Transmission Map Prior
- Authors: Fuheng Zhou, Dikai Wei, Ye Fan, Yulong Huang, Yonggang Zhang,
- Abstract summary: Deep learning models for underwater image enhancement face limitations in both lightweight and effectiveness.
In this paper, a lightweight network named lightweight selective attention network (LSNet) is proposed.
The proposed model achieves a PSNR of 97% with only 7K parameters compared to a similar attention-based model.
- Score: 13.453441079833627
- License: http://creativecommons.org/licenses/by-nc-sa/4.0/
- Abstract: Although deep learning based models for underwater image enhancement have achieved good performance, they face limitations in both lightweight and effectiveness, which prevents their deployment and application on resource-constrained platforms. Moreover, most existing deep learning based models use data compression to get high-level semantic information in latent space instead of using the original information. Therefore, they require decoder blocks to generate the details of the output. This requires additional computational cost. In this paper, a lightweight network named lightweight selective attention network (LSNet) based on the top-k selective attention and transmission maps mechanism is proposed. The proposed model achieves a PSNR of 97\% with only 7K parameters compared to a similar attention-based model. Extensive experiments show that the proposed LSNet achieves excellent performance in state-of-the-art models with significantly fewer parameters and computational resources. The code is available at https://github.com/FuhengZhou/LSNet}{https://github.com/FuhengZhou/LSNet.
Related papers
- Search for Efficient Large Language Models [52.98684997131108]
Large Language Models (LLMs) have long held sway in the realms of artificial intelligence research.
Weight pruning, quantization, and distillation have been embraced to compress LLMs, targeting memory reduction and inference acceleration.
Most model compression techniques concentrate on weight optimization, overlooking the exploration of optimal architectures.
arXiv Detail & Related papers (2024-09-25T21:32:12Z) - Low-Rank Adaption on Transformer-based Oriented Object Detector for Satellite Onboard Processing of Remote Sensing Images [5.234109158596138]
Deep learning models in satellite onboard enable real-time interpretation of remote sensing images.
This paper proposes a method based on parameter-efficient fine-tuning technology with low-rank adaptation (LoRA) module.
By fine-tuning and updating only 12.4$%$ of the model's total parameters, it is able to achieve 97$%$ to 100$%$ of the performance of full fine-tuning models.
arXiv Detail & Related papers (2024-06-04T15:00:49Z) - Dynamic Pre-training: Towards Efficient and Scalable All-in-One Image Restoration [100.54419875604721]
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.
arXiv Detail & Related papers (2024-04-02T17:58:49Z) - Do deep neural networks utilize the weight space efficiently? [2.9914612342004503]
Deep learning models like Transformers and Convolutional Neural Networks (CNNs) have revolutionized various domains, but their parameter-intensive nature hampers deployment in resource-constrained settings.
We introduce a novel concept utilizing column space and row space of weight matrices, which allows for a substantial reduction in model parameters without compromising performance.
Our approach applies to both Bottleneck and Attention layers, effectively halving the parameters while incurring only minor performance degradation.
arXiv Detail & Related papers (2024-01-26T21:51:49Z) - Edge-Cloud Cooperation for DNN Inference via Reinforcement Learning and
Supervised Learning [23.4463067406809]
An edge-cloud cooperation framework is proposed to improve inference accuracy while maintaining low inference latency.
We deploy a lightweight model on the edge and a heavyweight model on the cloud.
Our method reduces up to 78.8% inference latency and achieves higher accuracy compared with the cloud-only strategy.
arXiv Detail & Related papers (2022-10-11T06:35:45Z) - Deep learning model compression using network sensitivity and gradients [3.52359746858894]
We present model compression algorithms for both non-retraining and retraining conditions.
In the first case, we propose the Bin & Quant algorithm for compression of the deep learning models using the sensitivity of the network parameters.
In the second case, we propose our novel gradient-weighted k-means clustering algorithm (GWK)
arXiv Detail & Related papers (2022-10-11T03:02:40Z) - EdgeNeXt: Efficiently Amalgamated CNN-Transformer Architecture for
Mobile Vision Applications [68.35683849098105]
We introduce split depth-wise transpose attention (SDTA) encoder that splits input tensors into multiple channel groups.
Our EdgeNeXt model with 1.3M parameters achieves 71.2% top-1 accuracy on ImageNet-1K.
Our EdgeNeXt model with 5.6M parameters achieves 79.4% top-1 accuracy on ImageNet-1K.
arXiv Detail & Related papers (2022-06-21T17:59:56Z) - Effective Model Sparsification by Scheduled Grow-and-Prune Methods [73.03533268740605]
We propose a novel scheduled grow-and-prune (GaP) methodology without pre-training the dense models.
Experiments have shown that such models can match or beat the quality of highly optimized dense models at 80% sparsity on a variety of tasks.
arXiv Detail & Related papers (2021-06-18T01:03:13Z) - Highly Efficient Salient Object Detection with 100K Parameters [137.74898755102387]
We propose a flexible convolutional module, namely generalized OctConv (gOctConv), to efficiently utilize both in-stage and cross-stages multi-scale features.
We build an extremely light-weighted model, namely CSNet, which achieves comparable performance with about 0.2% (100k) of large models on popular object detection benchmarks.
arXiv Detail & Related papers (2020-03-12T07:00:46Z) - Model Watermarking for Image Processing Networks [120.918532981871]
How to protect the intellectual property of deep models is a very important but seriously under-researched problem.
We propose the first model watermarking framework for protecting image processing models.
arXiv Detail & Related papers (2020-02-25T18:36:18Z)
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.