UNet--: Memory-Efficient and Feature-Enhanced Network Architecture based on U-Net with Reduced Skip-Connections

• URL: http://arxiv.org/abs/2412.18276v1
• Date: Tue, 24 Dec 2024 08:38:34 GMT
• Title: UNet--: Memory-Efficient and Feature-Enhanced Network Architecture based on U-Net with Reduced Skip-Connections
• Authors: Lingxiao Yin, Wei Tao, Dongyue Zhao, Tadayuki Ito, Kinya Osa, Masami Kato, Tse-Wei Chen,
• Abstract summary: U-Net models with encoder, decoder, and skip-connections components have demonstrated effectiveness in a variety of vision tasks. It is necessary to maintain the feature maps used by the skip-connections in memory before the decoding stage. We propose a universal method and architecture to reduce the memory consumption and generate enhanced feature maps to improve network performance.
• Score: 9.919381070435525
• License:
• Abstract: U-Net models with encoder, decoder, and skip-connections components have demonstrated effectiveness in a variety of vision tasks. The skip-connections transmit fine-grained information from the encoder to the decoder. It is necessary to maintain the feature maps used by the skip-connections in memory before the decoding stage. Therefore, they are not friendly to devices with limited resource. In this paper, we propose a universal method and architecture to reduce the memory consumption and meanwhile generate enhanced feature maps to improve network performance. To this end, we design a simple but effective Multi-Scale Information Aggregation Module (MSIAM) in the encoder and an Information Enhancement Module (IEM) in the decoder. The MSIAM aggregates multi-scale feature maps into single-scale with less memory. After that, the aggregated feature maps can be expanded and enhanced to multi-scale feature maps by the IEM. By applying the proposed method on NAFNet, a SOTA model in the field of image restoration, we design a memory-efficient and feature-enhanced network architecture, UNet--. The memory demand by the skip-connections in the UNet-- is reduced by 93.3%, while the performance is improved compared to NAFNet. Furthermore, we show that our proposed method can be generalized to multiple visual tasks, with consistent improvements in both memory consumption and network accuracy compared to the existing efficient architectures.

Related papers

• SMOF: Streaming Modern CNNs on FPGAs with Smart Off-Chip Eviction [6.800641017055453]
  This paper introduces weight and activation eviction mechanisms to off-chip memory along the computational pipeline. The proposed mechanism is incorporated into an existing toolflow, expanding the design space by utilising off-chip memory as a buffer. SMOF has demonstrated the capacity to deliver competitive and, in some cases, state-of-the-art performance across a spectrum of computer vision tasks.
  arXiv  Detail & Related papers  (2024-03-27T18:12:24Z)
• Universal Recurrent Event Memories for Streaming Data [0.0]
  We propose a new event memory architecture (MemNet) for recurrent neural networks. MemNet stores key-value pairs, which separate the information for addressing and for content. MemNet architecture can be applied without modifications to scalar time series, logic operators on strings, and also to natural language processing.
  arXiv  Detail & Related papers  (2023-07-28T17:40:58Z)
• EasyNet: An Easy Network for 3D Industrial Anomaly Detection [49.26348455493123]
  3D anomaly detection is an emerging and vital computer vision task in industrial manufacturing. We propose an easy and deployment-friendly network (called EasyNet) without using pre-trained models and memory banks. Experiments show that EasyNet achieves an anomaly detection AUROC of 92.6% without using pre-trained models and memory banks.
  arXiv  Detail & Related papers  (2023-07-26T02:46:50Z)
• MF-NeRF: Memory Efficient NeRF with Mixed-Feature Hash Table [62.164549651134465]
  We propose MF-NeRF, a memory-efficient NeRF framework that employs a Mixed-Feature hash table to improve memory efficiency and reduce training time while maintaining reconstruction quality. Our experiments with state-of-the-art Instant-NGP, TensoRF, and DVGO, indicate our MF-NeRF could achieve the fastest training time on the same GPU hardware with similar or even higher reconstruction quality.
  arXiv  Detail & Related papers  (2023-04-25T05:44:50Z)
• ThreshNet: An Efficient DenseNet using Threshold Mechanism to Reduce Connections [1.2542322096299672]
  We propose a new network architecture using threshold mechanism to further optimize the method of connections. ThreshNet achieves up to 60% reduction in inference time compared to DenseNet, and up to 35% faster training speed and 20% reduction in error rate.
  arXiv  Detail & Related papers  (2022-01-09T13:52:16Z)
• Memory-Guided Semantic Learning Network for Temporal Sentence Grounding [55.31041933103645]
  We propose a memory-augmented network that learns and memorizes the rarely appeared content in TSG tasks. MGSL-Net consists of three main parts: a cross-modal inter-action module, a memory augmentation module, and a heterogeneous attention module.
  arXiv  Detail & Related papers  (2022-01-03T02:32:06Z)
• Continual Learning Approach for Improving the Data and Computation Mapping in Near-Memory Processing System [3.202860612193139]
  We propose an artificially intelligent memory mapping scheme, AIMM, that optimize data placement and resource utilization through page and computation remapping. AIMM uses a neural network to achieve a near-optimal mapping during execution, trained using a reinforcement learning algorithm. Our experimental evaluation shows that AIMM improves the baseline NMP performance in single and multiple program scenario by up to 70% and 50%, respectively.
  arXiv  Detail & Related papers  (2021-04-28T09:50:35Z)
• Dynamic Graph: Learning Instance-aware Connectivity for Neural Networks [78.65792427542672]
  Dynamic Graph Network (DG-Net) is a complete directed acyclic graph, where the nodes represent convolutional blocks and the edges represent connection paths. Instead of using the same path of the network, DG-Net aggregates features dynamically in each node, which allows the network to have more representation ability.
  arXiv  Detail & Related papers  (2020-10-02T16:50:26Z)
• Improving Memory Utilization in Convolutional Neural Network Accelerators [16.340620299847384]
  We propose a mapping method that allows activation layers to overlap and thus utilize the memory more efficiently. Experiments with various real-world object detector networks show that the proposed mapping technique can decrease the activations memory by up to 32.9%. For higher resolution de-noising networks, we achieve activation memory savings of 48.8%.
  arXiv  Detail & Related papers  (2020-07-20T09:34:36Z)
• Multi-Scale Boosted Dehazing Network with Dense Feature Fusion [92.92572594942071]
  We propose a Multi-Scale Boosted Dehazing Network with Dense Feature Fusion based on the U-Net architecture. We show that the proposed model performs favorably against the state-of-the-art approaches on the benchmark datasets as well as real-world hazy images.
  arXiv  Detail & Related papers  (2020-04-28T09:34:47Z)
• ResNeSt: Split-Attention Networks [86.25490825631763]
  We present a modularized architecture, which applies the channel-wise attention on different network branches to leverage their success in capturing cross-feature interactions and learning diverse representations. Our model, named ResNeSt, outperforms EfficientNet in accuracy and latency trade-off on image classification.
  arXiv  Detail & Related papers  (2020-04-19T20:40:31Z)

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.