Lighten CARAFE: Dynamic Lightweight Upsampling with Guided Reassemble Kernels

• URL: http://arxiv.org/abs/2410.22139v1
• Date: Tue, 29 Oct 2024 15:35:14 GMT
• Title: Lighten CARAFE: Dynamic Lightweight Upsampling with Guided Reassemble Kernels
• Authors: Ruigang Fu, Qingyong Hu, Xiaohu Dong, Yinghui Gao, Biao Li, Ping Zhong,
• Abstract summary: We propose a lightweight upsampling operation, termed Dynamic Lightweight Upsampling (DLU) Experiments on several mainstream vision tasks show that our DLU achieves comparable and even better performance to the original CARAFE.
• Score: 18.729177307412645
• License:
• Abstract: As a fundamental operation in modern machine vision models, feature upsampling has been widely used and investigated in the literatures. An ideal upsampling operation should be lightweight, with low computational complexity. That is, it can not only improve the overall performance but also not affect the model complexity. Content-aware Reassembly of Features (CARAFE) is a well-designed learnable operation to achieve feature upsampling. Albeit encouraging performance achieved, this method requires generating large-scale kernels, which brings a mass of extra redundant parameters, and inherently has limited scalability. To this end, we propose a lightweight upsampling operation, termed Dynamic Lightweight Upsampling (DLU) in this paper. In particular, it first constructs a small-scale source kernel space, and then samples the large-scale kernels from the kernel space by introducing learnable guidance offsets, hence avoiding introducing a large collection of trainable parameters in upsampling. Experiments on several mainstream vision tasks show that our DLU achieves comparable and even better performance to the original CARAFE, but with much lower complexity, e.g., DLU requires 91% fewer parameters and at least 63% fewer FLOPs (Floating Point Operations) than CARAFE in the case of 16x upsampling, but outperforms the CARAFE by 0.3% mAP in object detection. Code is available at https://github.com/Fu0511/Dynamic-Lightweight-Upsampling.

Related papers

• Learning to Upsample by Learning to Sample [19.849631293898693]
  We present DySample, an ultra-lightweight and effective dynamic upsampler. Compared with former kernel-based dynamic upsamplers, DySample requires no customized package and has much fewer parameters. DySample outperforms other upsamplers across five dense prediction tasks.
  arXiv  Detail & Related papers  (2023-08-29T07:50:11Z)
• SqueezeLLM: Dense-and-Sparse Quantization [80.32162537942138]
  Main bottleneck for generative inference with LLMs is memory bandwidth, rather than compute, for single batch inference. We introduce SqueezeLLM, a post-training quantization framework that enables lossless compression to ultra-low precisions of up to 3-bit. Our framework incorporates two novel ideas: (i) sensitivity-based non-uniform quantization, which searches for the optimal bit precision assignment based on second-order information; and (ii) the Dense-and-Sparse decomposition that stores outliers and sensitive weight values in an efficient sparse format.
  arXiv  Detail & Related papers  (2023-06-13T08:57:54Z)
• Ultra-High-Definition Low-Light Image Enhancement: A Benchmark and Transformer-Based Method [51.30748775681917]
  We consider the task of low-light image enhancement (LLIE) and introduce a large-scale database consisting of images at 4K and 8K resolution. We conduct systematic benchmarking studies and provide a comparison of current LLIE algorithms. As a second contribution, we introduce LLFormer, a transformer-based low-light enhancement method.
  arXiv  Detail & Related papers  (2022-12-22T09:05:07Z)
• CUF: Continuous Upsampling Filters [25.584630142930123]
  In this paper, we consider one of the most important operations in image processing: upsampling. We propose to parameterize upsampling kernels as neural fields. This parameterization leads to a compact architecture that obtains a 40-fold reduction in the number of parameters when compared with competing arbitrary-scale super-resolution architectures.
  arXiv  Detail & Related papers  (2022-10-13T12:45:51Z)
• BIMS-PU: Bi-Directional and Multi-Scale Point Cloud Upsampling [60.257912103351394]
  We develop a new point cloud upsampling pipeline called BIMS-PU. We decompose the up/downsampling procedure into several up/downsampling sub-steps by breaking the target sampling factor into smaller factors. We show that our method achieves superior results to state-of-the-art approaches.
  arXiv  Detail & Related papers  (2022-06-25T13:13:37Z)
• Hybrid Pixel-Unshuffled Network for Lightweight Image Super-Resolution [64.54162195322246]
  Convolutional neural network (CNN) has achieved great success on image super-resolution (SR) Most deep CNN-based SR models take massive computations to obtain high performance. We propose a novel Hybrid Pixel-Unshuffled Network (HPUN) by introducing an efficient and effective downsampling module into the SR task.
  arXiv  Detail & Related papers  (2022-03-16T20:10:41Z)
• GhostSR: Learning Ghost Features for Efficient Image Super-Resolution [49.393251361038025]
  Single image super-resolution (SISR) system based on convolutional neural networks (CNNs) achieves fancy performance while requires huge computational costs. We propose to use shift operation to generate the redundant features (i.e., Ghost features) of SISR models. We show that both the non-compact and lightweight SISR models embedded in our proposed module can achieve comparable performance to that of their baselines.
  arXiv  Detail & Related papers  (2021-01-21T10:09:47Z)
• Learning Affinity-Aware Upsampling for Deep Image Matting [83.02806488958399]
  We show that learning affinity in upsampling provides an effective and efficient approach to exploit pairwise interactions in deep networks. In particular, results on the Composition-1k matting dataset show that A2U achieves a 14% relative improvement in the SAD metric against a strong baseline. Compared with the state-of-the-art matting network, we achieve 8% higher performance with only 40% model complexity.
  arXiv  Detail & Related papers  (2020-11-29T05:09:43Z)

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.