paper-with-me

Papers

TinyViM: Frequency Decoupling for Tiny Hybrid Vision Mamba

2024-11-26 · Xiaowen Ma, ZhenLiang Ni, Xinghao Chen

Mamba has shown great potential for computer vision due to its linear complexity in modeling the global context with respect to the input length. However, existing lightweight Mamba-based backbones cannot demonstrate performance that matches Convolution or Transformer-based methods. We observe that simply modifying the scanning path in the image domain is not conducive to fully exploiting the potential of vision Mamba. In this paper, we first perform comprehensive spectral and quantitative analyses, and verify that the Mamba block mainly models low-frequency information under Convolution-Mamba hybrid architecture. Based on the analyses, we introduce a novel Laplace mixer to decouple the features in terms of frequency and input only the low-frequency components into the Mamba block. In addition, considering the redundancy of the features and the different requirements for high-frequency details and low-frequency global information at different stages, we introduce a frequency ramp inception, i.e., gradually reduce the input dimensions of the high-frequency branches, so as to efficiently trade-off the high-frequency and low-frequency components at different layers. By integrating mobile-friendly convolution and efficient Laplace mixer, we build a series of tiny hybrid vision Mamba called TinyViM. The proposed TinyViM achieves impressive performance on several downstream tasks including image classification, semantic segmentation, object detection and instance segmentation. In particular, TinyViM outperforms Convolution, Transformer and Mamba-based models with similar scales, and the throughput is about 2-3 times higher than that of other Mamba-based models. Code is available at https://github.com/xwmaxwma/TinyViM.

📄 PDF Abstract BibTeX arXiv:2411.17473

Code (1)

xwmaxwma/tinyvim 공식 구현 pytorch

Tasks

image-classificationImage ClassificationInstance SegmentationMambaobject-detectionObject DetectionSemantic Segmentation

Methods 이 논문이 사용한 방법론

Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Adam 설명 없음
Residual Connection 설명 없음

Similar Papers 제목 키워드 기반

TaFD: Threat-Aware Frequency Decoupling for Adversarial Robustness against Heterogeneous Attacks

2026-06-16 · Mengda Xie, Yiling He, Meie Fang arxiv

Multi-threat robustness remains a fundamental challenge in deep learning. Although joint adversarial training (JAT) is widely adopted, it suffers from negative transfer under heterogeneous threats, particularly between $…

Adversarial Robustness

Tiny-VBF: Resource-Efficient Vision Transformer based Lightweight Beamformer for Ultrasound Single-Angle Plane Wave Imaging

2023-11-20 · Abdul Rahoof, Vivek Chaturvedi, Mahesh Raveendranatha Panicker, Muhammad Shafique

Accelerating compute intensive non-real-time beam-forming algorithms in ultrasound imaging using deep learning architectures has been gaining momentum in the recent past. Nonetheless, the complexity of the state-of-the-a…

Deep LearningQuantization

Hybrid Convolution and Vision Transformer NAS Search Space for TinyML Image Classification

2025-11-04 · Mikhael Djajapermana, Moritz Reiber, Daniel Mueller-Gritschneder, Ulf Schlichtmann arxiv

Hybrids of Convolutional Neural Network (CNN) and Vision Transformer (ViT) have outperformed pure CNN or ViT architecture. However, since these architectures require large parameters and incur large computational costs, …

Neural Architecture SearchImage Classification

HyperD: Hybrid Periodicity Decoupling Framework for Traffic Forecasting

2025-11-12 · Minlan Shao, Zijian Zhang, Yili Wang, Yiwei Dai 외 arxiv

Accurate traffic forecasting plays a vital role in intelligent transportation systems, enabling applications such as congestion control, route planning, and urban mobility optimization. However, traffic forecasting remai…

Computational Efficiency

Highly Efficient Waveform Design and Hybrid Duplex for Joint Communication and Sensing

2022-07-07 · Yihua Ma, Zhifeng Yuan, Shuqiang Xia, Guanghui Yu 외

Joint communication and sensing (JCAS) is a very promising 6G technology, which attracts more and more research attention. Compared with communication, radar has many unique features in terms of waveform design criteria,…