中文
相关论文

相关论文: FFNet: MetaMixer-based Efficient Convolutional Mix…

200 篇论文

Existing stereo matching networks typically rely on either cost-volume construction based on 3D convolutions or deformation methods based on iterative optimization. The former incurs significant computational overhead during cost…

计算机视觉与模式识别 · 计算机科学 2026-01-09 Ao Xu , Rujin Zhao , Xiong Xu , Boceng Huang , Yujia Jia , Hongfeng Long , Fuxuan Chen , Zilong Cao , Fangyuan Chen

Multi-head-self-attention (MHSA)-equipped models have achieved notable performance in computer vision. Their computational complexity is proportional to quadratic numbers of pixels in input feature maps, resulting in slow processing,…

计算机视觉与模式识别 · 计算机科学 2023-12-19 Yuki Tatsunami , Masato Taki

The transformer architecture is central to the success of modern Large Language Models (LLMs), in part due to its surprising ability to perform a wide range of tasks - including mathematical reasoning, memorization, and retrieval - using…

机器学习 · 计算机科学 2025-09-05 Yihe Dong , Lorenzo Noci , Mikhail Khodak , Mufan Li

The encoder-decoder is the typical framework for Neural Machine Translation (NMT), and different structures have been developed for improving the translation performance. Transformer is one of the most promising structures, which can…

计算与语言 · 计算机科学 2018-12-11 Kaitao Song , Xu Tan , Furong Peng , Jianfeng Lu

Transformer with self-attention has led to the revolutionizing of natural language processing field, and recently inspires the emergence of Transformer-style architecture design with competitive results in numerous computer vision tasks.…

计算机视觉与模式识别 · 计算机科学 2021-07-27 Yehao Li , Ting Yao , Yingwei Pan , Tao Mei

Vision Transformer has demonstrated impressive success across various vision tasks. However, its heavy computation cost, which grows quadratically with respect to the token sequence length, largely limits its power in handling large feature…

计算机视觉与模式识别 · 计算机科学 2023-08-24 Sucheng Ren , Xingyi Yang , Songhua Liu , Xinchao Wang

Transformers, driven by attention mechanisms, form the foundation of large language models (LLMs). As these models scale up, efficient GPU attention kernels become essential for high-throughput and low-latency inference. Diverse LLM…

分布式、并行与集群计算 · 计算机科学 2025-04-23 Zihao Ye , Lequn Chen , Ruihang Lai , Wuwei Lin , Yineng Zhang , Stephanie Wang , Tianqi Chen , Baris Kasikci , Vinod Grover , Arvind Krishnamurthy , Luis Ceze

Decoding brain cognitive states from neuroimaging signals is an important topic in neuroscience. In recent years, deep neural networks (DNNs) have been recruited for multiple brain state decoding and achieved good performance. However, the…

图像与视频处理 · 电气工程与系统科学 2021-10-05 Zhoufan Jiang , Yanming Wang , ChenWei Shi , Yueyang Wu , Rongjie Hu , Shishuo Chen , Sheng Hu , Xiaoxiao Wang , Bensheng Qiu

Long-sequence video diffusion transformers hit a quadratic self-attention cost that dominates runtime and memory for very long token sequences. Most efficient attention methods use one approximation everywhere, yet video features are…

计算机视觉与模式识别 · 计算机科学 2026-04-28 Haopeng Jin

Since their emergence, Convolutional Neural Networks (CNNs) have made significant strides in medical image analysis. However, the local nature of the convolution operator may pose a limitation for capturing global and long-range…

图像与视频处理 · 电气工程与系统科学 2024-04-01 Abdul Rehman Khan , Asifullah Khan

Recent progress in single-image super-resolution (SISR) has achieved remarkable performance, yet the computational costs of these methods remain a challenge for deployment on resource-constrained devices. In particular, transformer-based…

计算机视觉与模式识别 · 计算机科学 2024-10-22 Gang Wu , Junjun Jiang , Junpeng Jiang , Xianming Liu

Transformer-based models have achieved dominant performance in numerous NLP tasks. Despite their remarkable successes, pre-trained transformers such as BERT suffer from a computationally expensive self-attention mechanism that interacts…

计算与语言 · 计算机科学 2024-06-04 Jungmin Yun , Mihyeon Kim , Youngbin Kim

The attention module is the key component in Transformers. While the global attention mechanism offers high expressiveness, its excessive computational cost restricts its applicability in various scenarios. In this paper, we propose a novel…

计算机视觉与模式识别 · 计算机科学 2024-07-16 Dongchen Han , Tianzhu Ye , Yizeng Han , Zhuofan Xia , Siyuan Pan , Pengfei Wan , Shiji Song , Gao Huang

Convolution and self-attention are acting as two fundamental building blocks in deep neural networks, where the former extracts local image features in a linear way while the latter non-locally encodes high-order contextual relationships.…

计算机视觉与模式识别 · 计算机科学 2021-06-08 Xuanhong Chen , Hang Wang , Bingbing Ni

Attention mechanisms, particularly softmax attention, have been instrumental in the success of transformer-based models such as GPT. However, the quadratic memory complexity of softmax attention with respect to sequence length poses…

机器学习 · 计算机科学 2026-02-20 Gabriel Mongaras , Trevor Dohm , Eric C. Larson

Deep learning has become a powerful tool for medical image analysis; however, conventional Convolutional Neural Networks (CNNs) often fail to capture the fine-grained and complex features critical for accurate diagnosis. To address this…

计算机视觉与模式识别 · 计算机科学 2025-09-09 Zahid Ullah , Minki Hong , Tahir Mahmood , Jihie Kim

Fine-tuning provides an effective means to specialize pre-trained models for various downstream tasks. However, fine-tuning often incurs high memory overhead, especially for large transformer-based models, such as LLMs. While existing…

计算与语言 · 计算机科学 2025-02-03 Antoine Simoulin , Namyong Park , Xiaoyi Liu , Grey Yang

Convolutions operate only locally, thus failing to model global interactions. Self-attention is, however, able to learn representations that capture long-range dependencies in sequences. We propose a network architecture for audio…

声音 · 计算机科学 2021-08-27 Nathanaël Carraz Rakotonirina

In this paper, we propose a vision model that adopts token mixing, sequence-pooling, and convolutional tokenizers to achieve state-of-the-art performance and efficient inference in fixed context-length tasks. In the CIFAR100 benchmark, our…

计算机视觉与模式识别 · 计算机科学 2025-08-27 Simpenzwe Honore Leandre , Natenaile Asmamaw Shiferaw , Dillip Rout

Although deep learning based methods have achieved great progress in unsupervised video object segmentation, difficult scenarios (e.g., visual similarity, occlusions, and appearance changing) are still not well-handled. To alleviate these…

计算机视觉与模式识别 · 计算机科学 2020-12-07 Daizong Liu , Dongdong Yu , Changhu Wang , Pan Zhou