English
Related papers

Related papers: Autoregressive Pretraining with Mamba in Vision

200 papers

Cross-modal alignment is crucial for multimodal representation fusion due to the inherent heterogeneity between modalities. While Transformer-based methods have shown promising results in modeling inter-modal relationships, their quadratic…

Computer Vision and Pattern Recognition · Computer Science 2024-12-03 Yan Li , Yifei Xing , Xiangyuan Lan , Xin Li , Haifeng Chen , Dongmei Jiang

State space models (SSMs) like Mamba have recently attracted much attention. Compared to Transformer-based large language models (LLMs), Mamba achieves linear computation complexity with the sequence length and demonstrates superior…

Computation and Language · Computer Science 2025-10-13 Renjie Wei , Songqiang Xu , Linfeng Zhong , Zebin Yang , Qingyu Guo , Yuan Wang , Runsheng Wang , Meng Li

Recent State Space Models (SSM), especially Mamba, have demonstrated impressive performance in visual modeling and possess superior model efficiency. However, the application of Mamba to visual tasks suffers inferior performance due to…

Computer Vision and Pattern Recognition · Computer Science 2025-05-20 Fei Xie , Jiahao Nie , Yujin Tang , Wenkang Zhang , Hongshen Zhao

Vision Mamba has emerged as a promising and efficient alternative to Vision Transformers, yet its efficiency remains fundamentally constrained by the number of input tokens. Existing token reduction approaches typically adopt token pruning…

Computer Vision and Pattern Recognition · Computer Science 2025-12-04 Shanhui Liu , Rui Xu , Yunke Wang

Contrastive Language-Image Pre-training (CLIP) relies on Vision Transformers whose attention mechanism is susceptible to spurious correlations, and scales quadratically with resolution. To address these limitations, We present CLIMP, the…

Computer Vision and Pattern Recognition · Computer Science 2026-01-13 Nimrod Shabtay , Itamar Zimerman , Eli Schwartz , Raja Giryes

Multi-view depth estimation has achieved impressive performance over various benchmarks. However, almost all current multi-view systems rely on given ideal camera poses, which are unavailable in many real-world scenarios, such as autonomous…

Computer Vision and Pattern Recognition · Computer Science 2024-12-31 Zelin Meng , Zhichen Wang

As one of the most representative DL techniques, Transformer architecture has empowered numerous advanced models, especially the large language models (LLMs) that comprise billions of parameters, becoming a cornerstone in deep learning.…

Machine Learning · Computer Science 2026-04-07 Haohao Qu , Liangbo Ning , Rui An , Wenqi Fan , Tyler Derr , Hui Liu , Xin Xu , Qing Li

Recent advances in Vision Transformers (ViTs) and State Space Models (SSMs) have challenged the dominance of Convolutional Neural Networks (CNNs) in computer vision. ViTs excel at capturing global context, and SSMs like Mamba offer linear…

Computer Vision and Pattern Recognition · Computer Science 2025-09-08 Mustafa Munir , Alex Zhang , Radu Marculescu

Prior efforts in light-weight model development mainly centered on CNN and Transformer-based designs yet faced persistent challenges. CNNs adept at local feature extraction compromise resolution while Transformers offer global reach but…

Computer Vision and Pattern Recognition · Computer Science 2024-03-18 Xiaohuan Pei , Tao Huang , Chang Xu

In recent years, Transformers have become the de-facto architecture for sequence modeling on text and a variety of multi-dimensional data, such as images and video. However, the use of self-attention layers in a Transformer incurs…

Computer Vision and Pattern Recognition · Computer Science 2024-07-16 Shufan Li , Harkanwar Singh , Aditya Grover

Despite the significant achievements of Vision Transformers (ViTs) in various vision tasks, they are constrained by the quadratic complexity. Recently, State Space Models (SSMs) have garnered widespread attention due to their global…

Computer Vision and Pattern Recognition · Computer Science 2024-05-24 Yuheng Shi , Minjing Dong , Chang Xu

The recent Mamba model has shown remarkable adaptability for visual representation learning, including in medical imaging tasks. This study introduces MambaMIR, a Mamba-based model for medical image reconstruction, as well as its Generative…

Image and Video Processing · Electrical Eng. & Systems 2024-06-27 Jiahao Huang , Liutao Yang , Fanwen Wang , Yang Nan , Angelica I. Aviles-Rivero , Carola-Bibiane Schönlieb , Daoqiang Zhang , Guang Yang

Deployment of efficient and accurate Deep Learning models has long been a challenge in autonomous navigation, particularly for real-time applications on resource-constrained edge devices. Edge devices are limited in computing power and…

Image and Video Processing · Electrical Eng. & Systems 2025-10-17 Romina Aalishah , Mozhgan Navardi , Tinoosh Mohsenin

Snapshot Compressive Imaging (SCI) enables fast spectral imaging but requires effective decoding algorithms for hyperspectral image (HSI) reconstruction from compressed measurements. Current CNN-based methods are limited in modeling…

Computer Vision and Pattern Recognition · Computer Science 2024-12-10 Wenzhe Tian , Haijin Zeng , Yin-Ping Zhao , Yongyong Chen , Zhen Wang , Xuelong Li

Audio super-resolution aims to enhance low-resolution signals by creating high-frequency content. In this work, we modify the architecture of AERO (a state-of-the-art system for this task) for music super-resolution. SPecifically, we…

Audio and Speech Processing · Electrical Eng. & Systems 2024-11-13 Wallace Abreu , Luiz Wagner Pereira Biscainho

Recent Mamba-based models have shown promise in speech enhancement by efficiently modeling long-range temporal dependencies. However, models like Speech Enhancement Mamba (SEMamba) remain limited to single-speaker scenarios and struggle in…

Sound · Computer Science 2025-10-01 Rong Chao , Wenze Ren , You-Jin Li , Kuo-Hsuan Hung , Sung-Feng Huang , Szu-Wei Fu , Wen-Huang Cheng , Yu Tsao

U-shaped architectures have long dominated the field of medical image segmentation, while Transformers are widely employed for modeling long-range dependencies. The former typically handles scale variations implicitly by aggregating…

Computer Vision and Pattern Recognition · Computer Science 2026-05-12 Yanhua Zhang , Ke Zhang , Jingyu Wang , Gabriella Balestra , Samanta Rosati , Yulin Wu , Wuwei Wang , Valentina Giannini

Transformers have proven effective in language modeling but are limited by high computational and memory demands that grow quadratically with input sequence length. State space models (SSMs) offer a promising alternative by reducing…

Hardware Architecture · Computer Science 2025-08-06 Dongho Yoon , Gungyu Lee , Jaewon Chang , Yunjae Lee , Dongjae Lee , Minsoo Rhu

The Mamba-based model has demonstrated outstanding performance across tasks in computer vision, natural language processing, and speech processing. However, in the realm of speech processing, the Mamba-based model's performance varies…

Audio and Speech Processing · Electrical Eng. & Systems 2024-09-12 Xiangyu Zhang , Jianbo Ma , Mostafa Shahin , Beena Ahmed , Julien Epps

Similar to Vision Transformers, this paper identifies artifacts also present within the feature maps of Vision Mamba. These artifacts, corresponding to high-norm tokens emerging in low-information background areas of images, appear much…

Computer Vision and Pattern Recognition · Computer Science 2025-06-02 Feng Wang , Jiahao Wang , Sucheng Ren , Guoyizhe Wei , Jieru Mei , Wei Shao , Yuyin Zhou , Alan Yuille , Cihang Xie
‹ Prev 1 3 4 5 6 7 10 Next ›