SalM$2$: An Extremely Lightweight Saliency Mamba Model for Real-Time Cognitive Awareness of Driver Attention

2025-02-22 · Chunyu Zhao, Wentao Mu, Xian Zhou, Wenbo Liu, Fei Yan, Tao Deng

Driver attention recognition in driving scenarios is a popular direction in traffic scene perception technology. It aims to understand human driver attention to focus on specific targets/objects in the driving scene. However, traffic scenes contain not only a large amount of visual information but also semantic information related to driving tasks. Existing methods lack attention to the actual semantic information present in driving scenes. Additionally, the traffic scene is a complex and dynamic process that requires constant attention to objects related to the current driving task. Existing models, influenced by their foundational frameworks, tend to have large parameter counts and complex structures. Therefore, this paper proposes a real-time saliency Mamba network based on the latest Mamba framework. As shown in Figure 1, our model uses very few parameters (0.08M, only 0.09~11.16% of other models), while maintaining SOTA performance or achieving over 98% of the SOTA model's performance.

📄 PDF Abstract BibTeX arXiv:2502.16214

Code (1)

zhao-chunyu/SaliencyMamba 공식 구현 pytorch

Tasks

Mamba

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Attention 설명 없음

Mamba Foundation models, now powering most of the exciting applications in deep learning, are almost universally based on the Transformer architecture and its core attention module.…

Focus 설명 없음

CausalMamba: Scalable Conditional State Space Models for Neural Causal Inference

2025-10-20 · Sangyoon Bae, Jiook Cha arxiv

We introduce CausalMamba, a scalable framework that addresses fundamental limitations in fMRI-based causal inference: the ill-posed nature of inferring neural causality from hemodynamically distorted BOLD signals and the…

Causal Inference

CausalMamba: Interpretable State Space Modeling for Temporal Rumor Causality

2025-11-20 · Xiaotong Zhan, Xi Cheng arxiv

Rumor detection on social media remains a challenging task due to the complex propagation dynamics and the limited interpretability of existing models. While recent neural architectures capture content and structural fea…

Towards Explainability in NLP: Analyzing and Calculating Word Saliency through Word Properties

2022-07-17 · Jialiang Dong, zhitao Guan, Longfei Wu, Zijian Zhang 외

The wide use of black-box models in natural language processing brings great challenges to the understanding of the decision basis, the trustworthiness of the prediction results, and the improvement of the model performa…

LightM-UNet: Mamba Assists in Lightweight UNet for Medical Image Segmentation

2024-03-08 · Weibin Liao, Yinghao Zhu, Xinyuan Wang, Chengwei Pan 외

UNet and its variants have been widely used in medical image segmentation. However, these models, especially those based on Transformer architectures, pose challenges due to their large number of parameters and computati…

Image Segmentation Mamba Medical Image Segmentation Semantic Segmentation+1

Mesh Mamba: A Unified State Space Model for Saliency Prediction in Non-Textured and Textured Meshes

2025-04-02 · CVPR 2025 1 · Kaiwei Zhang, Dandan Zhu, Xiongkuo Min, Guangtao Zhai

Mesh saliency enhances the adaptability of 3D vision by identifying and emphasizing regions that naturally attract visual attention. To investigate the interaction between geometric structure and texture in shaping visua…

Mamba Saliency Prediction