Polyline Path Masked Attention for Vision Transformer

• URL: http://arxiv.org/abs/2506.15940v1
• Date: Thu, 19 Jun 2025 00:52:30 GMT
• Title: Polyline Path Masked Attention for Vision Transformer
• Authors: Zhongchen Zhao, Chaodong Xiao, Hui Lin, Qi Xie, Lei Zhang, Deyu Meng,
• Abstract summary: Vision Transformers (ViTs) have achieved remarkable success in computer vision.<n>Mamba2 has demonstrated its significant potential in natural language processing tasks.<n>We propose Polyline Path Masked Attention (PPMA) that integrates the self-attention mechanism of ViTs with an enhanced structured mask of Mamba2.
• Score: 48.25001539205017
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Global dependency modeling and spatial position modeling are two core issues of the foundational architecture design in current deep learning frameworks. Recently, Vision Transformers (ViTs) have achieved remarkable success in computer vision, leveraging the powerful global dependency modeling capability of the self-attention mechanism. Furthermore, Mamba2 has demonstrated its significant potential in natural language processing tasks by explicitly modeling the spatial adjacency prior through the structured mask. In this paper, we propose Polyline Path Masked Attention (PPMA) that integrates the self-attention mechanism of ViTs with an enhanced structured mask of Mamba2, harnessing the complementary strengths of both architectures. Specifically, we first ameliorate the traditional structured mask of Mamba2 by introducing a 2D polyline path scanning strategy and derive its corresponding structured mask, polyline path mask, which better preserves the adjacency relationships among image tokens. Notably, we conduct a thorough theoretical analysis on the structural characteristics of the proposed polyline path mask and design an efficient algorithm for the computation of the polyline path mask. Next, we embed the polyline path mask into the self-attention mechanism of ViTs, enabling explicit modeling of spatial adjacency prior. Extensive experiments on standard benchmarks, including image classification, object detection, and segmentation, demonstrate that our model outperforms previous state-of-the-art approaches based on both state-space models and Transformers. For example, our proposed PPMA-T/S/B models achieve 48.7%/51.1%/52.3% mIoU on the ADE20K semantic segmentation task, surpassing RMT-T/S/B by 0.7%/1.3%/0.3%, respectively. Code is available at https://github.com/zhongchenzhao/PPMA.

Related papers

• The Missing Point in Vision Transformers for Universal Image Segmentation [17.571552686063335]
  We introduce ViT-P, a two-stage segmentation framework that decouples mask generation from classification.<n>ViT-P serves as a pre-training-free adapter, allowing the integration of various pre-trained vision transformers.<n>Experiments across COCO, ADE20K, and Cityscapes datasets validate the effectiveness of ViT-P.
  arXiv  Detail & Related papers  (2025-05-26T10:29:13Z)
• MaskGWM: A Generalizable Driving World Model with Video Mask Reconstruction [8.503246256880612]
  We propose MaskGWM: a Generalizable driving World Model embodied with Video Mask reconstruction.<n>Our model contains two variants: MaskGWM-long, focusing on long-horizon prediction, and MaskGWM-mview, dedicated to multi-view generation.
  arXiv  Detail & Related papers  (2025-02-17T10:53:56Z)
• Boosting Cross-Domain Point Classification via Distilling Relational Priors from 2D Transformers [59.0181939916084]
  Traditional 3D networks mainly focus on local geometric details and ignore the topological structure between local geometries. We propose a novel Priors Distillation (RPD) method to extract priors from the well-trained transformers on massive images. Experiments on the PointDA-10 and the Sim-to-Real datasets verify that the proposed method consistently achieves the state-of-the-art performance of UDA for point cloud classification.
  arXiv  Detail & Related papers  (2024-07-26T06:29:09Z)
• Bringing Masked Autoencoders Explicit Contrastive Properties for Point Cloud Self-Supervised Learning [116.75939193785143]
  Contrastive learning (CL) for Vision Transformers (ViTs) in image domains has achieved performance comparable to CL for traditional convolutional backbones. In 3D point cloud pretraining with ViTs, masked autoencoder (MAE) modeling remains dominant.
  arXiv  Detail & Related papers  (2024-07-08T12:28:56Z)
• Hyper-Transformer for Amodal Completion [82.4118011026855]
  Amodal object completion is a complex task that involves predicting the invisible parts of an object based on visible segments and background information. We introduce a novel framework named the Hyper-Transformer Amodal Network (H-TAN) This framework utilizes a hyper transformer equipped with a dynamic convolution head to directly learn shape priors and accurately predict amodal masks.
  arXiv  Detail & Related papers  (2024-05-30T11:11:54Z)
• i-MAE: Are Latent Representations in Masked Autoencoders Linearly Separable? [26.146459754995597]
  Masked image modeling (MIM) has been recognized as a strong self-supervised pre-training approach in the vision domain. This paper aims to explore an interactive Masked Autoencoders (i-MAE) framework to enhance the representation capability. In addition to qualitatively analyzing the characteristics of the latent representations, we examine the existence of linear separability and the degree of semantics in the latent space.
  arXiv  Detail & Related papers  (2022-10-20T17:59:54Z)
• AFNet-M: Adaptive Fusion Network with Masks for 2D+3D Facial Expression Recognition [1.8604727699812171]
  2D+3D facial expression recognition (FER) can effectively cope with illumination changes and pose variations. Most deep learning-based approaches employ the simple fusion strategy. We propose the adaptive fusion network with masks (AFNet-M) for 2D+3D FER.
  arXiv  Detail & Related papers  (2022-05-24T04:56:55Z)
• ConvMAE: Masked Convolution Meets Masked Autoencoders [65.15953258300958]
  Masked auto-encoding for feature pretraining and multi-scale hybrid convolution-transformer architectures can further unleash the potentials of ViT. Our ConvMAE framework demonstrates that multi-scale hybrid convolution-transformer can learn more discriminative representations via the mask auto-encoding scheme. Based on our pretrained ConvMAE models, ConvMAE-Base improves ImageNet-1K finetuning accuracy by 1.4% compared with MAE-Base.
  arXiv  Detail & Related papers  (2022-05-08T15:12:19Z)
• Mask Attention Networks: Rethinking and Strengthen Transformer [70.95528238937861]
  Transformer is an attention-based neural network, which consists of two sublayers, Self-Attention Network (SAN) and Feed-Forward Network (FFN)
  arXiv  Detail & Related papers  (2021-03-25T04:07:44Z)

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.