REVIEW 11 cited by
LocalMamba: Visual State Space Model with Windowed Selective Scan
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
LocalMamba: Visual State Space Model with Windowed Selective Scan
read the original abstract
Recent advancements in state space models, notably Mamba, have demonstrated significant progress in modeling long sequences for tasks like language understanding. Yet, their application in vision tasks has not markedly surpassed the performance of traditional Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs). This paper posits that the key to enhancing Vision Mamba (ViM) lies in optimizing scan directions for sequence modeling. Traditional ViM approaches, which flatten spatial tokens, overlook the preservation of local 2D dependencies, thereby elongating the distance between adjacent tokens. We introduce a novel local scanning strategy that divides images into distinct windows, effectively capturing local dependencies while maintaining a global perspective. Additionally, acknowledging the varying preferences for scan patterns across different network layers, we propose a dynamic method to independently search for the optimal scan choices for each layer, substantially improving performance. Extensive experiments across both plain and hierarchical models underscore our approach's superiority in effectively capturing image representations. For example, our model significantly outperforms Vim-Ti by 3.1% on ImageNet with the same 1.5G FLOPs. Code is available at: https://github.com/hunto/LocalMamba.
Forward citations
Cited by 11 Pith papers
-
MambaPanoptic: A Vision Mamba-based Structured State Space Framework for Panoptic Segmentation
MambaPanoptic replaces CNN and transformer components with Mamba blocks in a feature pyramid and kernel generator, achieving higher panoptic quality than PanopticDeepLab and PanopticFCN on Cityscapes and COCO while us...
-
FractalMamba++: Scaling Vision Mamba Across Resolutions via Hilbert Fractal Geometry
FractalMamba++ scales Vision Mamba across resolutions by using Hilbert fractal serialization, hierarchy-based skip connections, and fractal-aware 2D rotary position encoding.
-
Mamba-Based Graph Convolutional Networks: Tackling Over-smoothing with Selective State Space
MbaGCN combines message aggregation, selective state space transitions, and node state prediction to create a more scalable deep graph convolutional network.
-
Scaling Parallel Sequence Models to Foundation-Scale Vision Encoders
C-GSPN scales 2D spatial propagation to foundation vision encoders via a fast CUDA kernel, compressed blocks, and two-stage distillation, matching ViT performance with 15% fewer parameters and 4x block speedup at 2K r...
-
MambaPanoptic: A Vision Mamba-based Structured State Space Framework for Panoptic Segmentation
MambaPanoptic is a fully Mamba-based panoptic segmentation model that uses MambaFPN for multi-scale features and a QuadMamba kernel generator to outperform PanopticDeepLab and PanopticFCN on Cityscapes and COCO while ...
-
HAMSA: Scanning-Free Vision State Space Models via SpectralPulseNet
HAMSA achieves 85.7% ImageNet-1K top-1 accuracy as a spectral-domain SSM with 2.2x faster inference and lower memory than transformers or scanning-based SSMs.
-
Reload-Mamba: Hierarchical Anti-Dilution State-Space Modeling for Multi-Class Semantic Segmentation
Reload-Mamba augments a ConvNeXt-Tiny + four-directional Mamba encoder-decoder with boundary-supervised detail prior, entropy-aware Reload Gate, and three-level hierarchical reload, reporting 47.9% mIoU on ADE20K and ...
-
MambaADv2: Evolving Duality-enhanced State Space Model for Unsupervised Anomaly Detection
MambaADv2 evolves Mamba state space models with hybrid blocks, frequency convolutions, and adaptive scanning for improved unsupervised anomaly detection.
-
Can Visual Mamba Improve AI-Generated Image Detection? An In-Depth Investigation
Benchmarks Vision Mamba variants for AI-generated image detection against CNN, ViT, and VLM detectors on diverse datasets and synthetic sources, reporting promise alongside limitations.
-
Beyond ZOH: Advanced Discretization Strategies for Vision Mamba
Bilinear discretization improves Vision Mamba accuracy over zero-order hold on classification, segmentation, and detection benchmarks with only modest extra training cost.
-
A Survey of Mamba
The paper consolidates existing research on Mamba models, their architecture variants, adaptations to different data modalities, and applications across domains.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.