REVIEW 15 cited by
PlainMamba: Improving Non-Hierarchical Mamba in Visual Recognition
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
read the original abstract
We present PlainMamba: a simple non-hierarchical state space model (SSM) designed for general visual recognition. The recent Mamba model has shown how SSMs can be highly competitive with other architectures on sequential data and initial attempts have been made to apply it to images. In this paper, we further adapt the selective scanning process of Mamba to the visual domain, enhancing its ability to learn features from two-dimensional images by (i) a continuous 2D scanning process that improves spatial continuity by ensuring adjacency of tokens in the scanning sequence, and (ii) direction-aware updating which enables the model to discern the spatial relations of tokens by encoding directional information. Our architecture is designed to be easy to use and easy to scale, formed by stacking identical PlainMamba blocks, resulting in a model with constant width throughout all layers. The architecture is further simplified by removing the need for special tokens. We evaluate PlainMamba on a variety of visual recognition tasks, achieving performance gains over previous non-hierarchical models and is competitive with hierarchical alternatives. For tasks requiring high-resolution inputs, in particular, PlainMamba requires much less computing while maintaining high performance. Code and models are available at: https://github.com/ChenhongyiYang/PlainMamba .
Forward citations
Cited by 15 Pith papers
-
Partial Ring Scan: Revisiting Scan Order in Vision State Space Models
Ring-based scanning with selective channel routing improves accuracy, speed, and rotation robustness of vision state-space models.
-
UIS-Mamba: Exploring Mamba for Underwater Instance Segmentation via Dynamic Tree Scan and Hidden State Weaken
UIS-Mamba applies a Mamba state space backbone with dynamic tree scanning and background-hidden-state suppression to achieve SOTA underwater instance segmentation.
-
Training-free Token Reduction for Vision Mamba
MTR uses Mamba's timescale parameter Δ as a token importance score to merge unimportant tokens, giving training-free inference speedups with small accuracy loss.
-
Flatten Wisely: How Patch Order Shapes Mamba-Powered Vision for MRI Segmentation
A benchmark of 21 patch scan orders shows that contiguous raster scans significantly outperform diagonal scans for Vision Mamba MRI segmentation, with up to 27 Dice points difference.
-
MERba: Multi-Receptive Field MambaVision for Micro-Expression Recognition
MERba, a hybrid MambaVision architecture with asymmetric multi-scanning and coarse-to-fine classification, achieves state-of-the-art results on three micro-expression recognition benchmarks.
-
ECP-Mamba: An Efficient Multi-scale Self-supervised Contrastive Learning Method with State Space Model for PolSAR Image Classification
ECP-Mamba, a Mamba-based network with a spiral scan and multi-scale self-distillation, reports state-of-the-art PolSAR image classification accuracy at label rates as low as 0.2%.
-
ParVL: Parallel Scaling and Expandable Compute Allocation for Multimodal LLMs
ParVL scales MLLM computation by running multiple prefix-conditioned ViT and LLM branches over a shared backbone, improving average benchmark scores by 0.3 to 0.9 points and showing task-dependent vision-language allocation.
-
Correcting Prompt Dependence in LLM Benchmarks: A Bayesian Hierarchical Model with Embedding-Space Clustering
A Bayesian model that groups similar LLM test prompts into clusters gives better predictive scores than a no-clustering baseline but does not prove that it truly corrects prompt dependence.
-
Animate-X++: Universal Character Image Animation with Dynamic Backgrounds
Animate-X++ turns cartoon images into pose-driven animations with text-controlled moving backgrounds, claiming state-of-the-art results on a new synthetic anthropomorphic benchmark.
-
LIDAR: Lightweight Adaptive Cue-Aware Fusion Vision Mamba for Multimodal Segmentation of Structural Cracks
LIDAR is a lightweight adaptive fusion Vision Mamba network that reports state-of-the-art multimodal crack segmentation accuracy with 5.35M parameters on a light-field depth dataset.
-
HydraMamba: Multi-Head State Space Model for Global Point Cloud Learning
A state space model based point cloud network with shuffled Hilbert serialization, a convolutional bidirectional S6 branch, and multi-head S6 achieves new top scores on ModelNet40, ShapeNet, S3DIS, and ScanObjectNN.
-
MambaHash: Visual State Space Deep Hashing Model for Large-Scale Image Retrieval
MambaHash uses a grouped, multi-directional Mamba backbone for deep supervised hashing and reports the highest mean average precision on CIFAR-10 and IMAGENET, with marginal gains on NUS-WIDE.
-
DM-SegNet: Dual-Mamba Architecture for 3D Medical Image Segmentation with Global Context Modeling
DM-SegNet combines four-direction Mamba scanning, gated spatial convolutions, and a Mamba decoder to reach reported state-of-the-art Dice scores on Synapse and BraTS2023.
-
VCMamba: Bridging Convolutions with Multi-Directional Mamba for Efficient Visual Representation
VCMamba reports that using convolutional feed-forward blocks for the first three stages followed by multi-directional Mamba blocks in the final stage yields 82.6% ImageNet-1K and 47.1 ADE20K mIoU at 31.5M parameters, ...
-
A Survey on Mamba Architecture for Vision Applications
A survey of Mamba-based vision models that summarizes scanning mechanisms, key architectures, and benchmark results, contributing no new experimental findings.
Discussion (0). Continue with ORCID to comment.