REVIEW 6 cited by
Multi-Scale VMamba: Hierarchy in Hierarchy Visual State Space Model
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
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 receptive field and linear complexity with respect to the input length, demonstrating substantial potential across fields including natural language processing and computer vision. To improve the performance of SSMs in vision tasks, a multi-scan strategy is widely adopted, which leads to significant redundancy of SSMs. For a better trade-off between efficiency and performance, we analyze the underlying reasons behind the success of the multi-scan strategy, where long-range dependency plays an important role. Based on the analysis, we introduce Multi-Scale Vision Mamba (MSVMamba) to preserve the superiority of SSMs in vision tasks with limited parameters. It employs a multi-scale 2D scanning technique on both original and downsampled feature maps, which not only benefits long-range dependency learning but also reduces computational costs. Additionally, we integrate a Convolutional Feed-Forward Network (ConvFFN) to address the lack of channel mixing. Our experiments demonstrate that MSVMamba is highly competitive, with the MSVMamba-Tiny model achieving 82.8% top-1 accuracy on ImageNet, 46.9% box mAP, and 42.2% instance mAP with the Mask R-CNN framework, 1x training schedule on COCO, and 47.6% mIoU with single-scale testing on ADE20K.Code is available at \url{https://github.com/YuHengsss/MSVMamba}.
Forward citations
Cited by 6 Pith papers
-
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.
-
SMamba: Sparse Mamba for Event-based Object Detection
SMamba prunes uninformative event tokens using a spatiotemporal continuity score, then scans the survivors with Mamba blocks to match or beat prior event detectors at lower compute.
-
GLAM: Global-Local Variation Awareness in Mamba-based World Model
GLAM improves world model prediction in model-based RL by feeding state differences into two parallel Mamba modules and training agents on imagined variation-aware trajectories.
-
MANTA: Diffusion Mamba for Efficient and Effective Stochastic Long-Term Dense Anticipation
A bidirectional Mamba layer used as the diffusion generator improves accuracy and drastically cuts inference time for stochastic long-term action anticipation.
-
AVS-Mamba: Exploring Temporal and Multi-modal Mamba for Audio-Visual Segmentation
AVS-Mamba applies Mamba with temporal and cross-modal scanning to audio-visual segmentation, reporting top scores on AVSBench-object but not on AVSBench-semantic with the stronger backbone.
-
MambaGlue: Fast and Robust Local Feature Matching With Mamba
MambaGlue replaces parts of LightGlue with a parallel Mamba-and-attention mixer and a deeper confidence regressor, yielding slightly better matching accuracy at comparable latency.
Discussion (0). Continue with ORCID to comment.