Vision Mamba has emerged as a promising and efficient alternative to Vision Transformers, yet its efficiency remains fundamentally constrained by the number of input tokens. Existing token reduction approaches typically adopt token pruning or merging to reduce computation. However, they inherently lead to information loss as they discard or compress token representations. This problem is further exacerbated when the same fine-grained token processing is uniformly applied across all images regardless of visual complexity. We observe that not all inputs require fine-grained processing: simple images can be effectively handled at a coarse resolution, while only complex ones require refinement. Based on this insight, we propose MambaScope, an adaptive framework for efficient inference for Vision Mamba. MambaScope first performs coarse-grained inference by dividing the input image into large patches, significantly reducing token length and computation. When the model's prediction confidence is low, selected regions are re-processed at a finer resolution to recover essential visual details with minimal additional cost. This dynamic resolution assignment strategy allows MambaScope to allocate computation adaptively according to image complexity, achieving efficient processing without compromising accuracy. Experiments across various vision tasks demonstrate that MambaScope outperforms both the baseline Vision Mamba and state-of-the-art token reduction techniques in terms of accuracy and efficiency.

Jigsaw puzzle solving remains challenging in computer vision, requiring an understanding of both local fragment details and global spatial relationships. While most traditional approaches only focus on visual cues like edge matching and visual coherence, few methods explore natural language descriptions for semantic guidance in challenging scenarios, especially for eroded gap puzzles. We propose a vision-language framework that leverages textual context to enhance puzzle assembly performance. Our approach centers on the Vision-Language Hierarchical Semantic Alignment (VLHSA) module, which aligns visual patches with textual descriptions through multi-level semantic matching from local tokens to global context. Also, a multimodal architecture that combines dual visual encoders with language features for cross-modal reasoning is integrated into this module. Experiments demonstrate that our method significantly outperforms state-of-the-art models across various datasets, achieving substantial improvements, including a 14.2 percentage point gain in piece accuracy. Ablation studies confirm the critical role of the VLHSA module in driving improvements over vision-only approaches. Our work establishes a new paradigm for jigsaw puzzle solving by incorporating multimodal semantic insights.

Vision State Space Models (SSMs), particularly architectures like Vision Mamba (ViM), have emerged as promising alternatives to Vision Transformers (ViTs). However, the security implications of this novel architecture, especially their vulnerability to backdoor attacks, remain critically underexplored. Backdoor attacks aim to embed hidden triggers into victim models, causing the model to misclassify inputs containing these triggers while maintaining normal behavior on clean inputs. This paper investigates the susceptibility of ViM to backdoor attacks by introducing BadViM, a novel backdoor attack framework specifically designed for Vision Mamba. The proposed BadViM leverages a Resonant Frequency Trigger (RFT) that exploits the frequency sensitivity patterns of the victim model to create stealthy, distributed triggers. To maximize attack efficacy, we propose a Hidden State Alignment loss that strategically manipulates the internal representations of model by aligning the hidden states of backdoor images with those of target classes. Extensive experimental results demonstrate that BadViM achieves superior attack success rates while maintaining clean data accuracy. Meanwhile, BadViM exhibits remarkable resilience against common defensive measures, including PatchDrop, PatchShuffle and JPEG compression, which typically neutralize normal backdoor attacks.

Transformers have become foundational for visual tasks such as object detection, semantic segmentation, and video understanding, but their quadratic complexity in attention mechanisms presents scalability challenges. To address these limitations, the Mamba architecture utilizes state-space models (SSMs) for linear scalability, efficient processing, and improved contextual awareness. This paper investigates Mamba architecture for visual domain applications and its recent advancements, including Vision Mamba (ViM) and VideoMamba, which introduce bidirectional scanning, selective scanning mechanisms, and spatiotemporal processing to enhance image and video understanding. Architectural innovations like position embeddings, cross-scan modules, and hierarchical designs further optimize the Mamba framework for global and local feature extraction. These advancements position Mamba as a promising architecture in computer vision research and applications.

State Space Models (SSMs) with selective scan (Mamba) have been adapted into efficient vision models. Mamba, unlike Vision Transformers, achieves linear complexity for token interactions through a recurrent hidden state process. This sequential processing is enhanced by a parallel scan algorithm, which reduces the computational time of recurrent steps from $L$ sequential steps to $log(L)$ parallel steps with respect to the number of input tokens ($L$). In this work, we propose Fast Vision Mamba (FastVim), that further reduces the computational time of the SSM block by reducing the number of recurrent steps in Vision Mamba models while still retaining model performance. By alternately pooling tokens along image dimensions across Mamba blocks, we obtain a 2$\times$ reduction in the number of parallel steps in SSM block. Our model offers up to $72.5\%$ speedup in inference speed compared to baseline Vision Mamba models on high resolution (2048$\times$2048) images. Our experiments demonstrate state-of-the-art performance with dramatically improved throughput in a range of tasks such as image classification, cell perturbation prediction, segmentation, and object detection. Code is made available at https://github.com/insitro/FastVim

Pre-trained Vision Mamba (Vim) models have demonstrated exceptional performance across various computer vision tasks in a computationally efficient manner, attributed to their unique design of selective state space models. To further extend their applicability to diverse downstream vision tasks, Vim models can be adapted using the efficient fine-tuning technique known as visual prompting. However, existing visual prompting methods are predominantly tailored for Vision Transformer (ViT)-based models that leverage global attention, neglecting the distinctive sequential token-wise compression and propagation characteristics of Vim. Specifically, existing prompt tokens prefixed to the sequence are insufficient to effectively activate the input and forget gates across the entire sequence, hindering the extraction and propagation of discriminative information. To address this limitation, we introduce a novel Selective Visual Prompting (SVP) method specifically for the efficient fine-tuning of Vim. To prevent the loss of discriminative information during state space propagation, SVP employs lightweight selective prompters for token-wise prompt generation, ensuring adaptive activation of the update and forget gates within Mamba blocks to promote discriminative information propagation. Moreover, considering that Vim propagates both shared cross-layer information and specific inner-layer information, we further refine SVP with a dual-path structure: Cross-Prompting and Inner-Prompting. Cross-Prompting utilizes shared parameters across layers, while Inner-Prompting employs distinct parameters, promoting the propagation of both shared and specific information, respectively. Extensive experimental results on various large-scale benchmarks demonstrate that our proposed SVP significantly outperforms state-of-the-art methods. Our code is available at https://github.com/zhoujiahuan1991/AAAI2025-SVP.

Crack detection is a critical task in structural health monitoring, aimed at assessing the structural integrity of bridges, buildings, and roads to prevent potential failures. Vision-based crack detection has become the mainstream approach due to its ease of implementation and effectiveness. Fusing infrared (IR) channels with red, green and blue (RGB) channels can enhance feature representation and thus improve crack detection. However, IR and RGB channels often differ in resolution. To align them, higher-resolution RGB images typically need to be downsampled to match the IR image resolution, which leads to the loss of fine details. Moreover, crack detection performance is restricted by the limited receptive fields and high computational complexity of traditional image segmentation networks. Inspired by the recently proposed Mamba neural architecture, this study introduces a two-stage paradigm called MSCrackMamba, which leverages Vision Mamba along with a super-resolution network to address these challenges. Specifically, to align IR and RGB channels, we first apply super-resolution to IR channels to match the resolution of RGB channels for data fusion. Vision Mamba is then adopted as the backbone network, while UperNet is employed as the decoder for crack detection. Our approach is validated on the large-scale Crack Detection dataset Crack900, demonstrating an improvement of 3.55% in mIoU compared to the best-performing baseline methods.

As remote sensing imaging technology continues to advance and evolve, processing high-resolution and diversified satellite imagery to improve segmentation accuracy and enhance interpretation efficiency emerg as a pivotal area of investigation within the realm of remote sensing. Although segmentation algorithms based on CNNs and Transformers achieve significant progress in performance, balancing segmentation accuracy and computational complexity remains challenging, limiting their wide application in practical tasks. To address this, this paper introduces state space model (SSM) and proposes a novel hybrid semantic segmentation network based on vision Mamba (CVMH-UNet). This method designs a cross-scanning visual state space block (CVSSBlock) that uses cross 2D scanning (CS2D) to fully capture global information from multiple directions, while by incorporating convolutional neural network branches to overcome the constraints of Vision Mamba (VMamba) in acquiring local information, this approach facilitates a comprehensive analysis of both global and local features. Furthermore, to address the issue of limited discriminative power and the difficulty in achieving detailed fusion with direct skip connections, a multi-frequency multi-scale feature fusion block (MFMSBlock) is designed. This module introduces multi-frequency information through 2D discrete cosine transform (2D DCT) to enhance information utilization and provides additional scale local detail information through point-wise convolution branches. Finally, it aggregates multi-scale information along the channel dimension, achieving refined feature fusion. Findings from experiments conducted on renowned datasets of remote sensing imagery demonstrate that proposed CVMH-UNet achieves superior segmentation performance while maintaining low computational complexity, outperforming surpassing current leading-edge segmentation algorithms.

Mamba and Vision Mamba (Vim) models have shown their potential as an alternative to methods based on Transformer architecture. This work introduces Fast Mamba for Vision (Famba-V), a cross-layer token fusion technique to enhance the training efficiency of Vim models. The key idea of Famba-V is to identify and fuse similar tokens across different Vim layers based on a suit of cross-layer strategies instead of simply applying token fusion uniformly across all the layers that existing works propose. We evaluate the performance of Famba-V on CIFAR-100. Our results show that Famba-V is able to enhance the training efficiency of Vim models by reducing both training time and peak memory usage during training. Moreover, the proposed cross-layer strategies allow Famba-V to deliver superior accuracy-efficiency trade-offs. These results all together demonstrate Famba-V as a promising efficiency enhancement technique for Vim models.

Mamba, a State Space Model (SSM), has recently shown competitive performance to Convolutional Neural Networks (CNNs) and Transformers in Natural Language Processing and general sequence modeling. Various attempts have been made to adapt Mamba to Computer Vision tasks, including medical image segmentation (MIS). Vision Mamba (VM)-based networks are particularly attractive due to their ability to achieve global receptive fields, similar to Vision Transformers, while also maintaining linear complexity in the number of tokens. However, the existing VM models still struggle to maintain both spatially local and global dependencies of tokens in high dimensional arrays due to their sequential nature. Employing multiple and/or complicated scanning strategies is computationally costly, which hinders applications of SSMs to high-dimensional 2D and 3D images that are common in MIS problems. In this work, we propose Local-Global Vision Mamba, LoG-VMamba, that explicitly enforces spatially adjacent tokens to remain nearby on the channel axis, and retains the global context in a compressed form. Our method allows the SSMs to access the local and global contexts even before reaching the last token while requiring only a simple scanning strategy. Our segmentation models are computationally efficient and substantially outperform both CNN and Transformers-based baselines on a diverse set of 2D and 3D MIS tasks. The implementation of LoG-VMamba is available at \url{https://github.com/Oulu-IMEDS/LoG-VMamba}.