MambaEye: A Size-Agnostic Visual Encoder with Causal Sequential Processing

• URL: http://arxiv.org/abs/2511.19963v1
• Date: Tue, 25 Nov 2025 06:18:18 GMT
• Title: MambaEye: A Size-Agnostic Visual Encoder with Causal Sequential Processing
• Authors: Changho Choi, Minho Kim, Jinkyu Kim,
• Abstract summary: MambaEye is a novel, causal sequential encoder that leverages the low complexity and causal-process based pure Mamba2 backbone.<n>Unlike previous Mamba-based vision encoders that often employ bidirectional processing, our strictly unidirectional approach preserves the inherent causality of State Space Models.<n>MambaEye exhibits robust performance across a wide range of image resolutions, especially at higher resolutions such as $15362$ on the ImageNet-1K classification task.
• Score: 14.888533532729864
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Despite decades of progress, a truly input-size agnostic visual encoder-a fundamental characteristic of human vision-has remained elusive. We address this limitation by proposing \textbf{MambaEye}, a novel, causal sequential encoder that leverages the low complexity and causal-process based pure Mamba2 backbone. Unlike previous Mamba-based vision encoders that often employ bidirectional processing, our strictly unidirectional approach preserves the inherent causality of State Space Models, enabling the model to generate a prediction at any point in its input sequence. A core innovation is our use of relative move embedding, which encodes the spatial shift between consecutive patches, providing a strong inductive bias for translation invariance and making the model inherently adaptable to arbitrary image resolutions and scanning patterns. To achieve this, we introduce a novel diffusion-inspired loss function that provides dense, step-wise supervision, training the model to build confidence as it gathers more visual evidence. We demonstrate that MambaEye exhibits robust performance across a wide range of image resolutions, especially at higher resolutions such as $1536^2$ on the ImageNet-1K classification task. This feat is achieved while maintaining linear time and memory complexity relative to the number of patches.

Related papers

• MambaMIL+: Modeling Long-Term Contextual Patterns for Gigapixel Whole Slide Image [24.093388981091717]
  Multiple instance learning (MIL) offers a solution by treating each WSI as a bag of patch-level instances.<n>Mamba has emerged as a promising alternative for long sequence learning, scaling linearly to thousands of tokens.<n>We propose MambaMIL+, a new MIL framework that explicitly integrates spatial context while maintaining long-range dependency modeling.
  arXiv  Detail & Related papers  (2025-12-19T16:01:14Z)
• VQRAE: Representation Quantization Autoencoders for Multimodal Understanding, Generation and Reconstruction [83.50898344094153]
  VQRAE produces Continuous semantic features for image understanding and tokens for visual generation within a unified tokenizer.<n>Design enables negligible semantic information for maintaining the ability of multimodal understanding, discrete tokens.<n>VQRAE presents competitive performance on several benchmarks of visual understanding, generation and reconstruction.
  arXiv  Detail & Related papers  (2025-11-28T17:26:34Z)
• Hawk: Leveraging Spatial Context for Faster Autoregressive Text-to-Image Generation [87.00172597953228]
  Speculative decoding has shown promise in accelerating text generation without compromising quality.<n>We introduce Hawk, a new approach that harnesses the spatial structure of images to guide the speculative model toward more accurate and efficient predictions.<n> Experimental results on multiple text-to-image benchmarks demonstrate a 1.71x speedup over standard AR models.
  arXiv  Detail & Related papers  (2025-10-29T17:43:31Z)
• Scaling Vision Mamba Across Resolutions via Fractal Traversal [9.566046692165884]
  Vision Mamba has recently emerged as a promising alternative to Transformer-based architectures.<n>We propose FractalMamba++, a vision backbone that leverages fractal-based patch serialization via Hilbert curves.<n>We show that FractalMamba++ consistently outperforms previous Mamba-based backbones.
  arXiv  Detail & Related papers  (2025-05-20T08:08:28Z)
• DefMamba: Deformable Visual State Space Model [65.50381013020248]
  We propose a novel visual foundation model called DefMamba.<n>By combining a deformable scanning(DS) strategy, this model significantly improves its ability to learn image structures and detects changes in object details.<n>Numerous experiments have shown that DefMamba achieves state-of-the-art performance in various visual tasks.
  arXiv  Detail & Related papers  (2025-04-08T08:22:54Z)
• Detail Matters: Mamba-Inspired Joint Unfolding Network for Snapshot Spectral Compressive Imaging [40.80197280147993]
  We propose a Mamba-inspired Joint Unfolding Network (MiJUN) to overcome the inherent nonlinear and ill-posed characteristics of HSI reconstruction.<n>We introduce an accelerated unfolding network scheme, which reduces the reliance on initial optimization stages.<n>We refine the scanning strategy with Mamba by integrating the tensor mode-$k$ unfolding into the Mamba network.
  arXiv  Detail & Related papers  (2025-01-02T13:56:23Z)
• Multi-dimensional Visual Prompt Enhanced Image Restoration via Mamba-Transformer Aggregation [4.227991281224256]
  This paper proposes to fully utilize complementary advantages from Mamba and Transformer without sacrificing computation efficiency.<n>The selective scanning mechanism of Mamba is employed to focus on spatial modeling, enabling capture long-range spatial dependencies.<n>The self-attention mechanism of Transformer is applied to focus on channel modeling, avoiding high burdens that are in quadratic growth with image's spatial dimensions.
  arXiv  Detail & Related papers  (2024-12-20T12:36:34Z)
• Collaborative Decoding Makes Visual Auto-Regressive Modeling Efficient [52.96232442322824]
  Collaborative Decoding (CoDe) is a novel efficient decoding strategy tailored for the Visual Auto-Regressive ( VAR) framework.<n>CoDe capitalizes on two critical observations: the substantially reduced parameter demands at larger scales and the exclusive generation patterns across different scales.<n>CoDe achieves a 1.7x speedup, slashes memory usage by around 50%, and preserves image quality with only a negligible FID increase from 1.95 to 1.98.
  arXiv  Detail & Related papers  (2024-11-26T15:13:15Z)
• MMAR: Towards Lossless Multi-Modal Auto-Regressive Probabilistic Modeling [64.09238330331195]
  We propose a novel Multi-Modal Auto-Regressive (MMAR) probabilistic modeling framework.<n>Unlike discretization line of method, MMAR takes in continuous-valued image tokens to avoid information loss in an efficient way.<n>We also propose a theoretically proven technique that addresses the numerical stability issue and a training strategy that balances the generation and understanding task goals.
  arXiv  Detail & Related papers  (2024-10-14T17:57:18Z)
• LinFusion: 1 GPU, 1 Minute, 16K Image [71.44735417472043]
  We introduce a low-rank approximation of a wide spectrum of popular linear token mixers. We find that the distilled model, termed LinFusion, achieves performance on par with or superior to the original SD. Experiments on SD-v1.5, SD-v2.1, and SD-XL demonstrate that LinFusion enables satisfactory and efficient zero-shot cross-resolution generation.
  arXiv  Detail & Related papers  (2024-09-03T17:54:39Z)
• Demystify Mamba in Vision: A Linear Attention Perspective [72.93213667713493]
  Mamba is an effective state space model with linear computation complexity.<n>We show that Mamba shares surprising similarities with linear attention Transformer.<n>We propose a Mamba-Inspired Linear Attention (MILA) model by incorporating the merits of these two key designs into linear attention.
  arXiv  Detail & Related papers  (2024-05-26T15:31:09Z)
• Arbitrary-Scale Image Generation and Upsampling using Latent Diffusion Model and Implicit Neural Decoder [29.924160271522354]
  Super-resolution (SR) and image generation are important tasks in computer vision and are widely adopted in real-world applications. Most existing methods, however, generate images only at fixed-scale magnification and suffer from over-smoothing and artifacts. Most relevant work applied Implicit Neural Representation (INR) to the denoising diffusion model to obtain continuous-resolution yet diverse and high-quality SR results. We propose a novel pipeline that can super-resolve an input image or generate from a random noise a novel image at arbitrary scales.
  arXiv  Detail & Related papers  (2024-03-15T12:45:40Z)

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.