MaskMamba: A Hybrid Mamba-Transformer Model for Masked Image Generation

• URL: http://arxiv.org/abs/2409.19937v1
• Date: Mon, 30 Sep 2024 04:28:55 GMT
• Title: MaskMamba: A Hybrid Mamba-Transformer Model for Masked Image Generation
• Authors: Wenchao Chen, Liqiang Niu, Ziyao Lu, Fandong Meng, Jie Zhou,
• Abstract summary: MaskMamba is a novel hybrid model that combines Mamba and Transformer architectures. It achieves a remarkable $54.44%$ improvement in inference speed at a resolution of $2048times 2048$ over Transformer.
• Score: 63.73137438677585
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Image generation models have encountered challenges related to scalability and quadratic complexity, primarily due to the reliance on Transformer-based backbones. In this study, we introduce MaskMamba, a novel hybrid model that combines Mamba and Transformer architectures, utilizing Masked Image Modeling for non-autoregressive image synthesis. We meticulously redesign the bidirectional Mamba architecture by implementing two key modifications: (1) replacing causal convolutions with standard convolutions to better capture global context, and (2) utilizing concatenation instead of multiplication, which significantly boosts performance while accelerating inference speed. Additionally, we explore various hybrid schemes of MaskMamba, including both serial and grouped parallel arrangements. Furthermore, we incorporate an in-context condition that allows our model to perform both class-to-image and text-to-image generation tasks. Our MaskMamba outperforms Mamba-based and Transformer-based models in generation quality. Notably, it achieves a remarkable $54.44\%$ improvement in inference speed at a resolution of $2048\times 2048$ over Transformer.

Related papers

• Mamba-ST: State Space Model for Efficient Style Transfer [5.869642560299033]
  This paper explores a novel design of Mamba, an emergent State-Space Model (SSM), to perform style transfer. To do so, we adapt Mamba linear equation to simulate the behavior of cross-attention layers, which are able to combine two separate embeddings into a single output. Results show improved quality in terms of both ArtFID and FID metrics.
  arXiv  Detail & Related papers  (2024-09-16T15:20:48Z)
• The Mamba in the Llama: Distilling and Accelerating Hybrid Models [76.64055251296548]
  We show that it is feasible to distill large Transformers into linear RNNs by reusing the linear projection weights from attention layers with academic GPU resources. The resulting hybrid model, which incorporates a quarter of the attention layers, achieves performance comparable to the original Transformer in chat benchmarks.
  arXiv  Detail & Related papers  (2024-08-27T17:56:11Z)
• Scalable Autoregressive Image Generation with Mamba [23.027439743155192]
  We introduce AiM, an autoregressive (AR) image generative model based on Mamba architecture. Mamba is a novel state-space model characterized by its exceptional performance for long-sequence modeling with linear time. We provide AiM models in various scales, with parameter counts ranging from 148M to 1.3B.
  arXiv  Detail & Related papers  (2024-08-22T09:27:49Z)
• Transformers to SSMs: Distilling Quadratic Knowledge to Subquadratic Models [92.36510016591782]
  We present a method that is able to distill a pretrained Transformer architecture into alternative architectures such as state space models (SSMs) Our method, called MOHAWK, is able to distill a Mamba-2 variant based on the Phi-1.5 architecture using only 3B tokens and a hybrid version (Hybrid Phi-Mamba) using 5B tokens. Despite using less than 1% of the training data typically used to train models from scratch, Phi-Mamba boasts substantially stronger performance compared to all past open-source non-Transformer models.
  arXiv  Detail & Related papers  (2024-08-19T17:48:11Z)
• MambaVision: A Hybrid Mamba-Transformer Vision Backbone [54.965143338206644]
  We propose a novel hybrid Mamba-Transformer backbone, denoted as MambaVision, which is specifically tailored for vision applications. Our core contribution includes redesigning the Mamba formulation to enhance its capability for efficient modeling of visual features. We conduct a comprehensive ablation study on the feasibility of integrating Vision Transformers (ViT) with Mamba.
  arXiv  Detail & Related papers  (2024-07-10T23:02:45Z)
• An Empirical Study of Mamba-based Language Models [69.74383762508805]
  Selective state-space models (SSMs) like Mamba overcome some shortcomings of Transformers. We present a direct comparison between 8B-context Mamba, Mamba-2, and Transformer models trained on the same datasets. We find that the 8B Mamba-2-Hybrid exceeds the 8B Transformer on all 12 standard tasks.
  arXiv  Detail & Related papers  (2024-06-12T05:25:15Z)
• Dimba: Transformer-Mamba Diffusion Models [32.04949173308355]
  This paper unveils Dimba, a new text-to-image diffusion model that employs a distinctive hybrid architecture combining Transformer and Mamba elements. Extensive experiments indicate that Dimba achieves comparable performance compared with benchmarks in terms of image quality, artistic rendering, and semantic control.
  arXiv  Detail & Related papers  (2024-06-03T09:51:59Z)
• Demystify Mamba in Vision: A Linear Attention Perspective [72.93213667713493]
  Mamba is an effective state space model with linear computation complexity. We show that Mamba shares surprising similarities with linear attention Transformer. We propose a Mamba-Like Linear Attention (MLLA) model by incorporating the merits of these two key designs into linear attention.
  arXiv  Detail & Related papers  (2024-05-26T15:31:09Z)
• Mamba-in-Mamba: Centralized Mamba-Cross-Scan in Tokenized Mamba Model for Hyperspectral Image Classification [4.389334324926174]
  This study introduces the innovative Mamba-in-Mamba (MiM) architecture for HSI classification, the first attempt of deploying State Space Model (SSM) in this task. MiM model includes 1) A novel centralized Mamba-Cross-Scan (MCS) mechanism for transforming images into sequence-data, 2) A Tokenized Mamba (T-Mamba) encoder, and 3) A Weighted MCS Fusion (WMF) module. Experimental results from three public HSI datasets demonstrate that our method outperforms existing baselines and state-of-the-art approaches.
  arXiv  Detail & Related papers  (2024-05-20T13:19:02Z)

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.