CLIP-Mamba: CLIP Pretrained Mamba Models with OOD and Hessian Evaluation

• URL: http://arxiv.org/abs/2404.19394v1
• Date: Tue, 30 Apr 2024 09:40:07 GMT
• Title: CLIP-Mamba: CLIP Pretrained Mamba Models with OOD and Hessian Evaluation
• Authors: Weiquan Huang, Yifei Shen, Yifan Yang,
• Abstract summary: This report introduces the first attempt to train a Mamba model utilizing contrastive technical-image pretraining (CLIP) A Mamba model 67 million parameters is on par with a 307 million- parameters Vision Transformer (ViT) model in zero-shot classification tasks.
• Score: 18.383760896304604
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: State space models and Mamba-based models have been increasingly applied across various domains, achieving state-of-the-art performance. This technical report introduces the first attempt to train a transferable Mamba model utilizing contrastive language-image pretraining (CLIP). We have trained Mamba models of varying sizes and undertaken comprehensive evaluations of these models on 26 zero-shot classification datasets and 16 out-of-distribution (OOD) datasets. Our findings reveal that a Mamba model with 67 million parameters is on par with a 307 million-parameter Vision Transformer (ViT) model in zero-shot classification tasks, highlighting the parameter efficiency of Mamba models. In tests of OOD generalization, Mamba-based models exhibit exceptional performance in conditions of OOD image contrast or when subjected to high-pass filtering. However, a Hessian analysis indicates that Mamba models feature a sharper and more non-convex landscape compared to ViT-based models, making them more challenging to train. The source code is available at https://github.com/raytrun/mamba-clip.

Related papers

• 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)
• A Survey of Mamba [27.939712558507516]
  Recently, a novel architecture named Mamba has emerged as a promising alternative for building foundation models. This study investigates the advancements of Mamba-based models, the techniques of adapting Mamba to diverse data, and the applications where Mamba can excel.
  arXiv  Detail & Related papers  (2024-08-02T09:18:41Z)
• GroupMamba: Parameter-Efficient and Accurate Group Visual State Space Model [66.35608254724566]
  State-space models (SSMs) have showcased effective performance in modeling long-range dependencies with subquadratic complexity. However, pure SSM-based models still face challenges related to stability and achieving optimal performance on computer vision tasks. Our paper addresses the challenges of scaling SSM-based models for computer vision, particularly the instability and inefficiency of large model sizes.
  arXiv  Detail & Related papers  (2024-07-18T17:59:58Z)
• 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)
• Vision Mamba for Classification of Breast Ultrasound Images [9.90112908284836]
  Mamba-based models, VMamba and Vim, are a recent family of vision encoders that offer promising performance improvements in many computer vision tasks. This paper compares Mamba-based models with traditional Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs) using the breast ultrasound BUSI dataset and Breast Ultrasound B dataset.
  arXiv  Detail & Related papers  (2024-07-04T00:21:47Z)
• 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)
• The Hidden Attention of Mamba Models [54.50526986788175]
  The Mamba layer offers an efficient selective state space model (SSM) that is highly effective in modeling multiple domains. We show that such models can be viewed as attention-driven models. This new perspective enables us to empirically and theoretically compare the underlying mechanisms to that of the self-attention layers in transformers.
  arXiv  Detail & Related papers  (2024-03-03T18:58:21Z)
• Swin-UMamba: Mamba-based UNet with ImageNet-based pretraining [85.08169822181685]
  This paper introduces a novel Mamba-based model, Swin-UMamba, designed specifically for medical image segmentation tasks. Swin-UMamba demonstrates superior performance with a large margin compared to CNNs, ViTs, and latest Mamba-based models.
  arXiv  Detail & Related papers  (2024-02-05T18:58:11Z)
• MoE-Mamba: Efficient Selective State Space Models with Mixture of Experts [4.293771840782942]
  State Space Models (SSMs) have become serious contenders in the field of sequential modeling. MoE has significantly improved Transformer-based Large Language Models, including recent state-of-the-art open models. We propose that to unlock the potential of SSMs for scaling, they should be combined with MoE.
  arXiv  Detail & Related papers  (2024-01-08T18:35:07Z)

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.