DCFormer: Efficient 3D Vision-Language Modeling with Decomposed Convolutions

• URL: http://arxiv.org/abs/2502.05091v2
• Date: Fri, 25 Apr 2025 16:36:21 GMT
• Title: DCFormer: Efficient 3D Vision-Language Modeling with Decomposed Convolutions
• Authors: Gorkem Can Ates, Yu Xin, Kuang Gong, Wei Shao,
• Abstract summary: We introduce DCFormer, an efficient 3D image encoder that factorizes 3D convolutions into three parallel 1D convolutions along the depth, height, and width dimensions.<n>In zero-shot and fine-tuned detection of 18 pathologies, DCFormer consistently outperforms state-of-the-art 3D vision encoders.
• Score: 6.464464511743737
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Vision-language models (VLMs) have been widely applied to 2D medical image analysis due to their ability to align visual and textual representations. However, extending VLMs to 3D imaging remains computationally challenging. Existing 3D VLMs often rely on Vision Transformers (ViTs), which are computationally expensive due to the quadratic complexity of self-attention, or on 3D convolutions, which require large numbers of parameters and FLOPs as kernel size increases. We introduce DCFormer, an efficient 3D image encoder that factorizes 3D convolutions into three parallel 1D convolutions along the depth, height, and width dimensions. This design preserves spatial information while significantly reducing computational cost. Integrated into a CLIP-based vision-language framework, DCFormer is trained and evaluated on CT-RATE, a dataset of 50,188 paired 3D chest CT volumes and radiology reports. In zero-shot and fine-tuned detection of 18 pathologies, as well as in image-text retrieval tasks, DCFormer consistently outperforms state-of-the-art 3D vision encoders, including CT-ViT, ViT, ConvNeXt, PoolFormer, and TransUNet. These results highlight DCFormer's potential for scalable, clinically deployable 3D medical VLMs. Our code is available at: https://github.com/mirthAI/DCFormer.

Related papers

• Ross3D: Reconstructive Visual Instruction Tuning with 3D-Awareness [73.72335146374543]
  We introduce reconstructive visual instruction tuning with 3D-awareness (Ross3D), which integrates 3D-aware visual supervision into the training procedure. Ross3D achieves state-of-the-art performance across various 3D scene understanding benchmarks.
  arXiv  Detail & Related papers  (2025-04-02T16:59:55Z)
• HResFormer: Hybrid Residual Transformer for Volumetric Medical Image Segmentation [17.735791373128986]
  Vision Transformer shows great superiority in medical image segmentation due to the ability in learning long-range dependency.<n>We present a novel textbfHybrid textbfResidual transtextbfFormer textbf(HResFormer) for 3D medical image segmentation.
  arXiv  Detail & Related papers  (2024-12-16T05:32:28Z)
• Cross-D Conv: Cross-Dimensional Transferable Knowledge Base via Fourier Shifting Operation [3.69758875412828]
  Cross-D Conv operation bridges the dimensional gap by learning the phase shifting in the Fourier domain.<n>Our method enables seamless weight transfer between 2D and 3D convolution operations, effectively facilitating cross-dimensional learning.
  arXiv  Detail & Related papers  (2024-11-02T13:03:44Z)
• E3D-GPT: Enhanced 3D Visual Foundation for Medical Vision-Language Model [23.56751925900571]
  The development of 3D medical vision-language models holds significant potential for disease diagnosis and patient treatment. We utilize self-supervised learning to construct a 3D visual foundation model for extracting 3D visual features. We apply 3D spatial convolutions to aggregate and project high-level image features, reducing computational complexity. Our model demonstrates superior performance compared to existing methods in report generation, visual question answering, and disease diagnosis.
  arXiv  Detail & Related papers  (2024-10-18T06:31:40Z)
• EmbodiedSAM: Online Segment Any 3D Thing in Real Time [61.2321497708998]
  Embodied tasks require the agent to fully understand 3D scenes simultaneously with its exploration. An online, real-time, fine-grained and highly-generalized 3D perception model is desperately needed.
  arXiv  Detail & Related papers  (2024-08-21T17:57:06Z)
• Cross-Dimensional Medical Self-Supervised Representation Learning Based on a Pseudo-3D Transformation [68.60747298865394]
  We propose a new cross-dimensional SSL framework based on a pseudo-3D transformation (CDSSL-P3D) Specifically, we introduce an image transformation based on the im2col algorithm, which converts 2D images into a format consistent with 3D data. This transformation enables seamless integration of 2D and 3D data, and facilitates cross-dimensional self-supervised learning for 3D medical image analysis.
  arXiv  Detail & Related papers  (2024-06-03T02:57:25Z)
• CT-GLIP: 3D Grounded Language-Image Pretraining with CT Scans and Radiology Reports for Full-Body Scenarios [53.94122089629544]
  We introduce CT-GLIP (Grounded Language-Image Pretraining with CT scans), a novel method that constructs organ-level image-text pairs to enhance multimodal contrastive learning. Our method, trained on a multimodal CT dataset comprising 44,011 organ-level vision-text pairs from 17,702 patients across 104 organs, demonstrates it can identify organs and abnormalities in a zero-shot manner using natural languages.
  arXiv  Detail & Related papers  (2024-04-23T17:59:01Z)
• Any2Point: Empowering Any-modality Large Models for Efficient 3D Understanding [83.63231467746598]
  We introduce Any2Point, a parameter-efficient method to empower any-modality large models (vision, language, audio) for 3D understanding. We propose a 3D-to-any (1D or 2D) virtual projection strategy that correlates the input 3D points to the original 1D or 2D positions within the source modality.
  arXiv  Detail & Related papers  (2024-04-11T17:59:45Z)
• Generative Enhancement for 3D Medical Images [74.17066529847546]
  We propose GEM-3D, a novel generative approach to the synthesis of 3D medical images. Our method begins with a 2D slice, noted as the informed slice to serve the patient prior, and propagates the generation process using a 3D segmentation mask. By decomposing the 3D medical images into masks and patient prior information, GEM-3D offers a flexible yet effective solution for generating versatile 3D images.
  arXiv  Detail & Related papers  (2024-03-19T15:57:04Z)
• Med3DInsight: Enhancing 3D Medical Image Understanding with 2D Multi-Modal Large Language Models [1.64647940449869]
  Existing 3D convolution and transformer-based methods have limited semantic understanding of an image volume. We propose Med3DInsight, which marries existing 3D image encoders with 2D MLLMs and bridges them via a Plane-Slice-Aware Transformer (PSAT) module.
  arXiv  Detail & Related papers  (2024-03-08T08:15:53Z)
• Spatiotemporal Modeling Encounters 3D Medical Image Analysis: Slice-Shift UNet with Multi-View Fusion [0.0]
  We propose a new 2D-based model dubbed Slice SHift UNet which encodes three-dimensional features at 2D CNN's complexity. More precisely multi-view features are collaboratively learned by performing 2D convolutions along the three planes of a volume. The effectiveness of our approach is validated in Multi-Modality Abdominal Multi-Organ axis (AMOS) and Multi-Atlas Labeling Beyond the Cranial Vault (BTCV) datasets.
  arXiv  Detail & Related papers  (2023-07-24T14:53:23Z)
• Weakly Supervised Volumetric Image Segmentation with Deformed Templates [80.04326168716493]
  We propose an approach that is truly weakly-supervised in the sense that we only need to provide a sparse set of 3D point on the surface of target objects. We will show that it outperforms a more traditional approach to weak-supervision in 3D at a reduced supervision cost.
  arXiv  Detail & Related papers  (2021-06-07T22:09:34Z)

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.