paper-with-me

홈 › Papers

Efficient Bilinear Attention-based Fusion for Medical Visual Question Answering

2024-10-28 · Zhilin Zhang, Jie Wang, Zhanghao Qin, Ruiqi Zhu, Xiaoliang Gong

Medical Visual Question Answering (MedVQA) has attracted growing interest at the intersection of medical image understanding and natural language processing for clinical applications. By interpreting medical images and providing precise answers to relevant clinical inquiries, MedVQA has the potential to support diagnostic decision-making and reduce workload across various fields like radiology. While recent approaches rely heavily on unified large pre-trained Visual-Language Models, research on more efficient fusion mechanisms remains relatively limited in this domain. In this paper, we introduce a fusion model, OMniBAN, that integrates Orthogonality loss, Multi-head attention, and a Bilinear Attention Network to achieve high computational efficiency as well as solid performance. We conduct comprehensive experiments and demonstrate how bilinear attention fusion can approximate the performance of larger fusion models like cross-modal Transformer. Our results show that OMniBAN requires fewer parameters (approximately 2/3 of Transformer-based Co-Attention) and substantially lower FLOPs (approximately 1/4), while achieving comparable overall performance and even slight improvements on closed-ended questions on two key MedVQA benchmarks. This balance between efficiency and accuracy suggests that OMniBAN could be a viable option for real-world medical image question answering, where computational resources are often constrained.

📄 PDF Abstract BibTeX arXiv:2410.21000

Code (0)

등록된 구현이 없습니다.

Tasks

Computational EfficiencyDecision MakingDiagnosticMedical Visual Question AnsweringQuestion AnsweringVisual Question AnsweringVisual Question Answering (VQA)

Methods 이 논문이 사용한 방법론

Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Residual Connection 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Position-Wise Feed-Forward Layer 설명 없음
Adam 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Similar Papers 제목 키워드 기반

Multi-modal Factorized Bilinear Pooling with Co-Attention Learning for Visual Question Answering

2017-08-04 · ICCV 2017 10 · Zhou Yu, Jun Yu, Jianping Fan, DaCheng Tao

Visual question answering (VQA) is challenging because it requires a simultaneous understanding of both the visual content of images and the textual content of questions. The approaches used to represent the images and q…

Question AnsweringVisual Question AnsweringVisual Question Answering (VQA)

Hadamard Product for Low-rank Bilinear Pooling

2016-10-14 · Jin-Hwa Kim, Kyoung-Woon On, Woosang Lim, Jeonghee Kim 외

Bilinear models provide rich representations compared with linear models. They have been applied in various visual tasks, such as object recognition, segmentation, and visual question-answering, to get state-of-the-art p…

Visual Question AnsweringVisual Question Answering (VQA)

Bilinear Graph Networks for Visual Question Answering

2019-07-23 · Dalu Guo, Chang Xu, DaCheng Tao

This paper revisits the bilinear attention networks in the visual question answering task from a graph perspective. The classical bilinear attention networks build a bilinear attention map to extract the joint representa…

Question AnsweringVisual Question AnsweringVisual Question Answering (VQA)

MUTAN: Multimodal Tucker Fusion for Visual Question Answering

2017-05-18 · ICCV 2017 10 · Hedi Ben-Younes, Rémi Cadene, Matthieu Cord, Nicolas Thome

Bilinear models provide an appealing framework for mixing and merging information in Visual Question Answering (VQA) tasks. They help to learn high level associations between question meaning and visual concepts in the i…

Visual Question AnsweringVisual Question Answering (VQA)

Bilinear Attention Networks

2018-05-21 · NeurIPS 2018 12 · Jin-Hwa Kim, Jaehyun Jun, Byoung-Tak Zhang

Attention networks in multimodal learning provide an efficient way to utilize given visual information selectively. However, the computational cost to learn attention distributions for every pair of multimodal input chan…

Visual Question AnsweringVisual Question Answering (VQA)