FoRA: Low-Rank Adaptation Model beyond Multimodal Siamese Network

• URL: http://arxiv.org/abs/2407.16129v1
• Date: Tue, 23 Jul 2024 02:27:52 GMT
• Title: FoRA: Low-Rank Adaptation Model beyond Multimodal Siamese Network
• Authors: Weiying Xie, Yusi Zhang, Tianlin Hui, Jiaqing Zhang, Jie Lei, Yunsong Li,
• Abstract summary: We propose a novel multimodal object detector, named Low-rank Modal Adaptors (LMA) with a shared backbone. Our work was submitted to ACM MM in April 2024, but was rejected.
• Score: 19.466279425330857
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Multimodal object detection offers a promising prospect to facilitate robust detection in various visual conditions. However, existing two-stream backbone networks are challenged by complex fusion and substantial parameter increments. This is primarily due to large data distribution biases of multimodal homogeneous information. In this paper, we propose a novel multimodal object detector, named Low-rank Modal Adaptors (LMA) with a shared backbone. The shared parameters enhance the consistency of homogeneous information, while lightweight modal adaptors focus on modality unique features. Furthermore, we design an adaptive rank allocation strategy to adapt to the varying heterogeneity at different feature levels. When applied to two multimodal object detection datasets, experiments validate the effectiveness of our method. Notably, on DroneVehicle, LMA attains a 10.4% accuracy improvement over the state-of-the-art method with a 149M-parameters reduction. The code is available at https://github.com/zyszxhy/FoRA. Our work was submitted to ACM MM in April 2024, but was rejected. We will continue to refine our work and paper writing next, mainly including proof of theory and multi-task applications of FoRA.

Related papers

• RADAR: Robust Two-stage Modality-incomplete Industrial Anomaly Detection [61.71770293720491]
  We propose a novel two-stage Robust modAlity-imcomplete fusing and Detecting frAmewoRk, abbreviated as RADAR. Our bootstrapping philosophy is to enhance two stages in MIIAD, improving the robustness of the Multimodal Transformer. Our experimental results demonstrate that the proposed RADAR significantly surpasses conventional MIAD methods in terms of effectiveness and robustness.
  arXiv  Detail & Related papers  (2024-10-02T16:47:55Z)
• AMFD: Distillation via Adaptive Multimodal Fusion for Multispectral Pedestrian Detection [23.91870504363899]
  Double-stream networks in multispectral detection employ two separate feature extraction branches for multi-modal data. This has hindered the widespread employment of multispectral pedestrian detection in embedded devices for autonomous systems. We introduce the Adaptive Modal Fusion Distillation (AMFD) framework, which can fully utilize the original modal features of the teacher network.
  arXiv  Detail & Related papers  (2024-05-21T17:17:17Z)
• Multimodal Information Interaction for Medical Image Segmentation [24.024848382458767]
  We introduce an innovative Multimodal Information Cross Transformer (MicFormer) It queries features from one modality and retrieves corresponding responses from another, facilitating effective communication between bimodal features. Compared to other multimodal segmentation techniques, our method outperforms by margins of 2.83 and 4.23, respectively.
  arXiv  Detail & Related papers  (2024-04-25T07:21:14Z)
• Bi-directional Adapter for Multi-modal Tracking [67.01179868400229]
  We propose a novel multi-modal visual prompt tracking model based on a universal bi-directional adapter. We develop a simple but effective light feature adapter to transfer modality-specific information from one modality to another. Our model achieves superior tracking performance in comparison with both the full fine-tuning methods and the prompt learning-based methods.
  arXiv  Detail & Related papers  (2023-12-17T05:27:31Z)
• An Empirical Study of Multimodal Model Merging [148.48412442848795]
  Model merging is a technique that fuses multiple models trained on different tasks to generate a multi-task solution. We conduct our study for a novel goal where we can merge vision, language, and cross-modal transformers of a modality-specific architecture. We propose two metrics that assess the distance between weights to be merged and can serve as an indicator of the merging outcomes.
  arXiv  Detail & Related papers  (2023-04-28T15:43:21Z)
• Weakly Aligned Feature Fusion for Multimodal Object Detection [52.15436349488198]
  multimodal data often suffer from the position shift problem, i.e., the image pair is not strictly aligned. This problem makes it difficult to fuse multimodal features and puzzles the convolutional neural network (CNN) training. In this article, we propose a general multimodal detector named aligned region CNN (AR-CNN) to tackle the position shift problem.
  arXiv  Detail & Related papers  (2022-04-21T02:35:23Z)
• Modal-Adaptive Gated Recoding Network for RGB-D Salient Object Detection [2.9153096940947796]
  We propose a novel gated recoding network (GRNet) to evaluate the information validity of the two modes. A perception encoder is adopted to extract multi-level single-modal features. A modal-adaptive gate unit is proposed to suppress the invalid information and transfer the effective modal features to the recoding mixer and the hybrid branch decoder.
  arXiv  Detail & Related papers  (2021-08-13T15:08:21Z)
• MRDet: A Multi-Head Network for Accurate Oriented Object Detection in Aerial Images [51.227489316673484]
  We propose an arbitrary-oriented region proposal network (AO-RPN) to generate oriented proposals transformed from horizontal anchors. To obtain accurate bounding boxes, we decouple the detection task into multiple subtasks and propose a multi-head network. Each head is specially designed to learn the features optimal for the corresponding task, which allows our network to detect objects accurately.
  arXiv  Detail & Related papers  (2020-12-24T06:36:48Z)
• Exploring Data Augmentation for Multi-Modality 3D Object Detection [82.9988604088494]
  It is counter-intuitive that multi-modality methods based on point cloud and images perform only marginally better or sometimes worse than approaches that solely use point cloud. We propose a pipeline, named transformation flow, to bridge the gap between single and multi-modality data augmentation with transformation reversing and replaying. Our method also wins the best PKL award in the 3rd nuScenes detection challenge.
  arXiv  Detail & Related papers  (2020-12-23T15:23:16Z)

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.