Transformer-based RGB-T Tracking with Channel and Spatial Feature Fusion

• URL: http://arxiv.org/abs/2405.03177v2
• Date: Sat, 20 Jul 2024 12:17:11 GMT
• Title: Transformer-based RGB-T Tracking with Channel and Spatial Feature Fusion
• Authors: Yunfeng Li, Bo Wang, Ye Li, Zhiwen Yu, Liang Wang,
• Abstract summary: We show how to improve the performance of a visual Transformer by using direct fusion of cross-modal channels and spatial features. CSTNet achieves state-of-the-art performance on three public RGB-T tracking benchmarks.
• Score: 12.982885009492389
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: How to better fuse cross-modal features is the core issue of RGB-T tracking. Some previous methods either insufficiently fuse RGB and TIR features, or depend on intermediaries containing information from both modalities to achieve cross-modal information interaction. The former does not fully exploit the potential of using only RGB and TIR information of the template or search region for channel and spatial feature fusion, and the latter lacks direct interaction between the template and search area, which limits the model's ability to fully exploit the original semantic information of both modalities. To alleviate these limitations, we explore how to improve the performance of a visual Transformer by using direct fusion of cross-modal channels and spatial features, and propose CSTNet. CSTNet uses ViT as a backbone and inserts cross-modal channel feature fusion modules (CFM) and cross-modal spatial feature fusion modules (SFM) for direct interaction between RGB and TIR features. The CFM performs parallel joint channel enhancement and joint multilevel spatial feature modeling of RGB and TIR features and sums the features, and then globally integrates the sum feature with the original features. The SFM uses cross-attention to model the spatial relationship of cross-modal features and then introduces a convolutional feedforward network for joint spatial and channel integration of multimodal features. We retrain the model with CSNet as the pre-training weights in the model with CFM and SFM removed, and propose CSTNet-small, which achieves 36% reduction in parameters and 24% reduction in Flops, and 50% speedup with a 1-2% performance decrease. Comprehensive experiments show that CSTNet achieves state-of-the-art performance on three public RGB-T tracking benchmarks. Code is available at https://github.com/LiYunfengLYF/CSTNet.

Related papers

• Cross Fusion RGB-T Tracking with Bi-directional Adapter [8.425592063392857]
  We propose a novel Cross Fusion RGB-T Tracking architecture (CFBT) The effectiveness of CFBT relies on three newly designed cross-temporal information fusion modules. Experiments on three popular RGB-T tracking benchmarks demonstrate that our method achieves new state-of-the-art performance.
  arXiv  Detail & Related papers  (2024-08-30T02:45:56Z)
• WCCNet: Wavelet-integrated CNN with Crossmodal Rearranging Fusion for Fast Multispectral Pedestrian Detection [16.43119521684829]
  We propose a novel framework named WCCNet that is able to differentially extract rich features of different spectra with lower computational complexity. Based on the well extracted features, we elaborately design the crossmodal rearranging fusion module (CMRF) We conduct comprehensive evaluations on KAIST and FLIR benchmarks, in which WCCNet outperforms state-of-the-art methods with considerable computational efficiency and competitive accuracy.
  arXiv  Detail & Related papers  (2023-08-02T09:35:21Z)
• Dual Swin-Transformer based Mutual Interactive Network for RGB-D Salient Object Detection [67.33924278729903]
  In this work, we propose Dual Swin-Transformer based Mutual Interactive Network. We adopt Swin-Transformer as the feature extractor for both RGB and depth modality to model the long-range dependencies in visual inputs. Comprehensive experiments on five standard RGB-D SOD benchmark datasets demonstrate the superiority of the proposed DTMINet method.
  arXiv  Detail & Related papers  (2022-06-07T08:35:41Z)
• SwinNet: Swin Transformer drives edge-aware RGB-D and RGB-T salient object detection [12.126413875108993]
  We propose a cross-modality fusion model SwinNet for RGB-D and RGB-T salient object detection. The proposed model outperforms the state-of-the-art models on RGB-D and RGB-T datasets.
  arXiv  Detail & Related papers  (2022-04-12T07:37:39Z)
• Transformer-based Network for RGB-D Saliency Detection [82.6665619584628]
  Key to RGB-D saliency detection is to fully mine and fuse information at multiple scales across the two modalities. We show that transformer is a uniform operation which presents great efficacy in both feature fusion and feature enhancement. Our proposed network performs favorably against state-of-the-art RGB-D saliency detection methods.
  arXiv  Detail & Related papers  (2021-12-01T15:53:58Z)
• Middle-level Fusion for Lightweight RGB-D Salient Object Detection [81.43951906434175]
  A novel lightweight RGB-D SOD model is presented in this paper. With IMFF and L modules incorporated in the middle-level fusion structure, our proposed model has only 3.9M parameters and runs at 33 FPS. The experimental results on several benchmark datasets verify the effectiveness and superiority of the proposed method over some state-of-the-art methods.
  arXiv  Detail & Related papers  (2021-04-23T11:37:15Z)
• Self-Supervised Representation Learning for RGB-D Salient Object Detection [93.17479956795862]
  We use Self-Supervised Representation Learning to design two pretext tasks: the cross-modal auto-encoder and the depth-contour estimation. Our pretext tasks require only a few and un RGB-D datasets to perform pre-training, which make the network capture rich semantic contexts. For the inherent problem of cross-modal fusion in RGB-D SOD, we propose a multi-path fusion module.
  arXiv  Detail & Related papers  (2021-01-29T09:16:06Z)
• RGB-D Salient Object Detection with Cross-Modality Modulation and Selection [126.4462739820643]
  We present an effective method to progressively integrate and refine the cross-modality complementarities for RGB-D salient object detection (SOD) The proposed network mainly solves two challenging issues: 1) how to effectively integrate the complementary information from RGB image and its corresponding depth map, and 2) how to adaptively select more saliency-related features.
  arXiv  Detail & Related papers  (2020-07-14T14:22:50Z)
• Jointly Modeling Motion and Appearance Cues for Robust RGB-T Tracking [85.333260415532]
  We develop a novel late fusion method to infer the fusion weight maps of both RGB and thermal (T) modalities. When the appearance cue is unreliable, we take motion cues into account to make the tracker robust. Numerous results on three recent RGB-T tracking datasets show that the proposed tracker performs significantly better than other state-of-the-art algorithms.
  arXiv  Detail & Related papers  (2020-07-04T08:11:33Z)

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.