Light field (LF)Salient object detectionSegment anything modelAdapterFeature fusionWe propose a SAM-based network for accurate light field salient object detection.We use an adaptive method to extract saliency information and spatial details.A 3D convolution-based CMFM is designed to fuse complementary...
【TMM2024】Frequency-Guided Spatial Adaptation for Camouflaged Object Detection 论文链接: https://arxiv.org/abs/2409.12421这个论文研究 Camouflaged Object Detection (COD)问题,作者认为,使用 pretrained foundation model 可以改进COD的准确率,但是当前的 ada… 高峰OUC发表于OUC的搬... MULTI-SCALE CONTEXT AGGRE...
代码:https://github.com/BellyBeauty/MDSAM 论文的研究动机就是使用SAM来解决显著性检测(SOD)问题,主要有两个改进: 提出了Lightweight Multi-Scale Adapter, LMSA来微调SAM 提出了Multi-Level Fusion Module, MLFM 和 Detail Enhancement Module, DEM,分别改善了SAM在多尺度和细粒度感知方面的性能。 网络的整体架...
Joint semantic mining for weakly supervised RGB-D salient object detection. In Proceedings of the 35th Conference on Neural Information Processing Syste, pp. 11945–11959, 2021. M. A. Mazurowski, H. Y. Dong, H. X. Gu, J. C. Yang, N. Konz, Y. X. Zhang. Segment anything model for ...
Anomaly Detection Salient Object Detection Building Extracting License The model is licensed under theApache 2.0 license. Acknowledgement Segment Anythingprovides the SA-1B dataset and the base codes. YOLOv8provides codes and pre-trained models. ...
[2025.01]Progressive Self-Prompting Segment Anything Model for Salient Object Detection in Optical Remote Sensing Images [2024.12]Adapting SAM2 Model from Natural Images for Tooth Segmentation in Dental Panoramic X-Ray Images [2024.11]SAM-I2I: Unleash the Power of Segment Anything Model for Medical Im...
We rethink the segment anything model (SAM) and propose a novel multiprompt network called COMPrompter for camouflaged object detection (COD). SAM has zero-shot generalization ability beyond other models and can provide an ideal framework for COD. Our network aims to enhance the single prompt str...
Obtain salient objects by performing background subtraction using adaptive Gaussian thresholding [73], as explained in Sect.3.1. 2) Enhance the obtained salient object boundaries from the previous step with optical flow using RAFT [74], as explained in Sect.3.2. ...
"Modality Registration and Object Search Framework for UAV-based Unregistered RGB-T Image Salient Object Detection." ArXiv (2023). [paper] [code] [2023.11] CPVLF: Lv Tang, Peng-Tao Jiang, Zhihao Shen, Hao Zhang, Jinwei Chen, Bo Li. "Generalization and Hallucination of Large Vision-Language...
"Adaptive Low Rank Adaptation of Segment Anything to Salient Object Detection." ArXiv (2023). [paper] AquaSAM:Muduo Xu, Jianhao Su, Yutao Liu. "AquaSAM: Underwater Image Foreground Segmentation." ArXiv (2023). [paper] AdaptiveSAM:Jay N. Paranjape, Nithin Gopalakrishnan Nair, Shameema Sikder...