Segment any object model (saom): Real-to-simulation fine-tuning strategy for multi-class multi-instance segmentation

M Khan, Y Qiu, Y Cong, B Rosenhahn… - … on Image Processing …, 2024 - ieeexplore.ieee.org
Multi-class multi-instance segmentation is the task of identifying masks for multiple object
classes and multiple instances of the same class within an image. The foundational …

SSFam: Scribble Supervised Salient Object Detection Family

Z Liu, S Deng, X Wang, L Wang, X Fang… - arXiv preprint arXiv …, 2024 - arxiv.org
Scribble supervised salient object detection (SSSOD) constructs segmentation ability of
attractive objects from surroundings under the supervision of sparse scribble labels. For the …

[HTML][HTML] Reducing Training Data Using Pre-Trained Foundation Models: A Case Study on Traffic Sign Segmentation Using the Segment Anything Model

S Henninger, M Kellner, B Rombach, A Reiterer - Journal of Imaging, 2024 - mdpi.com
The utilization of robust, pre-trained foundation models enables simple adaptation to specific
ongoing tasks. In particular, the recently developed Segment Anything Model (SAM) has …

Multi-Scale and Detail-Enhanced Segment Anything Model for Salient Object Detection

S Gao, P Zhang, T Yan, H Lu - arXiv preprint arXiv:2408.04326, 2024 - arxiv.org
Salient Object Detection (SOD) aims to identify and segment the most prominent objects in
images. Advanced SOD methods often utilize various Convolutional Neural Networks (CNN) …

Adapting Segment Anything Model to Multi-modal Salient Object Detection with Semantic Feature Fusion Guidance

K Wang, K Chen, C Li, Z Tu, B Luo - arXiv preprint arXiv:2408.15063, 2024 - arxiv.org
Although most existing multi-modal salient object detection (SOD) methods demonstrate
effectiveness through training models from scratch, the limited multi-modal data hinders …

Enhancing Aspect-based Sentiment Analysis in Tourism Using Large Language Models and Positional Information

C Xu, M Wang, Y Ren, S Zhu - arXiv preprint arXiv:2409.14997, 2024 - arxiv.org
Aspect-Based Sentiment Analysis (ABSA) in tourism plays a significant role in
understanding tourists' evaluations of specific aspects of attractions, which is crucial for …

DLoRA-TrOCR: Mixed Text Mode Optical Character Recognition Based On Transformer

D Chang, Y Li - arXiv preprint arXiv:2404.12734, 2024 - arxiv.org
With the continuous development of OCR technology and the expansion of application
fields, text recognition in complex scenes has become a key challenge. Factors such as …