Redirigiendo al acceso original de articulo en 17 segundos...
Inicio  /  Applied Sciences  /  Vol: 12 Par: 18 (2022)  /  Artículo
ARTÍCULO
TITULO

Long-Tail Instance Segmentation Based on Memory Bank and Confidence Calibration

Xinyue Fan    
Teng Liu    
Hong Bao    
Weiguo Pan    
Tianjiao Liang and Han Li    

Resumen

In the field of computer vision, training a well-performing model on a dataset with a long-tail distribution is a challenging task. To address this challenge, image resampling is usually introduced as a simple and effective solution. However, when performing instance segmentation tasks, there may be multiple classes in one image. Hence, image resampling alone is not enough to obtain a sufficiently balanced distribution at the level of target data volume. In this paper, we propose an improved instance segmentation method for long-tail datasets based on Mask R-CNN. Specifically, an object-centric memory bank is used to establish an object-centric storage strategy that can solve the imbalance problem with respect to categories. In the testing phase, a post-processing calibration is used to adjust each class logit to change the confidence score, which improves the prediction score of tail classes. A discrete cosine transform-based mask is used to obtain high-quality masks, which improves segmentation accuracy. The evaluation of the proposed method on the LVIS dataset demonstrates its effectiveness. The proposed method improves the AP performance of EQL by 2.2%.

 Artículos similares

       
 
Hang Li, Shengjie Zhao and Hao Deng    
The extraction of community-scale green infrastructure (CSGI) poses challenges due to limited training data and the diverse scales of the targets. In this paper, we reannotate a training dataset of CSGI and propose a three-stage transfer learning method ... ver más
Revista: Information

 
Tatsuhito Hasegawa and Daichi Nakano    
Resource management for fisheries plays a pivotal role in fostering a sustainable fisheries industry. In Japan, resource surveys rely on manual measurements by staff, incurring high costs and limitations on the number of feasible measurements. This study... ver más

 
Alvin Lee, Suet-Peng Yong, Witold Pedrycz and Junzo Watada    
Drones play a pivotal role in various industries of Industry 4.0. For achieving the application of drones in a dynamic environment, finding a clear path for their autonomous flight requires more research. This paper addresses the problem of finding a nav... ver más
Revista: Algorithms

 
Shoffan Saifullah and Rafal Drezewski    
Accurate medical image segmentation is paramount for precise diagnosis and treatment in modern healthcare. This research presents a comprehensive study of the efficacy of particle swarm optimization (PSO) combined with histogram equalization (HE) preproc... ver más
Revista: Applied Sciences

 
Hongyu Shao, Sizhe Pan, Yufei Song and Quanfu Li    
In the context of rapid product iteration, design conflicts arise from discrepancies in designers? understanding of user needs, influenced by subjective preferences, behavioural stances, and other factors. This paper proposes a product conceptual design ... ver más
Revista: Applied Sciences