.png){kind=icon}
返回
Curriculum learning with class-label composition for weakly supervised semantic segmentation
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patrec.2024.12.016.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Weakly Supervised Semantic Segmentation (WSSS) aims to build a segmentation network using only weak labels. In WSSS training using image-level labels, a classifier is trained with multi-labeled images, as the task assumes the presence of multiple classes. The classifier plays a crucial role due to its impact on the quality of the derived pseudo-masks. However, training the classifier with the multi-labeled images presents two following challenges: (1) The presence of frequently co-occurring classes (e.g. chair and dining table) introduces a spurious correlation, making it difficult for the classifier to determine the location of each class. (2) Such multi-labeled datasets often exhibit imbalanced class distributions, which can create challenges during the training process. To tackle these issues, we propose a curriculum learning strategy based on the length and frequency of class-label composition. This strategy gradually reduces the influence of images with spurious correlation between classes and ensures that classes with fewer images appear more frequently during training. Our extensive experiments demonstrate that, when applied to eight WSSS methods, our curriculum strategy consistently enhances the quality of the pseudo-labels and segmentation performances, and also reduces the required computational resources for training.
Keyword:
Deep learning
Weakly-supervised learning
Computer vision
Semantic segmentation
Curriculum learning
期刊
IF:
3.3
论文数:
8.0K
被引数:
1.6W
机构
引用论文
Wider or Deeper: Revisiting the ResNet Model for Visual Recognition更广泛或更深入: 重新审视视觉识别的ResNet模型.png)
PATTERN RECOGNITION
OAAI
PATTERN RECOGNITIONIF7.6
OAAI分享收藏A systematic study of the class imbalance problem in convolutional neural networks卷积神经网络中类不平衡问题的系统研究NEURAL NETWORKSOAAI
NEURAL NETWORKSIF6.3
OAAI分享收藏分享收藏Elastic band structures of two-dimensional solid phononic crystal with negative Poisson's ratios负泊松比二维固体声子晶体的弹性带结构
PREAI
分享收藏Age and Date for Early Arrival of the Acheulian in Europe (Barranc de la Boella, la Canonja, Spain)PLoS ONEOAAI
PLoS ONEIF0
OAAI分享收藏
查看更多内容