.png){kind=icon}
返回
Memory-Efficient Continual Learning Object Segmentation for Long Videos
.png){kind=icon}
OA
AI
DOI：10.1109/ACCESS.2024.3426542.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Recent state-of-the-art semi-supervised Video Object Segmentation (VOS) methods have shown significant improvements in target object segmentation accuracy when information from preceding frames is used in segmenting the current frame. In particular, such memory-based approaches can help a model to more effectively handle appearance changes (representation drift) or occlusions. Ideally, for maximum performance, Online VOS methods would need all or most of the preceding frames (or their extracted information) to be stored in memory and be used for online learning in later frames. Such a solution is not feasible for long videos, as the required memory size grows without bound, and such methods can fail when memory is limited and a target object experiences repeated representation drifts over time. We propose two novel techniques to reduce the memory requirement of Online VOS methods while improving modeling accuracy and generalization on long videos. Motivated by the success of continual learning techniques in preserving previously-learned knowledge, here we propose Gated-Regularizer Continual Learning (GRCL), which improves the performance of any Online VOS subject to limited memory, and a Reconstruction-based Memory Selection Continual Learning (RMSCL), which empowers Online VOS methods to efficiently benefit from stored information in memory. We also analyze the performance of a hybrid combination of the two proposed methods. Experimental results show that the proposed methods are able to improve the performance of Online VOS models by more than 8%, with improved robustness on long-video datasets while maintaining comparable performance on short-video datasets such as DAVIS16, DAVIS17, and YouTube-VOS18.
Keyword:
Video object segmentation
continual learning
regularization-based solutions
replay-based methods
Video object segmentation
continual learning
regularization-based solutions
replay-based methods
期刊
IF:
3.6
论文数:
9.8W
被引数:
29.4W
机构
引用论文
An adaptive actuator failure compensation scheme for a cooperative manipulator system.png)
Robotica
RoboticaIF0
PREAI
分享收藏Pseudo-rehearsal: Achieving deep reinforcement learning without catastrophic forgetting伪演练: 在没有灾难性遗忘的情况下实现深度强化学习NEUROCOMPUTING
OAAI
NEUROCOMPUTINGIF6.5
OAAI分享收藏
查看更多内容