EUVIMEDEUVIMED entdecken
Crossref

Developing Evolving Adaptability in Biological Intelligence: A Novel Biologically-Inspired Continual Learning Model for Video Saliency Prediction

Dandan Zhu, Kaiwei Zhang, Kun Zhu, Nana Zhang, Xiongkuo Min, Guangtao Zhai, Xiaokang Yang

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2026-04 · 48 (4) · 4257-4274

DOI: 10.1109/tpami.2025.3643517 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2026-04. Verfasst von Dandan Zhu und 6 weiteren Autor:innen. Hauptthemen laut MEDLINE: Video Recording, Image Processing, Computer-Assisted, Deep Learning, Machine Learning. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 61 Literaturangaben. Gefördert von: National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In the era of deep learning, video saliency prediction task still remains major challenge due to the issue of catastrophic forgetting during feature learning. Most prior works commonly employ generative replay strategies to generate pseudo-samples from previous tasks, enabling them to recall the data distribution. However, scaling up generative replay to accommodate class-incremental and task-incremental settings poses challenges, as generated data with low quality can severely deteriorate performance. Additionally, existing advances mainly focus on preserving memory stability to alleviate catastrophic forgetting, but they remain difficult to flexibly adapt to incremental changes in dynamic scenes. To achieve a better balance between memory stability and learning plasticity, we propose a novel biologically-inspired continual learning (BICL) model tailored to effectively predict human attention in dynamic scenes while mitigate catastrophic forgetting. In particular, inspired by the function of the hippocampus in the human neural system, we elaborately design a visual saliency memory bank module to explicitly store and retrieve representative features from previous tasks. Furthermore, drawing inspiration from the Drosophila $\gamma$γMB system, we propose an active forgetting strategy equipped with multiple parallel adaptive learner modules, which can appropriately attenuate old memories in parameter distribution to enhance learning plasticity to adapt to new tasks, and accordingly to ensure compatibility among multiple learners. Notably, without compromising the performance of old tasks, our proposed model can achieve a better trade-off between memory stability and learning plasticity. Through extensive experiments on several benchmark datasets, our model not only enhances performance in task-incremental settings, but also potentially provides deep insights into neurological adaptive mechanisms.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Video RecordingImage Processing, Computer-AssistedDeep LearningMachine LearningHumansAnimalsAttentionAlgorithms

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Zhu, D., Zhang, K., Zhu, K., Zhang, N., Min, X., Zhai, G., & Yang, X. (2026). Developing Evolving Adaptability in Biological Intelligence: A Novel Biologically-Inspired Continual Learning Model for Video Saliency Prediction. IEEE Transactions on Pattern Analysis and Machine Intelligence, 48(4), 4257-4274. https://doi.org/10.1109/tpami.2025.3643517

Vancouver

Zhu D, Zhang K, Zhu K, Zhang N, Min X, Zhai G, et al. Developing Evolving Adaptability in Biological Intelligence: A Novel Biologically-Inspired Continual Learning Model for Video Saliency Prediction. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2026;48(4):4257-4274. doi:10.1109/tpami.2025.3643517

BibTeX
@article{Zhu2026,
  author = {Zhu, Dandan and Zhang, Kaiwei and Zhu, Kun and Zhang, Nana and Min, Xiongkuo and Zhai, Guangtao and Yang, Xiaokang},
  title = {Developing Evolving Adaptability in Biological Intelligence: A Novel Biologically-Inspired Continual Learning Model for Video Saliency Prediction},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2026},
  volume = {48},
  number = {4},
  pages = {4257--4274},
  doi = {10.1109/tpami.2025.3643517}
}
Kostenlos starten →