DeepAI AI Chat
Log In Sign Up

When Video Classification Meets Incremental Classes

by   Hanbin Zhao, et al.

With the rapid development of social media, tremendous videos with new classes are generated daily, which raise an urgent demand for video classification methods that can continuously update new classes while maintaining the knowledge of old videos with limited storage and computing resources. In this paper, we summarize this task as Class-Incremental Video Classification (CIVC) and propose a novel framework to address it. As a subarea of incremental learning tasks, the challenge of catastrophic forgetting is unavoidable in CIVC. To better alleviate it, we utilize some characteristics of videos. First, we decompose the spatio-temporal knowledge before distillation rather than treating it as a whole in the knowledge transfer process; trajectory is also used to refine the decomposition. Second, we propose a dual granularity exemplar selection method to select and store representative video instances of old classes and key-frames inside videos under a tight storage budget. We benchmark our method and previous SOTA class-incremental learning methods on Something-Something V2 and Kinetics datasets, and our method outperforms previous methods significantly.


page 1

page 4

page 5

page 6


Two-Level Residual Distillation based Triple Network for Incremental Object Detection

Modern object detection methods based on convolutional neural network su...

Incremental Classifier Learning Based on PEDCC-Loss and Cosine Distance

The main purpose of incremental learning is to learn new knowledge while...

Learning a Condensed Frame for Memory-Efficient Video Class-Incremental Learning

Recent incremental learning for action recognition usually stores repres...

Maintaining Discrimination and Fairness in Class Incremental Learning

Deep neural networks (DNNs) have been applied in class incremental learn...

Deep Class-Incremental Learning: A Survey

Deep models, e.g., CNNs and Vision Transformers, have achieved impressiv...

Effective Decision Boundary Learning for Class Incremental Learning

Rehearsal approaches in class incremental learning (CIL) suffer from dec...

Learning "O" Helps for Learning More: Handling the Concealed Entity Problem for Class-incremental NER

As the categories of named entities rapidly increase in real-world appli...