Slightly Shift New Classes to Remember Old Classes for Video Class-Incremental Learning
Recent video class-incremental learning usually excessively pursues the accuracy of the newly seen classes and relies on memory sets to mitigate catastrophic forgetting of the old classes. However, limited storage only allows storing a few representative videos. So we propose SNRO, which slightly shifts the features of new classes to remember old classes. Specifically, SNRO contains Examples Sparse(ES) and Early Break(EB). ES decimates at a lower sample rate to build memory sets and uses interpolation to align those sparse frames in the future. By this, SNRO stores more examples under the same memory consumption and forces the model to focus on low-semantic features which are harder to be forgotten. EB terminates the training at a small epoch, preventing the model from overstretching into the high-semantic space of the current task. Experiments on UCF101, HMDB51, and UESTC-MMEA-CL datasets show that SNRO performs better than other approaches while consuming the same memory consumption.
Code (0)
등록된 구현이 없습니다.
Tasks
class-incremental learningClass Incremental LearningIncremental LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Incremental Learning for Semantic Segmentation of Large-Scale Remote Sensing Data
In spite of remarkable success of the convolutional neural networks on semantic segmentation, they suffer from catastrophic forgetting: a significant performance drop for the already learned classes when new classes are …
Incremental LearningSemantic SegmentationMultivariate Prototype Representation for Domain-Generalized Incremental Learning
Deep learning models suffer from catastrophic forgetting when being fine-tuned with samples of new classes. This issue becomes even more pronounced when faced with the domain shift between training and testing data. In t…
class-incremental learningClass Incremental LearningIncremental LearningKnowledge DistillationBreaking the Model Forgetting Cycle in Long-Incremental 3D Object Detection
Incremental 3D object detection requires a detector to learn novel object classes while remembering previously learned ones over sequentially arriving data. Previous methods, primarily based on pseudo-labeling, perform r…
3D Object DetectionClaRe: Practical Class Incremental Learning By Remembering Previous Class Representations
This paper presents a practical and simple yet efficient method to effectively deal with the catastrophic forgetting for Class Incremental Learning (CIL) tasks. CIL tends to learn new concepts perfectly, but not at the e…
class-incremental learningClass Incremental LearningIncremental LearningDeducing neighborhoods of classes from a fitted model
In todays world the request for very complex models for huge data sets is rising steadily. The problem with these models is that by raising the complexity of the models, it gets much harder to interpret them. The growing…
BIG-bench Machine LearningInterpretable Machine Learningmodel