2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2019
DOI: 10.1109/cvpr.2019.00092
|View full text |Cite
|
Sign up to set email alerts
|

Learning a Unified Classifier Incrementally via Rebalancing

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

5
1,091
0

Year Published

2020
2020
2020
2020

Publication Types

Select...
5
2

Relationship

0
7

Authors

Journals

citations
Cited by 875 publications
(1,096 citation statements)
references
References 18 publications
5
1,091
0
Order By: Relevance
“…Javed et al [ 80 ] proposed a dynamic threshold shift method to improve the limitations of the deviation in a general knowledge distillation model. Hou et al [ 81 ] integrated cosine normalization, less-forget constraint and inter-class separation into a distillation model to mitigate the negative influences of the imbalance between new and old data.…”
Section: Methods Descriptionmentioning
confidence: 99%
“…Javed et al [ 80 ] proposed a dynamic threshold shift method to improve the limitations of the deviation in a general knowledge distillation model. Hou et al [ 81 ] integrated cosine normalization, less-forget constraint and inter-class separation into a distillation model to mitigate the negative influences of the imbalance between new and old data.…”
Section: Methods Descriptionmentioning
confidence: 99%
“…And the exemplar selection method in [15] needs to be improved. As shown in [16], the imbalance between old and new classes is a crucial reason for catastrophic forgetting, cosine normalization, and inter-class separation are used to address the problem. In [17], a linear model is added after the FC layer to alleviate the impact of class imbalance.…”
Section: B Incremental Learning With Deep Learningmentioning
confidence: 99%
“…The important network parameters are more robust in [5]- [8], and these works can be used for reference. But the main drawback of these methods is that they cannot be kept well in a long sequence of classes or tasks [16]. Based on the considerations above, memory-based methods, and model-based methods are combined in our work, and MAS is adopted for representation learning and classification.…”
Section: B Incremental Learning With Deep Learningmentioning
confidence: 99%
See 2 more Smart Citations