Few-Shot Class-Incremental Audio Classification Using Dynamically Expanded Classifier With Self-Attention Modified Prototypes

Li, Yanxiong; Cao, Wenchang; Xie, Wei; Li, Jialong; Benetos, Emmanouil

doi:10.1109/tmm.2023.3280011

Cited by 3 publications

(1 citation statement)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Replaybased algorithms [34], [35], [36], [37], [38], [39], [40] learn a new task by merging the stored or generated old samples into the current training process. [41], [42], [43], [44] dynamically assign parameters for previous tasks to guarantee the stability of performance. Regularization-based strategies aim at constraining the model as it changes, either directly on network weights [6], [45], [46], [47], output probabilities [15], [38], [48], or intermediary features [49].…”

Section: Related Workmentioning

confidence: 99%

Federated Incremental Semantic Segmentation

Dong,

Zhang,

Cong

et al. 2023

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

Incremental semantic segmentation aims to continually learn the segmentation of new coming classes without accessing the training data of previously learned classes. However, most current methods fail to address catastrophic forgetting and background shift since they 1) treat all previous classes equally without considering different forgetting paces caused by imbalanced gradient back-propagation; 2) lack strong semantic guidance between classes. To tackle the above challenges, in this paper, we propose a Gradient-Semantic Compensation (GSC) model, which surmounts incremental semantic segmentation from both gradient and semantic perspectives. Specifically, to address catastrophic forgetting from the gradient aspect, we develop a step-aware gradient compensation that can balance forgetting paces of previously seen classes via re-weighting gradient backpropagation. Meanwhile, we propose a soft-sharp semantic relation distillation to distill consistent inter-class semantic relations via soft labels for alleviating catastrophic forgetting from the semantic aspect. In addition, we develop a prototypical pseudo re-labeling that provides strong semantic guidance to mitigate background shift. It produces high-quality pseudo labels for old classes in the background by measuring distances between pixels and class-wise prototypes. Extensive experiments on three public datasets, i.e., Pascal VOC 2012, ADE20K, and Cityscapes, demonstrate the effectiveness of our proposed GSC model.

show abstract