Title: Dynamic concept-aware network for few-shot learning
Abstract: Few-shot learning (FSL) aims to recognize novel classes with extremely limited samples via adapting the prior knowledge learned from base classes. Most of existing methods for feature alignment in FSL consider the correspondence of semantic concepts between support and query images. However, encoding task-specific information for query features has not been sufficiently explored. Therefore, in this paper, we propose a dynamic concept-aware network (DCAN), which efficiently encodes task-specific structural concepts and adaptively dynamic alignment. Concretely, this is achieved by dynamic prototype task awareness (DPTA) and cross-correlation dynamic alignment (CoDA). The DPTA module assigns concept weights to each pixel position feature of support images so that dynamically generate prototypes to encode task-specific information with attention mechanism. The CoDA module first calculates the co-attention maps between image representations, and adaptively learns channel-dependent and spatial-dependent dynamic meta-filters based on inputs. Combining two dynamic modules to obtain final embeddings that generalize well to novel categories. Extensive experiments demonstrate that DCAN outperforms the state-of-the-art methods on four FSL classification benchmarks. Our code is available at https://github.com/zjgans/dcan . • We design a Dynamic Prototype Task Awareness (DPTA) module to encode task-specific information with transferable structural concepts. • We propose a novel feature alignment strategy incorporating decoupled dynamic filter, which is task-adaptive and generalizes well to new scenarios. • Extensive experiments demonstrate that our method outperforms the state-of-the-art methods on four standard FSL benchmarks, and ablation studies verify the effectiveness of our proposed components.
Publication Year: 2022
Publication Date: 2022-12-01
Language: en
Type: article
Indexed In: ['crossref']
Access and Citation
Cited By Count: 6
AI Researcher Chatbot
Get quick answers to your questions about the article from our AI researcher chatbot