Deformable Audio Transformer for Audio Event Detection
원문 초록
Transformers have achieved promising results on a variety of tasks. However, the quadratic complexity in self-attention computation has limited the applications, especially in low-resource settings and mobile or edge devices. Existing works have proposed to exploit hand-crafted attention patterns to reduce computation complexity. However, such hand-crafted patterns are data-agnostic and may not be optimal. Hence, it is likely that relevant keys or values are being reduced, while less important ones are still preserved. Based on this key insight, we propose a novel deformable audio Transformer for audio recognition, named DATAR, where a deformable attention equipping with a pyramid transformer backbone is constructed and learnable. Such an architecture has been proven effective in prediction tasks,~\textit{e.g.}, event classification. Moreover, we identify that the deformable attention map computation may over-simplify the input feature, which can be further enhanced. Hence, we introduce a learnable input adaptor to alleviate this issue, and DATAR achieves state-of-the-art performance.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Hybrid Disagreement-Diversity Active Learning for Bioacoustic Sound Event Detection
CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-training
Multimodal Event Detection: Current Approaches and Defining the New Playground through LLMs and VLMs
Temporal Attention Pooling for Frequency Dynamic Convolution in Sound Event Detection
F$^3$Set: Towards Analyzing Fast, Frequent, and Fine-grained Events from Videos
Explainable AI Components for Narrative Map Extraction
토론
이 논문과 연결된 포럼 글이 아직 없습니다.