IEEE Transactions on Multimedia · 2021 · 114 citations · 30 references
ComputingComputer ScienceComputer VisionMachine LearningVisual AttentionAttention NetworksFeature-based AttentionImage ClassificationObject DetectionObject RecognitionSelective AttentionAttentionFew-shot ClassificationFew-shot Image ClassificationFew-shot LearningFew-shot Object DetectionSpatial Variability
While recent progress has significantly boosted few-shot classification (FSC) performance, few-shot object detection (FSOD) remains challenging for modern learning systems. Existing FSOD systems follow FSC approaches, ignoring critical issues such as spatial variability and uncertain representations, and consequently result in low performance. Observing this, we propose a novel <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Dual-Awareness Attention (DAnA)</b> mechanism that enables networks to adaptively interpret the given support images. DAnA transforms support images into <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">query-position-aware</b> (QPA) features, guiding detection networks precisely by assigning customized support information to each local region of the query. In addition, the proposed DAnA component is flexible and adaptable to multiple existing object detection frameworks. By adopting DAnA, conventional object detection networks, Faster R-CNN and RetinaNet, which are not designed explicitly for few-shot learning, reach state-of-the-art performance in FSOD tasks. In comparison with previous methods, our model significantly increases the performance by 47% (+6.9 AP), showing remarkable ability under various evaluation settings.
30
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
Ross Girshick, Jeff Donahue, Trevor Darrell et al. · 2014 · 31.8K citations
Feature Pyramid Networks for Object Detection
Tsung-Yi Lin, Piotr Dollár, Ross Girshick et al. · 2017 · 28.7K citations
Squeeze-and-Excitation Networks