Accurate Few-Shot Object Detection With Support-Query Mutual Guidance and Hybrid Loss
Most object detection methods require huge amounts of annotated data and can detect only the categories that appear in the training set. However, in reality acquiring massive annotated training data is both expensive and time-consuming. In this paper, we propose a novel two-stage detector for accurate few-shot object detection. In the first stage, we employ a support-query mutual guidance mechanism to generate more support-relevant proposals. Concretely, on the one hand, a query-guided support weighting module is developed for aggregating different supports to generate the support feature. On the other hand, a support-guided query enhancement module is designed by dynamic kernels. In the second stage, we score and filter proposals via multi-level feature comparison between each proposal and the aggregated support feature based on a distance metric learnt by an effective hybrid loss, which makes the embedding space of distance metric more discriminative. Extensive experiments on benchmark datasets show that our method substantially outperforms the existing methods and lifts the SOTA of FSOD task to a higher level.
Code (0)
등록된 구현이 없습니다.
Tasks
Few-Shot Object Detectionobject-detectionObject DetectionSimilar Papers 제목 키워드 기반
Dynamic Prototype Convolution Network for Few-Shot Semantic Segmentation
The key challenge for few-shot semantic segmentation (FSS) is how to tailor a desirable interaction among support and query features and/or their prototypes, under the episodic training scenario. Most existing FSS method…
Few-Shot Semantic SegmentationSemantic SegmentationFew-Shot Object Detection by Attending to Per-Sample-Prototype
Few-shot object detection aims to detect instances of specific categories in a query image with only a handful of support samples. Although this takes less effort than obtaining enough annotated images for supervised obj…
Few-Shot Object DetectionMeta-LearningObjectobject-detection+1Hierarchical Attention Network for Few-Shot Object Detection via Meta-Contrastive Learning
Few-shot object detection (FSOD) aims to classify and detect few images of novel categories. Existing meta-learning methods insufficiently exploit features between support and query images owing to structural limitations…
Contrastive LearningFew-Shot LearningFew-Shot Object DetectionMeta-Learning+2Dual-Awareness Attention for Few-Shot Object Detection
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, ig…
Few-Shot LearningFew-Shot Object DetectionObjectobject-detection+1Task-Disruptive Background Suppression for Few-Shot Segmentation
Few-shot segmentation aims to accurately segment novel target objects within query images using only a limited number of annotated support images. The recent works exploit support background as well as its foreground to …