Kernelized Few-Shot Object Detection With Efficient Integral Aggregation
We design a Kernelized Few-shot Object Detector by leveraging kernelized matrices computed over multiple proposal regions, which yield expressive non-linear representations whose model complexity is learned on the fly. Our pipeline contains several modules. An Encoding Network encodes support and query images. Our Kernelized Autocorrelation unit forms the linear, polynomial and RBF kernelized representations from features extracted within support regions of support images. These features are then cross-correlated against features of a query image to obtain attention weights, and generate query proposal regions via an Attention Region Proposal Net. As the query proposal regions are many, each described by the linear, polynomial and RBF kernelized matrices, their formation is costly but that cost is reduced by our proposed Integral Region-of-Interest Aggregation unit. Finally, the Multi-head Relation Net combines all kernelized (second-order) representations with the first-order feature maps to learn support-query class relations and locations. We outperform the state of the art on novel classes by 3.8%, 5.4% and 5.7% mAP on PASCAL VOC 2007, FSOD, and COCO.
Code (0)
등록된 구현이 없습니다.
Tasks
Few-Shot Object DetectionObjectobject-detectionObject DetectionRegion ProposalSimilar Papers 제목 키워드 기반
Booster-SHOT: Boosting Stacked Homography Transformations for Multiview Pedestrian Detection with Attention
Improving multi-view aggregation is integral for multi-view pedestrian detection, which aims to obtain a bird's-eye-view pedestrian occupancy map from images captured through a set of calibrated cameras. Inspired by the …
Multiview DetectionPedestrian DetectionImproving Network Anomaly Detection via Choquet-Integral-Based Feature Aggregation
This work investigates a generalized Choquet-integral-based feature aggregation framework to improve anomaly detection in high-dimensional network traffic data. The approach combines adaptive weighting with incremental f…
Intrusion DetectionAnomaly DetectionDense Relation Distillation with Context-aware Aggregation for Few-Shot Object Detection
Conventional deep learning based methods for object detection require a large amount of bounding box annotations for training, which is expensive to obtain such high quality annotated data. Few-shot object detection, whi…
Few-Shot Object DetectionMeta-LearningObjectobject-detection+2Single Shot Video Object Detector
Single shot detectors that are potentially faster and simpler than two-stage detectors tend to be more applicable to object detection in videos. Nevertheless, the extension of such object detectors from image to video is…
GPUObjectobject-detectionObject Detection+1A Novel Unified Architecture for Low-Shot Counting by Detection and Segmentation
Low-shot object counters estimate the number of objects in an image using few or no annotated exemplars. Objects are localized by matching them to prototypes, which are constructed by unsupervised image-wide object appea…
Exemplar-Free CountingFew-shot Object Counting and DetectionObjectObject Counting+3