MaxpoolNMS: Getting Rid of NMS Bottlenecks in Two-Stage Object Detectors
Modern convolutional object detectors have improved the detection accuracy significantly, which in turn inspired the development of dedicated hardware accelerators to achieve real-time performance by exploiting inherent parallelism in the algorithm. Non-maximum suppression (NMS) is an indispensable operation in object detection. In stark contrast to most operations, the commonly-adopted GreedyNMS algorithm does not foster parallelism, which can be a major performance bottleneck. In this paper, we introduce MaxpoolNMS, a parallelizable alternative to the NMS algorithm, which is based on max-pooling classification score maps. By employing a novel multi-scale multi-channel max-pooling strategy, our method is 20x faster than GreedyNMS while simultaneously achieves comparable accuracy, when quantified across various benchmarking datasets, i.e., MS COCO, KITTI and PASCAL VOC. Furthermore, our method is better suited for hardware-based acceleration than GreedyNMS.
Code (0)
등록된 구현이 없습니다.
Tasks
BenchmarkingGeneral ClassificationObjectobject-detectionObject DetectionVocal Bursts Valence PredictionSimilar Papers 제목 키워드 기반
PSRR-MaxpoolNMS: Pyramid Shifted MaxpoolNMS with Relationship Recovery
Non-maximum Suppression (NMS) is an essential postprocessing step in modern convolutional neural networks for object detection. Unlike convolutions which are inherently parallel, the de-facto standard for NMS, namely Gre…
object-detectionObject DetectionEfficient One-stage Video Object Detection by Exploiting Temporal Consistency
Recently, one-stage detectors have achieved competitive accuracy and faster speed compared with traditional two-stage detectors on image data. However, in the field of video object detection (VOD), most existing VOD meth…
object-detectionObject DetectionVideo Object DetectionTeach YOLO to Remember: A Self-Distillation Approach for Continual Object Detection
Real-time object detectors like YOLO achieve exceptional performance when trained on large datasets for multiple epochs. However, in real-world scenarios where data arrives incrementally, neural networks suffer from cata…
class-incremental learningClass Incremental LearningContinual LearningIncremental Learning+3Learning Task-Aware Language-Image Representation for Class-Incremental Object Detection
Class-incremental object detection (CIOD) is a real-world desired capability, requiring an object detector to continuously adapt to new tasks without forgetting learned ones, with the main challenge being catastrophic fo…
Class-Incremental Object Detectionobject-detectionObject DetectionYOLO-IOD: Towards Real Time Incremental Object Detection
Current methods for incremental object detection (IOD) primarily rely on Faster R-CNN or DETR series detectors; however, these approaches do not accommodate the real-time YOLO detection frameworks. In this paper, we firs…
parameter-efficient fine-tuningKnowledge DistillationIncremental LearningObject Detection