Simple Training Strategies and Model Scaling for Object Detection
The speed-accuracy Pareto curve of object detection systems have advanced through a combination of better model architectures, training and inference methods. In this paper, we methodically evaluate a variety of these techniques to understand where most of the improvements in modern detection systems come from. We benchmark these improvements on the vanilla ResNet-FPN backbone with RetinaNet and RCNN detectors. The vanilla detectors are improved by 7.7% in accuracy while being 30% faster in speed. We further provide simple scaling strategies to generate family of models that form two Pareto curves, named RetinaNet-RS and Cascade RCNN-RS. These simple rescaled detectors explore the speed-accuracy trade-off between the one-stage RetinaNet detectors and two-stage RCNN detectors. Our largest Cascade RCNN-RS models achieve 52.9% AP with a ResNet152-FPN backbone and 53.6% with a SpineNet143L backbone. Finally, we show the ResNet architecture, with three minor architectural changes, outperforms EfficientNet as the backbone for object detection and instance segmentation systems.
Code (1)
Tasks
Instance SegmentationObjectobject-detectionObject DetectionSemantic SegmentationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Simple Open-Vocabulary Object Detection with Vision Transformers
Combining simple architectures with large-scale pre-training has led to massive improvements in image classification. For object detection, pre-training and scaling approaches are less well established, especially in the…
Described Object Detectionimage-classificationImage ClassificationObject+4HD-OOD3D: Supervised and Unsupervised Out-of-Distribution object detection in LiDAR data
Autonomous systems rely on accurate 3D object detection from LiDAR data, yet most detectors are limited to a predefined set of known classes, making them vulnerable to unexpected out-of-distribution (OOD) objects. In thi…
3D Object DetectionObjectobject-detectionObject Detection+1Revisiting 3D ResNets for Video Recognition
A recent work from Bello shows that training and scaling strategies may be more significant than model architectures for visual recognition. This short note studies effective training and scaling strategies for video rec…
Action ClassificationContrastive LearningVideo RecognitionRevisiting ResNets: Improved Training and Scaling Strategies
Novel computer vision architectures monopolize the spotlight, but the impact of the model architecture is often conflated with simultaneous changes to training methodology and scaling strategies. Our work revisits the ca…
Action ClassificationDocument Image ClassificationImage ClassificationSemantic Object Interaction Classification+1An Investigation on Hardware-Aware Vision Transformer Scaling
Vision Transformer (ViT) has demonstrated promising performance in various computer vision tasks, and recently attracted a lot of research attention. Many recent works have focused on proposing new architectures to impro…
GPUimage-classificationImage Classificationobject-detection+2