Label-Free Synthetic Pretraining of Object Detectors
We propose a new approach, Synthetic Optimized Layout with Instance Detection (SOLID), to pretrain object detectors with synthetic images. Our "SOLID" approach consists of two main components: (1) generating synthetic images using a collection of unlabelled 3D models with optimized scene arrangement; (2) pretraining an object detector on "instance detection" task - given a query image depicting an object, detecting all instances of the exact same object in a target image. Our approach does not need any semantic labels for pretraining and allows the use of arbitrary, diverse 3D models. Experiments on COCO show that with optimized data generation and a proper pretraining task, synthetic data can be highly effective data for pretraining object detectors. In particular, pretraining on rendered images achieves performance competitive with pretraining on real images while using significantly less computing resources. Code is available at https://github.com/princeton-vl/SOLID.
Code (1)
Tasks
ObjectSimilar Papers 제목 키워드 기반
On Pre-Trained Image Features and Synthetic Images for Deep Learning
Deep Learning methods usually require huge amounts of training data to perform at their full potential, and often require expensive manual labeling. Using synthetic images is therefore very attractive to train object det…
ObjectObject RecognitionBridging Synthetic and Real Worlds for Pre-training Scene Text Detectors
Existing scene text detection methods typically rely on extensive real data for training. Due to the lack of annotated real images, recent works have attempted to exploit large-scale labeled synthetic data (LSD) for pre-…
Scene Text DetectionText DetectionAligned Unsupervised Pretraining of Object Detectors with Self-training
The unsupervised pretraining of object detectors has recently become a key component of object detector training, as it leads to improved performance and faster convergence during the supervised fine-tuning stage. Existi…
Few-Shot Object DetectionObjectobject-detectionObject Detection+2Towards Few-Annotation Learning in Computer Vision: Application to Image Classification and Object Detection tasks
In this thesis, we develop theoretical, algorithmic and experimental contributions for Machine Learning with limited labels, and more specifically for the tasks of Image Classification and Object Detection in Computer Vi…
Contrastive Learningimage-classificationImage ClassificationMeta-Learning+4Self-Supervised YOLO: Leveraging Contrastive Learning for Label-Efficient Object Detection
One-stage object detectors such as the YOLO family achieve state-of-the-art performance in real-time vision applications but remain heavily reliant on large-scale labeled datasets for training. In this work, we present a…
Self-Supervised LearningContrastive LearningObject Detection