Proposal-Contrastive Pretraining for Object Detection from Fewer Data
The use of pretrained deep neural networks represents an attractive way to achieve strong results with few data available. When specialized in dense problems such as object detection, learning local rather than global information in images has proven to be more efficient. However, for unsupervised pretraining, the popular contrastive learning requires a large batch size and, therefore, a lot of resources. To address this problem, we are interested in transformer-based object detectors that have recently gained traction in the community with good performance and with the particularity of generating many diverse object proposals. In this work, we present Proposal Selection Contrast (ProSeCo), a novel unsupervised overall pretraining approach that leverages this property. ProSeCo uses the large number of object proposals generated by the detector for contrastive learning, which allows the use of a smaller batch size, combined with object-level features to learn local information in the images. To improve the effectiveness of the contrastive loss, we introduce the object location information in the selection of positive examples to take into account multiple overlapping object proposals. When reusing pretrained backbone, we advocate for consistency in learning local information between the backbone and the detection head. We show that our method outperforms state of the art in unsupervised pretraining for object detection on standard and novel benchmarks in learning with fewer data.
Code (0)
등록된 구현이 없습니다.
Tasks
Contrastive LearningObjectobject-detectionObject DetectionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Aligning Pretraining for Detection via Object-Level Contrastive Learning
Image-level contrastive representation learning has proven to be highly effective as a generic model for transfer learning. Such generality for transfer learning, however, sacrifices specificity if we are interested in a…
Contrastive LearningObjectobject-detectionObject Detection+4Region-Aware Pretraining for Open-Vocabulary Object Detection with Vision Transformers
We present Region-aware Open-vocabulary Vision Transformers (RO-ViT) - a contrastive image-text pretraining recipe to bridge the gap between image-level pretraining and open-vocabulary object detection. At the pretrainin…
Contrastive LearningImage-text Retrievalobject-detectionObject Detection+5Aligned 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+2FSCE: Few-Shot Object Detection via Contrastive Proposal Encoding
Emerging interests have been brought to recognize previously unseen objects given very few training examples, known as few-shot object detection (FSOD). Recent researches demonstrate that good feature embedding is the ke…
Contrastive LearningCross-Domain Few-Shot Object DetectionFew-Shot LearningFew-Shot Object Detection+4Efficient Visual Pretraining with Contrastive Detection
Self-supervised pretraining has been shown to yield powerful representations for transfer learning. These performance gains come at a large computational cost however, with state-of-the-art methods requiring an order of …
Semantic SegmentationTransfer Learning