DETR-based object detectors have achieved remarkable performance but are
sample-inefficient and exhibit slow convergence. Unsupervised pretraining has
been found to be helpful to alleviate these impediments, allowing training with
large amounts of unlabeled data to improve the detector's performance. However,
existing methods have their own limitations, like keeping the detector's
backbone frozen in order to avoid performance degradation and utilizing
pretraining objectives misaligned with the downstream task. To overcome these
limitations, we propose a simple pretraining framework for DETR-based detectors
that consists of three simple yet key ingredients: (i) richer, semantics-based
initial proposals derived from high-level feature maps, (ii) discriminative
training using object pseudo-labels produced via clustering, (iii)
self-training to take advantage of the improved object proposals learned by the
detector. We report two main findings: (1) Our pretraining outperforms prior
DETR pretraining works on both the full and low data regimes by significant
margins. (2) We show we can pretrain DETR from scratch (including the backbone)
directly on complex image datasets like COCO, paving the path for unsupervised
representation learning directly using DETR.

使用 DETR 为基础的目标检测器，通过无监督预训练和利用大量未标记数据来提高检测器的性能，采用更丰富、基于语义的初始提议、基于聚类的物体伪标签的判别性训练以及自我训练等三个关键因素，显著提升了 DETR 在完整和低数据情况下的性能，并且证明能够在复杂图像数据集上从头开始预训练，直接实现无监督表示学习。