Object localization in general environments is a fundamental part of vision
systems. While dominating on the COCO benchmark, recent Transformer-based
detection methods are not competitive in diverse domains. Moreover, these
methods still struggle to very accurately estimate the object bounding boxes in
complex environments.
We introduce Cascade-DETR for high-quality universal object detection. We
jointly tackle the generalization to diverse domains and localization accuracy
by proposing the Cascade Attention layer, which explicitly integrates
object-centric information into the detection decoder by limiting the attention
to the previous box prediction. To further enhance accuracy, we also revisit
the scoring of queries. Instead of relying on classification scores, we predict
the expected IoU of the query, leading to substantially more well-calibrated
confidences. Lastly, we introduce a universal object detection benchmark,
UDB10, that contains 10 datasets from diverse domains. While also advancing the
state-of-the-art on COCO, Cascade-DETR substantially improves DETR-based
detectors on all datasets in UDB10, even by over 10 mAP in some cases. The
improvements under stringent quality requirements are even more pronounced. Our
code and models will be released at this https URL

我们引入了 Cascade-DETR 用于高质量的通用目标检测，通过提出级联注意力层来共同解决对多样领域的泛化和定位准确性问题，通过限制关注先前的目标框预测来显式地将对象中心信息集成到检测解码器中。为了进一步提高准确性，我们重新审视了查询的评分，不依赖于分类分数，而是预测查询的预期 IoU，从而显著提高了置信度的校准性，最后，我们引入了一个包含来自多个领域的 10 个数据集的通用目标检测基准，UDB10，在 COCO 上也取得了最新的进展，Cascade-DETR 在 UDB10 的所有数据集上都对基于 DETR 的检测器有了显著的改进，有些甚至超过 10 个 mAP，严格质量要求下的改进效果更加显著。

级联 DETR：深入高质量的通用目标检测

Cascade-DETR: Delving into High-Quality Universal Object Detection

In this paper, we formally address universal object detection, which aims to
detect every scene and predict every category. The dependence on human
annotations, the limited visual information, and the novel categories in the
open world severely restrict the universality of traditional detectors. We
propose UniDetector, a universal object detector that has the ability to
recognize enormous categories in the open world. The critical points for the
universality of UniDetector are: 1) it leverages images of multiple sources and
heterogeneous label spaces for training through the alignment of image and text
spaces, which guarantees sufficient information for universal representations.
2) it generalizes to the open world easily while keeping the balance between
seen and unseen classes, thanks to abundant information from both vision and
language modalities. 3) it further promotes the generalization ability to novel
categories through our proposed decoupling training manner and probability
calibration. These contributions allow UniDetector to detect over 7k
categories, the largest measurable category size so far, with only about 500
classes participating in training. Our UniDetector behaves the strong zero-shot
generalization ability on large-vocabulary datasets like LVIS, ImageNetBoxes,
and VisualGenome - it surpasses the traditional supervised baselines by more
than 4\% on average without seeing any corresponding images. On 13 public
detection datasets with various scenes, UniDetector also achieves
state-of-the-art performance with only a 3\% amount of training data.

本文提出 UniDetector，一种通用的目标检测器，克服了传统检测器中人工注释、视觉信息和新类别的限制，并在 LVIS、ImageNetBoxes 和 VisualGenome 等大型数据集上表现出强大的零样本泛化能力，探讨了其对于开放世界、大词汇量数据集、高零样本泛化能力等方面的实验结果。