This paper presents DetCLIPv2, an efficient and scalable training framework that
incorporates large-scale image-text pairs to achieve open-vocabulary object detection …

Network pruning is widely used for reducing the heavy inference cost of deep models in low-
resource settings. A typical pruning algorithm is a three-stage pipeline, ie, training (a large …

We propose a novel scene graph generation model called Graph R-CNN, that is both
effective and efficient at detecting objects and their relations in images. Our model contains …

We introduce a novel framework for image captioning that can produce natural language
explicitly grounded in entities that object detectors find in the image. Our approach …

Cross-domain object detection is challenging, because object detection model is often
vulnerable to data variance, especially to the considerable domain shift between two …

Abstract Knowledge distillation has shown great success in classification, however, it is still
challenging for detection. In a typical image for detection, representations from different …

Despite increasing efforts on universal representations for visual recognition, few have
addressed object detection. In this paper, we develop an effective and efficient universal …

We address a learning-to-normalize problem by proposing Switchable Normalization (SN),
which learns to select different normalizers for different normalization layers of a deep neural …

Abstract We introduce Probabilistic Object Detection, the task of detecting objects in images
and accurately quantifying the spatial and semantic uncertainties of the detections. Given …

Can we improve detection in the thermal domain by borrowing features from rich domains
like visual RGB? In this paper, we propose a pseudo-multimodal object detector trained on …