Object detection, as of one the most fundamental and challenging problems in computer
vision, has received great attention in recent years. Over the past two decades, we have …

Pre-trained vision-language (VL) models such as CLIP have shown excellent generalization
ability to downstream tasks. However, they are sensitive to the choice of input text prompts …

Most visual recognition studies rely heavily on crowd-labelled data in deep neural networks
(DNNs) training, and they usually train a DNN for each single visual recognition task …

Neural compression is the application of neural networks and other machine learning
methods to data compression. Recent advances in statistical machine learning have opened …

Prompt learning has emerged as an efficient alternative for fine-tuning foundational models,
such as CLIP, for various downstream tasks. Conventionally trained using the task-specific …

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 …

Leveraging the extensive training data from SA-1B, the segment anything model (SAM)
demonstrates remarkable generalization and zero-shot capabilities. However, as a category …

Abstract We present Region-aware Open-vocabulary Vision Transformers (RO-ViT)--a
contrastive image-text pretraining recipe to bridge the gap between image-level pretraining …

Deriving reliable region-word alignment from image-text pairs is critical to learnobject-level
vision-language representations for open-vocabulary object detection. Existing methods …

In the field of visual scene understanding, deep neural networks have made impressive
advancements in various core tasks like segmentation, tracking, and detection. However …