Liang Wan

ExDet achieves state-of-the-art performance in open-domain open-vocabulary detection while significantly reducing training costs through innovative cross-modal techniques.

Real-time object detectors can achieve cross-domain generalization without any extra inference overhead by leveraging collaborative evidence modeling during training.

Object detection gets a flexible upgrade: now you can specify objects with text *and* images, opening the door to more intuitive and practical real-world applications.

Freezing your visual encoder and carefully nudging the text embeddings lets you continually teach an object detector new tricks without catastrophic forgetting.

Even when crucial medical data is missing, a new framework can still achieve state-of-the-art diagnostic accuracy by intelligently synthesizing the missing modalities and aligning them with available data.