Open world object detection (OWOD) has attracted extensive attention due to its
practicability in the real world. Previous OWOD works manually designed unknown-discover …

Albeit the notable performance on in-domain test points, it is non-trivial for deep neural
networks to attain satisfactory accuracy when deploying in the open world, where novel …

To promote the safe application of detectors, a task of unsupervised out-of-distribution object
detection (OOD-OD) is recently proposed, whose goal is to detect unseen OOD objects …

We propose a latent diffusion model with contrastive learning for audio-visual segmentation
(AVS) to extensively explore the contribution of audio. We interpret AVS as a conditional …

In the quest for unveiling novel categories at test time, we confront the inherent limitations of
traditional supervised recognition models that are restricted by a predefined category set …

Current state-of-the-art object proposal networks are trained with a closed-world
assumption, meaning they learn to only detect objects of the training classes. These models …

Abstract Domain Adaptive Object Detection (DAOD) transfers an object detector to a novel
domain free of labels. However, in the real world, besides encountering novel scenes, novel …

Detecting diverse objects, including ones never-seen-before during training, is critical for the
safe application of object detectors. To this end, a task of unsupervised out-of-distribution …

Open world object detection aims to identify objects of unseen categories and incrementally
recognize them once their annotations are provided. In distinction to the traditional paradigm …

Detecting both known and unknown objects is a fundamental skill for robot manipulation in
unstructured environments. Open-set object detection (OSOD) is a promising direction to …