Annealing-based label-transfer learning for open world object detection

Y Ma, H Li, Z Zhang, J Guo, S Zhang… - Proceedings of the …, 2023 - openaccess.thecvf.com
Open world object detection (OWOD) has attracted extensive attention due to its
practicability in the real world. Previous OWOD works manually designed unknown-discover …

Activate and reject: towards safe domain generalization under category shift

C Chen, L Tang, L Tao, HY Zhou… - Proceedings of the …, 2023 - openaccess.thecvf.com
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 …

Deep Feature Deblurring Diffusion for Detecting Out-of-Distribution Objects

A Wu, D Chen, C Deng - Proceedings of the IEEE/CVF …, 2023 - openaccess.thecvf.com
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 …

Contrastive conditional latent diffusion for audio-visual segmentation

Y Mao, J Zhang, M Xiang, Y Lv, Y Zhong… - arXiv preprint arXiv …, 2023 - arxiv.org
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 …

Learn to categorize or categorize to learn? self-coding for generalized category discovery

S Rastegar, H Doughty… - Advances in Neural …, 2024 - proceedings.neurips.cc
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 …

Tunable Hybrid Proposal Networks for the Open World

M Inkawhich, N Inkawhich, H Li… - Proceedings of the …, 2024 - openaccess.thecvf.com
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 …

Novel Scenes & Classes: Towards Adaptive Open-set Object Detection

W Li, X Guo, Y Yuan - Proceedings of the IEEE/CVF …, 2023 - openaccess.thecvf.com
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 …

TIB: Detecting unknown objects via two-stream information bottleneck

A Wu, C Deng - IEEE Transactions on Pattern Analysis and …, 2023 - ieeexplore.ieee.org
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 …

Exploring Orthogonality in Open World Object Detection

Z Sun, J Li, Y Mu - … of the IEEE/CVF Conference on …, 2024 - openaccess.thecvf.com
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 …

Open-set object detection using classification-free object proposal and instance-level contrastive learning

Z Zhou, Y Yang, Y Wang… - IEEE Robotics and …, 2023 - ieeexplore.ieee.org
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 …