3.2k citations · 5.9k across the 33 of their papers we have counts for
34 papers
4D Panoptic Scene Graph Generation
Jingkang Yang, Jun Cen, Wenxuan Peng +6
We are living in a three-dimensional space while moving forward through a fourth dimension: time. To allow artificial intelligence to develop a comprehensive understanding of such…
Panoptic Video Scene Graph Generation
Jingkang Yang, Wenxuan Peng, Xiangtai Li +8
Towards building comprehensive real-world visual perception systems, we propose and study a new problem called panoptic scene graph generation (PVSG). PVSG relates to the existing…
Octopus: Embodied Vision-Language Programmer from Environmental Feedback
Jingkang Yang, Yuhao Dong, Shuai Liu +8
Large vision-language models (VLMs) have achieved substantial progress in multimodal perception and reasoning. When integrated into an embodied agent, existing embodied VLM works e…
OpenOOD v1.5: Enhanced Benchmark for Out-of-Distribution Detection
Jingyang Zhang, Jingkang Yang, Pengyun Wang +9
Out-of-Distribution (OOD) detection is critical for the reliable operation of open-world intelligent systems. Despite the emergence of an increasing number of OOD detection methods…
Semi-Supervised and Long-Tailed Object Detection with CascadeMatch
Yuhang Zang, Kaiyang Zhou, Chen Huang +1
This paper focuses on long-tailed object detection in the semi-supervised learning setting, which poses realistic challenges, but has rarely been studied in the literature. We prop…
Contextual Object Detection with Multimodal Large Language Models
Yuhang Zang, Wei Li, Jun Han +2
Recent Multimodal Large Language Models (MLLMs) are remarkable in vision-language tasks, such as image captioning and question answering, but lack the essential perception ability,…
What Makes Good Examples for Visual In-Context Learning?
Yuanhan Zhang, Kaiyang Zhou, Ziwei Liu
Large-scale models trained on broad data have recently become the mainstream architecture in computer vision due to their strong generalization performance. In this paper, the main…
Learning to Augment via Implicit Differentiation for Domain Generalization
Tingwei Wang, Da Li, Kaiyang Zhou +2
Machine learning models are intrinsically vulnerable to domain shift between training and testing data, resulting in poor performance in novel domains. Domain generalization (DG) a…
OpenOOD: Benchmarking Generalized Out-of-Distribution Detection
Jingkang Yang, Pengyun Wang, Dejian Zou +13
Out-of-distribution (OOD) detection is vital to safety-critical machine learning applications and has thus been extensively studied, with a plethora of methods developed in the lit…
Unified Vision and Language Prompt Learning
Yuhang Zang, Wei Li, Kaiyang Zhou +2
Prompt tuning, a parameter- and data-efficient transfer learning paradigm that tunes only a small number of parameters in a model's input space, has become a trend in the vision co…
On-Device Domain Generalization
Kaiyang Zhou, Yuanhan Zhang, Yuhang Zang +3
We present a systematic study of domain generalization (DG) for tiny neural networks. This problem is critical to on-device machine learning applications but has been overlooked in…
Panoptic Scene Graph Generation
Jingkang Yang, Yi Zhe Ang, Zujin Guo +3
Existing research addresses scene graph generation (SGG) -- a critical technology for scene understanding in images -- from a detection perspective, i.e., objects are detected usin…
Detecting Humans in RGB-D Data with CNNs
Kaiyang Zhou, Adeline Paiement, Majid Mirmehdi
We address the problem of people detection in RGB-D data where we leverage depth information to develop a region-of-interest (ROI) selection method that provides proposals to two c…
Neural Prompt Search
Yuanhan Zhang, Kaiyang Zhou, Ziwei Liu
The size of vision models has grown exponentially over the last few years, especially after the emergence of Vision Transformer. This has motivated the development of parameter-eff…
Full-Spectrum Out-of-Distribution Detection
Jingkang Yang, Kaiyang Zhou, Ziwei Liu
Existing out-of-distribution (OOD) detection literature clearly defines semantic shift as a sign of OOD but does not have a consensus over covariate shift. Samples experiencing cov…
Open-Vocabulary DETR with Conditional Matching
Yuhang Zang, Wei Li, Kaiyang Zhou +2
Open-vocabulary object detection, which is concerned with the problem of detecting novel objects guided by natural language, has gained increasing attention from the community. Ide…
Conditional Prompt Learning for Vision-Language Models
Kaiyang Zhou, Jingkang Yang, Chen Change Loy +1
With the rise of powerful pre-trained vision-language models like CLIP, it becomes essential to investigate ways to adapt these models to downstream datasets. A recently proposed m…
Dynamic Instance Domain Adaptation
Zhongying Deng, Kaiyang Zhou, Da Li +3
Most existing studies on unsupervised domain adaptation (UDA) assume that each domain's training samples come with domain labels (e.g., painting, photo). Samples from each domain a…
Domain Attention Consistency for Multi-Source Domain Adaptation
Zhongying Deng, Kaiyang Zhou, Yongxin Yang +1
Most existing multi-source domain adaptation (MSDA) methods minimize the distance between multiple source-target domain pairs via feature distribution alignment, an approach borrow…
Generalized Out-of-Distribution Detection: A Survey
Jingkang Yang, Kaiyang Zhou, Yixuan Li +1
Out-of-distribution (OOD) detection is critical to ensuring the reliability and safety of machine learning systems. For instance, in autonomous driving, we would like the driving s…
Learning to Prompt for Vision-Language Models
Kaiyang Zhou, Jingkang Yang, Chen Change Loy +1
Large pre-trained vision-language models like CLIP have shown great potential in learning representations that are transferable across a wide range of downstream tasks. Different f…
Energy-Based Open-World Uncertainty Modeling for Confidence Calibration
Yezhen Wang, Bo Li, Tong Che +3
Confidence calibration is of great importance to the reliability of decisions made by machine learning systems. However, discriminative classifiers based on deep neural networks ar…
MixStyle Neural Networks for Domain Generalization and Adaptation
Kaiyang Zhou, Yongxin Yang, Yu Qiao +1
Neural networks do not generalize well to unseen data with domain shifts -- a longstanding problem in machine learning and AI. To overcome the problem, we propose MixStyle, a simpl…
Semi-Supervised Domain Generalization with Stochastic StyleMatch
Kaiyang Zhou, Chen Change Loy, Ziwei Liu
Ideally, visual learning algorithms should be generalizable, for dealing with any unseen domain shift when deployed in a new target environment; and data-efficient, for reducing de…