80 citations · 188 across the 39 of their papers we have counts for
14 papers · 1 filter
Synthetic-to-Real Domain Generalized Semantic Segmentation for 3D Indoor Point Clouds
Yuyang Zhao, Na Zhao, Gim Hee Lee
Semantic segmentation in 3D indoor scenes has achieved remarkable performance under the supervision of large-scale annotated data. However, previous works rely on the assumption th…
Open World DETR: Transformer based Open World Object Detection
Na Dong, Yongqiang Zhang, Mingli Ding +1
Open world object detection aims at detecting objects that are absent in the object classes of the training data as unknown objects without explicit supervision. Furthermore, the e…
UNIKD: UNcertainty-filtered Incremental Knowledge Distillation for Neural Implicit Representation
Mengqi Guo, Chen Li, Hanlin Chen +1
Recent neural implicit representations (NIRs) have achieved great success in the tasks of 3D reconstruction and novel view synthesis. However, they require the images of a scene fr…
Style-Hallucinated Dual Consistency Learning: A Unified Framework for Visual Domain Generalization
Yuyang Zhao, Zhun Zhong, Na Zhao +2
Domain shift widely exists in the visual world, while modern deep neural networks commonly suffer from severe performance degradation under domain shift due to the poor generalizat…
Motion and Context-Aware Audio-Visual Conditioned Video Prediction
Yating Xu, Conghui Hu, Gim Hee Lee
The existing state-of-the-art method for audio-visual conditioned video prediction uses the latent codes of the audio-visual frames from a multimodal stochastic network and a frame…
Feature Representation Learning for Unsupervised Cross-domain Image Retrieval
Conghui Hu, Gim Hee Lee
Current supervised cross-domain image retrieval methods can achieve excellent performance. However, the cost of data collection and labeling imposes an intractable barrier to pract…
Rethinking IoU-based Optimization for Single-stage 3D Object Detection
Hualian Sheng, Sijia Cai, Na Zhao +5
Since Intersection-over-Union (IoU) based optimization maintains the consistency of the final IoU prediction metric and losses, it has been widely used in both regression and class…
NeurAR: Neural Uncertainty for Autonomous 3D Reconstruction with Implicit Neural Representations
Yunlong Ran, Jing Zeng, Shibo He +5
Implicit neural representations have shown compelling results in offline 3D reconstruction and also recently demonstrated the potential for online SLAM systems. However, applying t…
Adversarial Style Augmentation for Domain Generalized Urban-Scene Segmentation
Zhun Zhong, Yuyang Zhao, Gim Hee Lee +1
In this paper, we consider the problem of domain generalization in semantic segmentation, which aims to learn a robust model using only labeled synthetic (source) data. The model i…
CA-UDA: Class-Aware Unsupervised Domain Adaptation with Optimal Assignment and Pseudo-Label Refinement
Can Zhang, Gim Hee Lee
Recent works on unsupervised domain adaptation (UDA) focus on the selection of good pseudo-labels as surrogates for the missing labels in the target data. However, source domain bi…
VRAG: Region Attention Graphs for Content-Based Video Retrieval
Kennard Ng, Ser-Nam Lim, Gim Hee Lee
Content-based Video Retrieval (CBVR) is used on media-sharing platforms for applications such as video recommendation and filtering. To manage databases that scale to billions of v…
Incremental-DETR: Incremental Few-Shot Object Detection via Self-Supervised Learning
Na Dong, Yongqiang Zhang, Mingli Ding +1
Incremental few-shot object detection aims at detecting novel classes without forgetting knowledge of the base classes with only a few labeled training data from the novel classes.…
Style-Hallucinated Dual Consistency Learning for Domain Generalized Semantic Segmentation
Yuyang Zhao, Zhun Zhong, Na Zhao +2
In this paper, we study the task of synthetic-to-real domain generalized semantic segmentation, which aims to learn a model that is robust to unseen real-world scenes using only sy…
Weakly Supervised Learning of Keypoints for 6D Object Pose Estimation
Meng Tian, Gim Hee Lee
State-of-the-art approaches for 6D object pose estimation require large amounts of labeled data to train the deep networks. However, the acquisition of 6D object pose annotations i…