13 citations · 37 across the 15 of their papers we have counts for
15 papers
SAM 3: Segment Anything with Concepts
Nicolas Carion, Laura Gustafson, Yuan-Ting Hu +35
We present Segment Anything Model (SAM) 3, a unified model that detects, segments, and tracks objects in images and videos based on concept prompts, which we define as either short…
Revisiting Semi-supervised Adversarial Robustness via Noise-aware Online Robust Distillation
Tsung-Han Wu, Hung-Ting Su, Shang-Tse Chen +1
The robust self-training (RST) framework has emerged as a prominent approach for semi-supervised adversarial training. To explore the possibility of tackling more complicated tasks…
AED: Adaptable Error Detection for Few-shot Imitation Policy
Jia-Fong Yeh, Kuo-Han Hung, Pang-Chi Lo +5
We introduce a new task called Adaptable Error Detection (AED), which aims to identify behavior errors in few-shot imitation (FSI) policies based on visual observations in novel en…
WLST: Weak Labels Guided Self-training for Weakly-supervised Domain Adaptation on 3D Object Detection
Tsung-Lin Tsou, Tsung-Han Wu, Winston H. Hsu
In the field of domain adaptation (DA) on 3D object detection, most of the work is dedicated to unsupervised domain adaptation (UDA). Yet, without any target annotations, the perfo…
MuRAL: Multi-Scale Region-based Active Learning for Object Detection
Yi-Syuan Liou, Tsung-Han Wu, Jia-Fong Yeh +2
Obtaining large-scale labeled object detection dataset can be costly and time-consuming, as it involves annotating images with bounding boxes and class labels. Thus, some specializ…
Free-form 3D Scene Inpainting with Dual-stream GAN
Ru-Fen Jheng, Tsung-Han Wu, Jia-Fong Yeh +1
Nowadays, the need for user editing in a 3D scene has rapidly increased due to the development of AR and VR technology. However, the existing 3D scene completion task (and datasets…
Learning Fine-Grained Visual Understanding for Video Question Answering via Decoupling Spatial-Temporal Modeling
Hsin-Ying Lee, Hung-Ting Su, Bing-Chen Tsai +3
While recent large-scale video-language pre-training made great progress in video question answering, the design of spatial modeling of video-language models is less fine-grained t…
CrossDTR: Cross-view and Depth-guided Transformers for 3D Object Detection
Ching-Yu Tseng, Yi-Rong Chen, Hsin-Ying Lee +3
To achieve accurate 3D object detection at a low cost for autonomous driving, many multi-camera methods have been proposed and solved the occlusion problem of monocular approaches.…
Fair Robust Active Learning by Joint Inconsistency
Tsung-Han Wu, Hung-Ting Su, Shang-Tse Chen +1
Fairness and robustness play vital roles in trustworthy machine learning. Observing safety-critical needs in various annotation-expensive vision applications, we introduce a novel…
MonoDTR: Monocular 3D Object Detection with Depth-Aware Transformer
Kuan-Chih Huang, Tsung-Han Wu, Hung-Ting Su +1
Monocular 3D object detection is an important yet challenging task in autonomous driving. Some existing methods leverage depth information from an off-the-shelf depth estimator to…
D2ADA: Dynamic Density-aware Active Domain Adaptation for Semantic Segmentation
Tsung-Han Wu, Yi-Syuan Liou, Shao-Ji Yuan +4
In the field of domain adaptation, a trade-off exists between the model performance and the number of target domain annotations. Active learning, maximizing model performance with…
Anomaly-Aware Semantic Segmentation by Leveraging Synthetic-Unknown Data
Guan-Rong Lu, Yueh-Cheng Liu, Tung-I Chen +3
Anomaly awareness is an essential capability for safety-critical applications such as autonomous driving. While recent progress of robotics and computer vision has enabled anomaly…
ReDAL: Region-based and Diversity-aware Active Learning for Point Cloud Semantic Segmentation
Tsung-Han Wu, Yueh-Cheng Liu, Yu-Kai Huang +4
Despite the success of deep learning on supervised point cloud semantic segmentation, obtaining large-scale point-by-point manual annotations is still a significant challenge. To r…
: Learnable Sparse Signal Superdensity for Guided Depth Estimation
Yu-Kai Huang, Yueh-Cheng Liu, Tsung-Han Wu +5
Dense depth estimation plays a key role in multiple applications such as robotics, 3D reconstruction, and augmented reality. While sparse signal, e.g., LiDAR and Radar, has been le…
Expanding Sparse Guidance for Stereo Matching
Yu-Kai Huang, Yueh-Cheng Liu, Tsung-Han Wu +2
The performance of image based stereo estimation suffers from lighting variations, repetitive patterns and homogeneous appearance. Moreover, to achieve good performance, stereo sup…