1 code implementation • 6 Feb 2024 • Tianyang Han, Qing Lian, Rui Pan, Renjie Pi, Jipeng Zhang, Shizhe Diao, Yong Lin, Tong Zhang
In this paper, we identify a typical class of inputs that baffles MLLMs, which consist of images that are highly relevant but inconsistent with answers, causing MLLMs to suffer from hallucination.
1 code implementation • 5 Jan 2024 • Renjie Pi, Tianyang Han, Yueqi Xie, Rui Pan, Qing Lian, Hanze Dong, Jipeng Zhang, Tong Zhang
The deployment of multimodal large language models (MLLMs) has brought forth a unique vulnerability: susceptibility to malicious attacks through visual inputs.
1 code implementation • 16 Nov 2023 • Hanning Zhang, Shizhe Diao, Yong Lin, Yi R. Fung, Qing Lian, Xingyao Wang, Yangyi Chen, Heng Ji, Tong Zhang
This approach is formalized by first identifying the disparity in knowledge encompassed by pre-trained parameters compared to that of instruction tuning data.
1 code implementation • 17 Oct 2023 • Hao Lu, Yunpeng Zhang, Qing Lian, Dalong Du, Yingcong Chen
In our approach, we render diverse view maps from BEV features and rectify the perspective bias of these maps, leveraging implicit foreground volumes to bridge the camera and BEV planes.
1 code implementation • 18 Sep 2023 • Helbert Paat, Qing Lian, Weilong Yao, Tong Zhang
In this paper, we present the first approach that addresses the inherent ambiguities present in pseudo labels by introducing an Evidential Deep Learning (EDL) based uncertainty estimation framework.
no code implementations • 5 Sep 2023 • Yong Lin, Chen Liu, Chenlu Ye, Qing Lian, Yuan YAO, Tong Zhang
Our proposed method, COPS (unCertainty based OPtimal Sub-sampling), is designed to minimize the expected loss of a model trained on subsampled data.
no code implementations • CVPR 2023 • Leheng Li, Qing Lian, Luozhou Wang, Ningning Ma, Ying-Cong Chen
This work explores the use of 3D generative models to synthesize training data for 3D vision tasks.
1 code implementation • 29 Mar 2023 • Qing Lian, Tai Wang, Dahua Lin, Jiangmiao Pang
Recent multi-camera 3D object detectors usually leverage temporal information to construct multi-view stereo that alleviates the ill-posed depth estimation.
1 code implementation • 26 Jul 2022 • Tai Wang, Qing Lian, Chenming Zhu, Xinge Zhu, Wenwei Zhang
In this technical report, we present our solution, dubbed MV-FCOS3D++, for the Camera-Only 3D Detection track in Waymo Open Dataset Challenge 2022.
1 code implementation • CVPR 2022 • Qing Lian, Peiliang Li, Xiaozhi Chen
Based on the object depth, the dense coordinates patch together with the corresponding object features is reprojected to the image space to build a cost volume in a joint semantic and geometric error manner.
no code implementations • 2 Jun 2021 • Yunqi Wang, Furui Liu, Zhitang Chen, Qing Lian, Shoubo Hu, Jianye Hao, Yik-Chung Wu
Domain generalization aims to learn knowledge invariant across different distributions while semantically meaningful for downstream tasks from multiple source domains, to improve the model's generalization ability on unseen target domains.
no code implementations • CVPR 2022 • Qing Lian, Botao Ye, Ruijia Xu, Weilong Yao, Tong Zhang
In addition, we demonstrate that the augmentation methods are well suited for semi-supervised training and cross-dataset generalization.
no code implementations • 1 Jan 2021 • Qing Lian, LIN Yong, Tong Zhang
We consider the domain generalization problem, where the test domain differs from the training domain.
1 code implementation • 6 Oct 2020 • Xinwei Shen, Furui Liu, Hanze Dong, Qing Lian, Zhitang Chen, Tong Zhang
This paper proposes a Disentangled gEnerative cAusal Representation (DEAR) learning method under appropriate supervised information.
1 code implementation • ICCV 2019 • Qing Lian, Fengmao Lv, Lixin Duan, Boqing Gong
We propose a new approach, called self-motivated pyramid curriculum domain adaptation (PyCDA), to facilitate the adaptation of semantic segmentation neural networks from synthetic source domains to real target domains.
Ranked #14 on Image-to-Image Translation on SYNTHIA-to-Cityscapes
1 code implementation • 3 May 2019 • Qing Lian, Wen Li, Lin Chen, Lixin Duan
Particularly, in open set domain adaptation, we allow the classes from the source and target domains to be partially overlapped.