no code implementations • 26 Jan 2025 • Zengran Wang, Yanan Zhang, Jiaxin Chen, Di Huang
To address the annotation burden in LiDAR-based 3D object detection, active learning (AL) methods offer a promising solution.
no code implementations • 25 Jan 2025 • Jieming Cao, Chen Huang, Yanan Zhang, Ruibo Deng, Jincheng Zhang, Wenqiang Lei
Stigma has emerged as one of the major obstacles to effectively diagnosing depression, as it prevents users from open conversations about their struggles.
no code implementations • 15 Jan 2025 • ChenGuang Liu, Yongchao Feng, Yanan Zhang, Qingjie Liu, Yunhong Wang
These detectors exhibit higher-variance class-conditional distributions in the target domain than that in the source domain, along with mean shift.
no code implementations • 10 Dec 2024 • Bo Lv, Chen Tang, Yanan Zhang, Xin Liu, Yue Yu, Ping Luo
In this paper, we propose SpecFuse, a novel ensemble framework that outputs the fused result by iteratively producing the next segment through collaboration among LLMs.
no code implementations • 8 Dec 2024 • Jinqing Zhang, Yanan Zhang, Qingjie Liu, Yunhong Wang
Finally, TPV Embeddings will interact with each other by Lightweight TPV Interaction module to obtain the Spatial Embedding that is optimal supplementary to BEV features.
no code implementations • 15 Nov 2024 • Maria Petrillo, Daniel Valdenegro, Charles Rahal, Yanan Zhang, Gwilym Pryce, Matthew R. Bennett
Informal carers provide the majority of care for people living with challenges related to older age, long-term illness, or disability.
no code implementations • 5 Nov 2024 • Bowei Du, Zhixuan Liao, Yanan Zhang, Zhi Cai, Jiaxin Chen, Di Huang
While some existing methods aim to achieve high accuracy by utilizing larger models, their computational cost is prohibitive for drones.
no code implementations • 1 Oct 2024 • Yanan Zhang, Jiangmeng Li, Lixiang Liu, Wenwen Qiang
As task-irrelevant knowledge is unobservable, we leverage the front-door adjustment and propose Causality-Guided Semantic Decoupling and Classification (CDC) to mitigate the interference of task-irrelevant knowledge.
1 code implementation • 3 Sep 2024 • Jinqing Zhang, Yanan Zhang, Yunlong Qi, Zehua Fu, Qingjie Liu, Yunhong Wang
In this paper, we identify the drawbacks of previous approaches that limit the geometric quality of BEV representation and propose Radial-Cartesian BEV Sampling (RC-Sampling), which outperforms other feature transformation methods in efficiently generating high-resolution dense BEV representation to restore fine-grained geometric information.
Ranked #7 on
3D Object Detection
on nuScenes Camera Only
1 code implementation • 11 Aug 2024 • Yingjie Gao, Yanan Zhang, Ziyue Huang, Nanqing Liu, Di Huang
Specifically, we design a Test-Time Learning (TTL) module that employs a mean-teacher network for self-training to discover novel instances from test data, allowing detectors to learn better representations and classifiers for novel classes.
1 code implementation • 14 Jul 2024 • Zheng Jiang, Jinqing Zhang, Yanan Zhang, Qingjie Liu, Zhenghui Hu, Baohui Wang, Yunhong Wang
In recent years, several cross-modal distillation methods have been proposed to transfer beneficial information from teacher models to student models, with the aim of enhancing performance.
no code implementations • 27 Jun 2024 • Yanan Zhang, Chao Zhou, Di Huang
Existing 3D object detection suffers from expensive annotation costs and poor transferability to unknown data due to the domain gap, Unsupervised Domain Adaptation (UDA) aims to generalize detection models trained in labeled source domains to perform robustly on unexplored target domains, providing a promising solution for cross-domain 3D object detection.
1 code implementation • 4 May 2024 • Yanan Zhang, Jinqing Zhang, Zengran Wang, Junhao Xu, Di Huang
In recent years, autonomous driving has garnered escalating attention for its potential to relieve drivers' burdens and improve driving safety.
1 code implementation • 9 Apr 2024 • Yanan Zhang, Xiaoling Bai, Tianhua Zhou
Furthermore, to strengthen the focus on critical event information in events, we include a decoder module after the document encoder, introduce a generative event triplet extraction scheme based on prompt-tuning, and correlate the events with query encoder optimization through comparative learning.
no code implementations • 23 Jan 2024 • Shun Fang, Ming Cui, Xing Feng, Yanan Zhang
NeRF's high-quality scene synthesis capability was quickly accepted by scholars in the years after it was proposed, and significant progress has been made in 3D scene representation and synthesis.
no code implementations • 17 Nov 2023 • Yongchao Feng, Shiwei Li, Yingjie Gao, Ziyue Huang, Yanan Zhang, Qingjie Liu, Yunhong Wang
Furthermore, these methods face a more formidable challenge in achieving consistent classification and localization in the target domain compared to the source domain.
1 code implementation • ICCV 2023 • Jinqing Zhang, Yanan Zhang, Qingjie Liu, Yunhong Wang
In this paper, we propose Semantic-Aware BEV Pooling (SA-BEVPool), which can filter out background information according to the semantic segmentation of image features and transform image features into semantic-aware BEV features.
Ranked #10 on
3D Object Detection
on nuScenes Camera Only
no code implementations • 30 May 2023 • Yanan Zhang, Weijie Cui, Yangfan Zhang, Xiaoling Bai, Zhe Zhang, Jin Ma, Xiang Chen, Tianhua Zhou
In search engines, query expansion (QE) is a crucial technique to improve search experience.
no code implementations • CVPR 2023 • Chao Zhou, Yanan Zhang, Jiaxin Chen, Di Huang
A key challenge for LiDAR-based 3D object detection is to capture sufficient features from large scale 3D scenes especially for distant or/and occluded objects.
no code implementations • 2 Nov 2022 • Haolin Deng, Yanan Zhang, Yangfan Zhang, Wangyang Ying, Changlong Yu, Jun Gao, Wei Wang, Xiaoling Bai, Nan Yang, Jin Ma, Xiang Chen, Tianhua Zhou
To the best of our knowledge, it is currently the largest manually-annotated Chinese dataset for open event extraction.
2 code implementations • 16 Sep 2022 • Jiangmeng Li, Wenwen Qiang, Yanan Zhang, Wenyi Mo, Changwen Zheng, Bing Su, Hui Xiong
As a successful approach to self-supervised learning, contrastive learning aims to learn invariant information shared among distortions of the input sample.
1 code implementation • 26 Aug 2022 • Jiangmeng Li, Yanan Zhang, Wenwen Qiang, Lingyu Si, Chengbo Jiao, Xiaohui Hu, Changwen Zheng, Fuchun Sun
To understand the reasons behind this phenomenon, we revisit the learning paradigm of knowledge distillation on the few-shot object detection task from the causal theoretic standpoint, and accordingly, develop a Structural Causal Model.
no code implementations • CVPR 2022 • Yanan Zhang, Jiaxin Chen, Di Huang
In autonomous driving, LiDAR point-clouds and RGB images are two major data modalities with complementary cues for 3D object detection.
no code implementations • 29 Sep 2021 • Qibin Li, Nianmin Yao, Jian Zhao, Yanan Zhang
Based on the traditional attention mechanism, multi-scale fusion self attention extracts phrase information at different scales by setting convolution kernels at different levels, and calculates the corresponding attention matrix at different scales, so that the model can better extract phrase level information.
no code implementations • 17 Sep 2021 • Zheng Lian, Yanan Zhang, Haichang Li, Rui Wang, Xiaohui Hu
The conventional encoder-decoder framework for image captioning generally adopts a single-pass decoding process, which predicts the target descriptive sentence word by word in temporal order.
no code implementations • 18 Dec 2020 • Yanan Zhang, Di Huang, Yunhong Wang
LiDAR-based 3D object detection is an important task for autonomous driving and current approaches suffer from sparse and partial point clouds of distant and occluded objects.
Ranked #4 on
3D Object Detection
on KITTI Cars Hard val