Search Results for author: Yanan Zhang

Found 26 papers, 8 papers with code

Breaking the Stigma! Unobtrusively Probe Symptoms in Depression Disorder Diagnosis Dialogue

no code implementations25 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.

PACF: Prototype Augmented Compact Features for Improving Domain Adaptive Object Detection

no code implementations15 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.

object-detection Object Detection

SpecFuse: Ensembling Large Language Models via Next-Segment Prediction

no code implementations10 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.

Lightweight Spatial Embedding for Vision-based 3D Occupancy Prediction

no code implementations8 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.

Autonomous Driving

Estimating the Cost of Informal Care with a Novel Two-Stage Approach to Individual Synthetic Control

no code implementations15 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.

Rethinking Misalignment in Vision-Language Model Adaptation from a Causal Perspective

no code implementations1 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.

Language Modeling Language Modelling

GeoBEV: Learning Geometric BEV Representation for Multi-view 3D Object Detection

1 code implementation3 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.

3D Object Detection object-detection

PS-TTL: Prototype-based Soft-labels and Test-Time Learning for Few-shot Object Detection

1 code implementation11 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.

Few-Shot Object Detection object-detection

FSD-BEV: Foreground Self-Distillation for Multi-view 3D Object Detection

1 code implementation14 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.

3D Object Detection Autonomous Driving +2

STAL3D: Unsupervised Domain Adaptation for 3D Object Detection via Collaborating Self-Training and Adversarial Learning

no code implementations27 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.

3D Object Detection object-detection +1

Vision-based 3D occupancy prediction in autonomous driving: a review and outlook

1 code implementation4 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.

Autonomous Driving

Event-enhanced Retrieval in Real-time Search

1 code implementation9 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.

Contrastive Learning Decoder +3

Exploration and Improvement of Nerf-based 3D Scene Editing Techniques

no code implementations23 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.

3D scene Editing NeRF

DSD-DA: Distillation-based Source Debiasing for Domain Adaptive Object Detection

no code implementations17 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.

Classification object-detection +2

SA-BEV: Generating Semantic-Aware Bird's-Eye-View Feature for Multi-view 3D Object Detection

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.

3D Object Detection

OcTr: Octree-based Transformer for 3D Object Detection

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.

3D Object Detection Object +1

MetaMask: Revisiting Dimensional Confounder for Self-Supervised Learning

2 code implementations16 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.

Contrastive Learning Meta-Learning +1

Disentangle and Remerge: Interventional Knowledge Distillation for Few-Shot Object Detection from A Conditional Causal Perspective

1 code implementation26 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.

Few-Shot Learning Few-Shot Object Detection +4

CAT-Det: Contrastively Augmented Transformer for Multi-modal 3D Object Detection

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.

3D Object Detection Autonomous Driving +4

Multi-scale fusion self attention mechanism

no code implementations29 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.

Relation Extraction

Cross Modification Attention Based Deliberation Model for Image Captioning

no code implementations17 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.

Decoder Descriptive +2

PC-RGNN: Point Cloud Completion and Graph Neural Network for 3D Object Detection

no code implementations18 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.

3D Object Detection Autonomous Driving +3

Cannot find the paper you are looking for? You can Submit a new open access paper.