2 citations · 5 across the 20 of their papers we have counts for
21 papers
From Semantic Grounding to Decision Optimization: A Unified Framework for Long-Horizon UAV Vision-Language Navigation
Zeyuan Ma, Jiaxin Chen, Di Huang
UAV vision-language navigation (UAV-VLN) focuses on enabling an aerial agent to follow natural-language instructions in open 3D environments from egocentric visual observations. Cu…
DroneFINE: Domain-Aware Parameter-Efficient Fine-Tuning of Vision-Language Detectors for Drone Images
Ke Wu, Yanan Zhang, Yingjie Gao +5
Object detection for Unmanned Aerial Vehicles (UAVs) working in open and dynamic environments is a highly challenging task. While Vision-Language Models (VLMs) have offered a power…
MP-ISMoE: Mixed-Precision Interactive Side Mixture-of-Experts for Efficient Transfer Learning
Yutong Zhang, Zimeng Wu, Shangcai Liao +2
Parameter-efficient transfer learning (PETL) has emerged as a pivotal paradigm for adapting pre-trained foundation models to downstream tasks, significantly reducing trainable para…
Memory-Efficient Transfer Learning with Fading Side Networks via Masked Dual Path Distillation
Yutong Zhang, Jiaxin Chen, Honglin Chen +5
Memory-efficient transfer learning (METL) approaches have recently achieved promising performance in adapting pre-trained models to downstream tasks. They avoid applying gradient b…
Visual Prototype Conditioned Focal Region Generation for UAV-Based Object Detection
Wenhao Li, Zimeng Wu, Yu Wu +2
Unmanned aerial vehicle (UAV) based object detection is a critical but challenging task, when applied in dynamically changing scenarios with limited annotated training data. Layout…
Collaborative Multi-Mode Pruning for Vision-Language Models
Zimeng Wu, Yunhong Wang, Donghao Wang +1
Vision-Language Models (VLMs) have advanced rapidly within the unified Transformer architecture, yet their deployment on resource-constrained devices remains challenging due to hig…
Beyond Open Vocabulary: Multimodal Prompting for Object Detection in Remote Sensing Images
Shuai Yang, Ziyue Huang, Jiaxin Chen +2
Open-vocabulary object detection in remote sensing commonly relies on text-only prompting to specify target categories, implicitly assuming that inference-time category queries can…
Probe and Skip: Self-Predictive Token Skipping for Efficient Long-Context LLM Inference
Zimeng Wu, Donghao Wang, Chaozhe Jin +2
Long-context inference enhances the reasoning capability of Large Language Models (LLMs), but incurs significant computational overhead. Token-oriented methods, such as pruning and…
FIMA-Q: Post-Training Quantization for Vision Transformers by Fisher Information Matrix Approximation
Zhuguanyu Wu, Shihe Wang, Jiayi Zhang +2
Post-training quantization (PTQ) has stood out as a cost-effective and promising model compression paradigm in recent years, as it avoids computationally intensive model retraining…
APHQ-ViT: Post-Training Quantization with Average Perturbation Hessian Based Reconstruction for Vision Transformers
Zhuguanyu Wu, Jiayi Zhang, Jiaxin Chen +3
Vision Transformers (ViTs) have become one of the most commonly used backbones for vision tasks. Despite their remarkable performance, they often suffer significant accuracy drops…
Transforming Vision Transformer: Towards Efficient Multi-Task Asynchronous Learning
Hanwen Zhong, Jiaxin Chen, Yutong Zhang +2
Multi-Task Learning (MTL) for Vision Transformer aims at enhancing the model capability by tackling multiple tasks simultaneously. Most recent works have predominantly focused on d…
Breaking the SSL-AL Barrier: A Synergistic Semi-Supervised Active Learning Framework for 3D Object Detection
Zengran Wang, Yanan Zhang, Jiaxin Chen +1
To address the annotation burden in LiDAR-based 3D object detection, active learning (AL) methods offer a promising solution. However, traditional active learning approaches solely…
TCAQ-DM: Timestep-Channel Adaptive Quantization for Diffusion Models
Haocheng Huang, Jiaxin Chen, Jinyang Guo +2
Diffusion models have achieved remarkable success in the image and video generation tasks. Nevertheless, they often require a large amount of memory and time overhead during infere…
3D-Actor: Learning Pose-Conditioned 3D-Aware Denoiser for Realistic Gaussian Avatar Modeling
Zichen Tang, Hongyu Yang, Hanchen Zhang +2
Advancements in neural implicit representations and differentiable rendering have markedly improved the ability to learn animatable 3D avatars from sparse multi-view RGB videos. Ho…
Centerness-based Instance-aware Knowledge Distillation with Task-wise Mutual Lifting for Object Detection on Drone Imagery
Bowei Du, Zhixuan Liao, Yanan Zhang +3
Developing accurate and efficient detectors for drone imagery is challenging due to the inherent complexity of aerial scenes. While some existing methods aim to achieve high accura…
AdaLog: Post-Training Quantization for Vision Transformers with Adaptive Logarithm Quantizer
Zhuguanyu Wu, Jiaxin Chen, Hanwen Zhong +2
Vision Transformer (ViT) has become one of the most prevailing fundamental backbone networks in the computer vision community. Despite the high accuracy, deploying it in real appli…
iVPT: Improving Task-relevant Information Sharing in Visual Prompt Tuning by Cross-layer Dynamic Connection
Nan Zhou, Jiaxin Chen, Di Huang
Recent progress has shown great potential of visual prompt tuning (VPT) when adapting pre-trained vision transformers to various downstream tasks. However, most existing solutions…
Reading Chinese in Natural Scenes with a Bag-of-Radicals Prior
Liu Yongbin, Liu Qingjie, Chen Jiaxin +1
Scene text recognition (STR) on Latin datasets has been extensively studied in recent years, and state-of-the-art (SOTA) models often reach high accuracy. However, the performance…
UFPMP-Det: Toward Accurate and Efficient Object Detection on Drone Imagery
Yecheng Huang, Jiaxin Chen, Di Huang
This paper proposes a novel approach to object detection on drone imagery, namely Multi-Proxy Detection Network with Unified Foreground Packing (UFPMP-Det). To deal with the numero…
PR-GCN: A Deep Graph Convolutional Network with Point Refinement for 6D Pose Estimation
Guangyuan Zhou, Huiqun Wang, Jiaxin Chen +1
RGB-D based 6D pose estimation has recently achieved remarkable progress, but still suffers from two major limitations: (1) ineffective representation of depth data and (2) insuffi…
Video Person Re-identification using Attribute-enhanced Features
Tianrui Chai, Zhiyuan Chen, Annan Li +3
Video-based person re-identification (Re-ID) which aims to associate people across non-overlapping cameras using surveillance video is a challenging task. Pedestrian attribute, suc…