Copertina

FQ-PETR: Fully Quantized Position Embedding Transformation for Multi-View 3D Object Detection

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Yu, Jiangyong, Shu, Changyong, Zhou, Sifan, Yu, Zichen, Hu, Xing, Chen, Yan, Yang, Dawei
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

FQ-PETR: Fully Quantized Position Embedding Transformation for Multi-View 3D Object Detection
di: Yu, Jiangyong, et al.
Pubblicazione: (2025)

UltimateDO: An Efficient Framework to Marry Occupancy Prediction with 3D Object Detection via Channel2height
di: Yu, Zichen, et al.
Pubblicazione: (2024)

I-LLM: Efficient Integer-Only Inference for Fully-Quantized Low-Bit Large Language Models
di: Hu, Xing, et al.
Pubblicazione: (2024)

OstQuant: Refining Large Language Model Quantization with Orthogonal and Scaling Transformations for Better Distribution Fitting
di: Hu, Xing, et al.
Pubblicazione: (2025)

RWKVQuant: Quantizing the RWKV Family with Proxy Guided Hybrid of Scalar and Vector Quantization
di: Xu, Chen, et al.
Pubblicazione: (2025)

GSRender: Deduplicated Occupancy Prediction via Weakly Supervised 3D Gaussian Splatting
di: Sun, Qianpu, et al.
Pubblicazione: (2024)

MoEQuant: Enhancing Quantization for Mixture-of-Experts Large Language Models via Expert-Balanced Sampling and Affinity Guidance
di: Hu, Xing, et al.
Pubblicazione: (2025)

DVPE: Divided View Position Embedding for Multi-View 3D Object Detection
di: Wang, Jiasen, et al.
Pubblicazione: (2024)

FreqPDE: Rethinking Positional Depth Embedding for Multi-View 3D Object Detection Transformers
di: Su, Haisheng, et al.
Pubblicazione: (2025)

RoPETR: Improving Temporal Camera-Only 3D Detection by Integrating Enhanced Rotary Position Embedding
di: Ji, Hang, et al.
Pubblicazione: (2025)

MQuant: Unleashing the Inference Potential of Multimodal Large Language Models via Full Static Quantization
di: Yu, JiangYong, et al.
Pubblicazione: (2025)

MambaQuant: Quantizing the Mamba Family with Variance Aligned Rotation Methods
di: Xu, Zukang, et al.
Pubblicazione: (2025)

Panoptic-FlashOcc: An Efficient Baseline to Marry Semantic Occupancy with Panoptic via Instance Center
di: Yu, Zichen, et al.
Pubblicazione: (2024)

PolarBEVDet: Exploring Polar Representation for Multi-View 3D Object Detection in Bird's-Eye-View
di: Yu, Zichen, et al.
Pubblicazione: (2024)

CAR-SAM: Cross-Attention Reconstruction for Post-Training Quantization of the Segment Anything Model
di: Wen, Houji, et al.
Pubblicazione: (2026)

GSQ-Tuning: Group-Shared Exponents Integer in Fully Quantized Training for LLMs On-Device Fine-tuning
di: Zhou, Sifan, et al.
Pubblicazione: (2025)

FedFQ: Federated Learning with Fine-Grained Quantization
di: Li, Haowei, et al.
Pubblicazione: (2024)

OPEN: Object-wise Position Embedding for Multi-view 3D Object Detection
di: Hou, Jinghua, et al.
Pubblicazione: (2024)

NLI:Non-uniform Linear Interpolation Approximation of Nonlinear Operations for Efficient LLMs Inference
di: Yu, Jiangyong, et al.
Pubblicazione: (2026)

View Transformation Robustness for Multi-View 3D Object Reconstruction with Reconstruction Error-Guided View Selection
di: Zhang, Qi, et al.
Pubblicazione: (2024)

Information Entropy Guided Height-aware Histogram for Quantization-friendly Pillar Feature Encoder
di: Zhou, Sifan, et al.
Pubblicazione: (2024)

LiDAR-PTQ: Post-Training Quantization for Point Cloud 3D Object Detection
di: Zhou, Sifan, et al.
Pubblicazione: (2024)

EVT: Efficient View Transformation for Multi-Modal 3D Object Detection
di: Lee, Yongjin, et al.
Pubblicazione: (2024)

MGVQ: Synergizing Multi-dimensional Sensitivity-Aware and Gradient-Hessian Fusion for Vector Quantization
di: Wang, Zhong, et al.
Pubblicazione: (2026)

TORQ: Two-Level Orthogonal Rotation for MXFP4 Quantization
di: Xu, Zukang, et al.
Pubblicazione: (2026)

AQD: Towards Accurate Fully-Quantized Object Detection
di: Chen, Peng, et al.
Pubblicazione: (2020)

Multi-View Attentive Contextualization for Multi-View 3D Object Detection
di: Liu, Xianpeng, et al.
Pubblicazione: (2024)

From Detection to Association: Learning Discriminative Object Embeddings for Multi-Object Tracking
di: Shao, Yuqing, et al.
Pubblicazione: (2025)

Learning Where to Embed: Noise-Aware Positional Embedding for Query Retrieval in Small-Object Detection
di: Zeng, Yangchen, et al.
Pubblicazione: (2026)

Fully Sparse Fusion for 3D Object Detection
di: Li, Yingyan, et al.
Pubblicazione: (2023)

OA-DET3D: Embedding Object Awareness as a General Plug-in for Multi-Camera 3D Object Detection
di: Chu, Xiaomeng, et al.
Pubblicazione: (2023)

Fronthaul-Efficient Distributed Cooperative 3D Positioning with Quantized Latent CSI Embeddings
di: An, Tong, et al.
Pubblicazione: (2026)

MDHA: Multi-Scale Deformable Transformer with Hybrid Anchors for Multi-View 3D Object Detection
di: Adeline, Michelle, et al.
Pubblicazione: (2024)

MVCTrack: Boosting 3D Point Cloud Tracking via Multimodal-Guided Virtual Cues
di: Hu, Zhaofeng, et al.
Pubblicazione: (2024)

PillarTrack:Boosting Pillar Representation for Transformer-based 3D Single Object Tracking on Point Clouds
di: Xu, Weisheng, et al.
Pubblicazione: (2024)

Boosting Multi-View Indoor 3D Object Detection via Adaptive 3D Volume Construction
di: Zhang, Runmin, et al.
Pubblicazione: (2025)

RayD3D: Distilling Depth Knowledge Along the Ray for Robust Multi-View 3D Object Detection
di: Ding, Rui, et al.
Pubblicazione: (2026)

RSAVQ: Riemannian Sensitivity-Aware Vector Quantization for Large Language Models
di: Xu, Zukang, et al.
Pubblicazione: (2025)

OcRFDet: Object-Centric Radiance Fields for Multi-View 3D Object Detection in Autonomous Driving
di: Ji, Mingqian, et al.
Pubblicazione: (2025)

StereoMV2D: A Sparse Temporal Stereo-Enhanced Framework for Robust Multi-View 3D Object Detection
di: Wu, Di, et al.
Pubblicazione: (2025)