Copertina

Faster Training, Fewer Labels: Self-Supervised Pretraining for Fine-Grained BEV Segmentation

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Busch, Daniel, Bohn, Christian, Kurbiel, Thomas, Friedrichs, Klaus, Meyes, Richard, Meisen, Tobias
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Improved Single Camera BEV Perception Using Multi-Camera Training
di: Busch, Daniel, et al.
Pubblicazione: (2024)

Efficient Inter-Task Attention for Multitask Transformer Models
di: Bohn, Christian, et al.
Pubblicazione: (2025)

Out-of-Distribution Object Detection in Street Scenes via Synthetic Outlier Exposure and Transfer Learning
di: Ilyas, Sadia, et al.
Pubblicazione: (2026)

CASPFormer: Trajectory Prediction from BEV Images with Deformable Attention
di: Yadav, Harsh, et al.
Pubblicazione: (2024)

Self-Supervised Pretraining for Fine-Grained Plankton Recognition
di: Kareinen, Joona, et al.
Pubblicazione: (2025)

AttentiveGRU: Recurrent Spatio-Temporal Modeling for Advanced Radar-Based BEV Object Detection
di: Saini, Loveneet, et al.
Pubblicazione: (2025)

Guided Exploration of Industrial Sensor Data
di: Tristan Langer, et al.
Pubblicazione: (2024)

Principal Component Clustering for Semantic Segmentation in Synthetic Data Generation
di: Stillger, Felix, et al.
Pubblicazione: (2024)

OccFeat: Self-supervised Occupancy Feature Prediction for Pretraining BEV Segmentation Networks
di: Sirko-Galouchenko, Sophia, et al.
Pubblicazione: (2024)

Depth-supervised NeRF: Fewer Views and Faster Training for Free
di: Deng, Kangle, et al.
Pubblicazione: (2021)

Boosting Sclera Segmentation through Semi-supervised Learning with Fewer Labels
di: Wang, Guanjun, et al.
Pubblicazione: (2025)

Disentanglement in T-space for Faster and Distributed Training of Diffusion Models with Fewer Latent-states
di: Gupta, Samarth, et al.
Pubblicazione: (2025)

RendBEV: Semantic Novel View Synthesis for Self-Supervised Bird's Eye View Segmentation
di: Monteagudo, Henrique Piñeiro, et al.
Pubblicazione: (2025)

Self and Mixed Supervision to Improve Training Labels for Multi-Class Medical Image Segmentation
di: Liu, Jianfei, et al.
Pubblicazione: (2024)

Large Scale Supervised Pretraining For Traumatic Brain Injury Segmentation
di: Ulrich, Constantin, et al.
Pubblicazione: (2025)

Combining Boundary Supervision and Segment-Level Regularization for Fine-Grained Action Segmentation
di: Mitsuoka, Hinako, et al.
Pubblicazione: (2026)

Mitigating Instance-Dependent Label Noise: Integrating Self-Supervised Pretraining with Pseudo-Label Refinement
di: Bala, Gouranga, et al.
Pubblicazione: (2024)

ReGATE: Learning Faster and Better with Fewer Tokens in MLLMs
di: Li, Chaoyu, et al.
Pubblicazione: (2025)

PCT: Perspective Cue Training Framework for Multi-Camera BEV Segmentation
di: Ishikawa, Haruya, et al.
Pubblicazione: (2024)

Self-Supervised Pretraining on Satellite Imagery: a Case Study on Label-Efficient Vehicle Detection
di: BOURCIER, Jules, et al.
Pubblicazione: (2022)

Rethinking Backbone Design for Lightweight 3D Object Detection in LiDAR
di: Chandorkar, Adwait, et al.
Pubblicazione: (2025)

Semantics-Guided Multimodal Masked Autoencoder Pretraining for 3D BEV Object Detection
di: Wariyapperuma, Prabuddhi, et al.
Pubblicazione: (2026)

SG-BEV: Satellite-Guided BEV Fusion for Cross-View Semantic Segmentation
di: Ye, Junyan, et al.
Pubblicazione: (2024)

MaskBEV: Towards A Unified Framework for BEV Detection and Map Segmentation
di: Zhao, Xiao, et al.
Pubblicazione: (2024)

InstanceBEV: Unifying Instance and BEV Representation for 3D Panoptic Segmentation
di: Li, Feng, et al.
Pubblicazione: (2025)

Self-Supervised Vision Transformers Are Efficient Segmentation Learners for Imperfect Labels
di: Lee, Seungho, et al.
Pubblicazione: (2024)

Learning Ego-Centric BEV Representations from a Perspective-Privileged View: Cross-View Supervision for Online HD Map Construction
di: Lengerer, Daniel, et al.
Pubblicazione: (2026)

Static Segmentation by Tracking: A Label-Efficient Approach for Fine-Grained Specimen Image Segmentation
di: Feng, Zhenyang, et al.
Pubblicazione: (2025)

Excite, Attend and Segment (EASe): Domain-Agnostic Fine-Grained Mask Discovery with Feature Calibration and Self-Supervised Upsampling
di: Singh, Deepank, et al.
Pubblicazione: (2026)

Score-based Conditional Generation with Fewer Labeled Data by Self-calibrating Classifier Guidance
di: Huang, Paul Kuo-Ming, et al.
Pubblicazione: (2023)

PEPL: Precision-Enhanced Pseudo-Labeling for Fine-Grained Image Classification in Semi-Supervised Learning
di: Tian, Bowen, et al.
Pubblicazione: (2024)

Graph Query Networks for Object Detection with Automotive Radar
di: Saini, Loveneet, et al.
Pubblicazione: (2025)

PC-BEV: An Efficient Polar-Cartesian BEV Fusion Framework for LiDAR Semantic Segmentation
di: Qiu, Shoumeng, et al.
Pubblicazione: (2024)

RESAR-BEV: An Explainable Progressive Residual Autoregressive Approach for Camera-Radar Fusion in BEV Segmentation
di: Zeng, Zhiwen, et al.
Pubblicazione: (2025)

A Semi-Supervised Framework for Breast Ultrasound Segmentation with Training-Free Pseudo-Label Generation and Label Refinement
di: Li, Ruili, et al.
Pubblicazione: (2026)

PP-SSL : Priority-Perception Self-Supervised Learning for Fine-Grained Recognition
di: Li, ShuaiHeng, et al.
Pubblicazione: (2024)

Geometry-Guided Self-Supervision for Ultra-Fine-Grained Recognition with Limited Data
di: Wang, Shijie, et al.
Pubblicazione: (2026)

Bayesian Self-Training for Semi-Supervised 3D Segmentation
di: Unal, Ozan, et al.
Pubblicazione: (2024)

Why Fine-grained Labels in Pretraining Benefit Generalization?
di: Hong, Guan Zhe, et al.
Pubblicazione: (2024)

FinePseudo: Improving Pseudo-Labelling through Temporal-Alignablity for Semi-Supervised Fine-Grained Action Recognition
di: Dave, Ishan Rajendrakumar, et al.
Pubblicazione: (2024)