Cover Image

Scaling Backwards: Minimal Synthetic Pre-training?

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Nakamura, Ryo, Tadokoro, Ryu, Yamada, Ryosuke, Asano, Yuki M., Laina, Iro, Rupprecht, Christian, Inoue, Nakamasa, Yokota, Rio, Kataoka, Hirokatsu
Format:	Preprint
Published:	2024
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Rethinking Image Super-Resolution from Training Data Perspectives
by: Ohtani, Go, et al.
Published: (2024)

AnimalClue: Recognizing Animals by their Traces
by: Shinoda, Risa, et al.
Published: (2025)

Primitive Geometry Segment Pre-training for 3D Medical Image Segmentation
by: Tadokoro, Ryu, et al.
Published: (2024)

Formula-Supervised Visual-Geometric Pre-training
by: Yamada, Ryosuke, et al.
Published: (2024)

PowerCLIP: Powerset Alignment for Contrastive Pre-Training
by: Kawamura, Masaki, et al.
Published: (2025)

Pre-training Vision Transformers with Formula-driven Supervised Learning
by: Kataoka, Hirokatsu, et al.
Published: (2022)

On the Relationship Between Double Descent of CNNs and Shape/Texture Bias Under Learning Process
by: Iwase, Shun, et al.
Published: (2025)

Industrial Synthetic Segment Pre-training
by: Mae, Shinichi, et al.
Published: (2025)

Pre-training with 3D Synthetic Data: Learning 3D Point Cloud Instance Segmentation from 3D Synthetic Scenes
by: Otsuka, Daichi, et al.
Published: (2025)

S3OD: Towards Generalizable Salient Object Detection with Synthetic Data
by: Kupyn, Orest, et al.
Published: (2025)

Text-guided Synthetic Geometric Augmentation for Zero-shot 3D Understanding
by: Torimi, Kohei, et al.
Published: (2025)

3D sans 3D Scans: Scalable Pre-training from Video-Generated Point Clouds
by: Yamada, Ryousuke, et al.
Published: (2025)

AgroBench: Vision-Language Model Benchmark in Agriculture
by: Shinoda, Risa, et al.
Published: (2025)

Invisible Stitch: Generating Smooth 3D Scenes with Depth Inpainting
by: Engstler, Paul, et al.
Published: (2024)

Diffusion Models for Open-Vocabulary Segmentation
by: Karazija, Laurynas, et al.
Published: (2023)

Learning segmentation from point trajectories
by: Karazija, Laurynas, et al.
Published: (2025)

SynCity: Training-Free Generation of 3D Worlds
by: Engstler, Paul, et al.
Published: (2025)

MoireDB: Formula-generated Interference-fringe Image Dataset
by: Matsuo, Yuto, et al.
Published: (2025)

What Happens Next? Anticipating Future Motion by Generating Point Trajectories
by: Boduljak, Gabrijel, et al.
Published: (2025)

MoireMix: A Formula-Based Data Augmentation for Improving Image Classification Robustness
by: Matsuo, Yuto, et al.
Published: (2026)

Simple Visual Artifact Detection in Sora-Generated Videos
by: Sugiyama, Misora, et al.
Published: (2025)

Syn4D: A Multiview Synthetic 4D Dataset
by: Jiang, Zeren, et al.
Published: (2026)

DGE: Direct Gaussian 3D Editing by Consistent Multi-view Editing
by: Chen, Minghao, et al.
Published: (2024)

IM-3D: Iterative Multiview Diffusion and Reconstruction for High-Quality 3D Generation
by: Melas-Kyriazi, Luke, et al.
Published: (2024)

Exploring Limits of Diffusion-Synthetic Training with Weakly Supervised Semantic Segmentation
by: Yoshihashi, Ryota, et al.
Published: (2023)

Human Action Recognition without Human
by: Kataoka, Hirokatsu, et al.
Published: (2016)

Watermark-embedded Adversarial Examples for Copyright Protection against Diffusion Models
by: Zhu, Peifei, et al.
Published: (2024)

Layered Motion Fusion: Lifting Motion Segmentation to 3D in Egocentric Videos
by: Tschernezki, Vadim, et al.
Published: (2025)

VGGHeads: 3D Multi Head Alignment with a Large-Scale Synthetic Dataset
by: Kupyn, Orest, et al.
Published: (2024)

Reflect3r: Single-View 3D Stereo Reconstruction Aided by Mirror Reflections
by: Wu, Jing, et al.
Published: (2025)

Masked Gated Linear Unit
by: Tajima, Yukito, et al.
Published: (2025)

TRAVL: A Recipe for Making Video-Language Models Better Judges of Physics Implausibility
by: Motamed, Saman, et al.
Published: (2025)

Splatt3R: Zero-shot Gaussian Splatting from Uncalibrated Image Pairs
by: Smart, Brandon, et al.
Published: (2024)

Can masking background and object reduce static bias for zero-shot action recognition?
by: Fukuzawa, Takumi, et al.
Published: (2025)

Leveraging LLMs with Iterative Loop Structure for Enhanced Social Intelligence in Video Question Answering
by: Mori, Erika, et al.
Published: (2025)

Mesh4D: 4D Mesh Reconstruction and Tracking from Monocular Video
by: Jiang, Zeren, et al.
Published: (2026)

Pyramid Coder: Hierarchical Code Generator for Compositional Visual Question Answering
by: Shen, Ruoyue, et al.
Published: (2024)

STATUS Bench: A Rigorous Benchmark for Evaluating Object State Understanding in Vision-Language Models
by: Ukai, Mahiro, et al.
Published: (2025)

Geo4D: Leveraging Video Generators for Geometric 4D Scene Reconstruction
by: Jiang, Zeren, et al.
Published: (2025)

When Do Diffusion Models learn to Generate Multiple Objects?
by: Jeong, Yujin, et al.
Published: (2026)