Image de couverture de livre

On the Relationship Between Double Descent of CNNs and Shape/Texture Bias Under Learning Process

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Iwase, Shun, Takahashi, Shuya, Inoue, Nakamasa, Yokota, Rio, Nakamura, Ryo, Kataoka, Hirokatsu
Format:	Preprint
Publié:	2025
Sujets:	Computer Vision and Pattern Recognition Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

PowerCLIP: Powerset Alignment for Contrastive Pre-Training
par: Kawamura, Masaki, et autres
Publié: (2025)

Scaling Backwards: Minimal Synthetic Pre-training?
par: Nakamura, Ryo, et autres
Publié: (2024)

Formula-Supervised Visual-Geometric Pre-training
par: Yamada, Ryosuke, et autres
Publié: (2024)

Pre-training Vision Transformers with Formula-driven Supervised Learning
par: Kataoka, Hirokatsu, et autres
Publié: (2022)

AnimalClue: Recognizing Animals by their Traces
par: Shinoda, Risa, et autres
Publié: (2025)

AgroBench: Vision-Language Model Benchmark in Agriculture
par: Shinoda, Risa, et autres
Publié: (2025)

Rethinking Image Super-Resolution from Training Data Perspectives
par: Ohtani, Go, et autres
Publié: (2024)

MoireDB: Formula-generated Interference-fringe Image Dataset
par: Matsuo, Yuto, et autres
Publié: (2025)

Primitive Geometry Segment Pre-training for 3D Medical Image Segmentation
par: Tadokoro, Ryu, et autres
Publié: (2024)

Watermark-embedded Adversarial Examples for Copyright Protection against Diffusion Models
par: Zhu, Peifei, et autres
Publié: (2024)

Simple Visual Artifact Detection in Sora-Generated Videos
par: Sugiyama, Misora, et autres
Publié: (2025)

Industrial Synthetic Segment Pre-training
par: Mae, Shinichi, et autres
Publié: (2025)

S3OD: Towards Generalizable Salient Object Detection with Synthetic Data
par: Kupyn, Orest, et autres
Publié: (2025)

Human Action Recognition without Human
par: Kataoka, Hirokatsu, et autres
Publié: (2016)

Pre-training with 3D Synthetic Data: Learning 3D Point Cloud Instance Segmentation from 3D Synthetic Scenes
par: Otsuka, Daichi, et autres
Publié: (2025)

Can masking background and object reduce static bias for zero-shot action recognition?
par: Fukuzawa, Takumi, et autres
Publié: (2025)

Leveraging LLMs with Iterative Loop Structure for Enhanced Social Intelligence in Video Question Answering
par: Mori, Erika, et autres
Publié: (2025)

Clarifying Myths About the Relationship Between Shape Bias, Accuracy, and Robustness
par: Golpayegani, Zahra, et autres
Publié: (2024)

Pyramid Coder: Hierarchical Code Generator for Compositional Visual Question Answering
par: Shen, Ruoyue, et autres
Publié: (2024)

MoireMix: A Formula-Based Data Augmentation for Improving Image Classification Robustness
par: Matsuo, Yuto, et autres
Publié: (2026)

STATUS Bench: A Rigorous Benchmark for Evaluating Object State Understanding in Vision-Language Models
par: Ukai, Mahiro, et autres
Publié: (2025)

FDIF: Formula-Driven supervised Learning with Implicit Functions for 3D Medical Image Segmentation
par: Yamamoto, Yukinori, et autres
Publié: (2026)

Exploring Limits of Diffusion-Synthetic Training with Weakly Supervised Semantic Segmentation
par: Yoshihashi, Ryota, et autres
Publié: (2023)

HanDyVQA: A Video QA Benchmark for Fine-Grained Hand-Object Interaction Dynamics
par: Tateno, Masatoshi, et autres
Publié: (2025)

Promoting Shape Bias in CNNs: Frequency-Based and Contrastive Regularization for Corruption Robustness
par: Ranabhat, Robin Narsingh, et autres
Publié: (2025)

Constant Rate Scheduling: A General Framework for Optimizing Diffusion Noise Schedule via Distributional Change
par: Okada, Shuntaro, et autres
Publié: (2024)

Quantifying and Inducing Shape Bias in CNNs via Max-Pool Dilation
par: Sawada, Takito, et autres
Publié: (2026)

Multi-modal, Multi-task, Multi-criteria Automatic Evaluation with Vision Language Models
par: Ohi, Masanari, et autres
Publié: (2024)

Multi-Point Positional Insertion Tuning for Small Object Detection
par: Goto, Kanoko, et autres
Publié: (2024)

Referring Expression Comprehension for Small Objects
par: Goto, Kanoko, et autres
Publié: (2025)

On the Influence of Shape, Texture and Color for Learning Semantic Segmentation
par: Mütze, Annika, et autres
Publié: (2024)

Understanding the Double Descent Phenomenon in Deep Learning
par: Lafon, Marc, et autres
Publié: (2024)

From Correspondence to Actions: Human-Like Multi-Image Spatial Reasoning in Multi-modal Large Language Models
par: Oi, Masanari, et autres
Publié: (2026)

BioVITA: Biological Dataset, Model, and Benchmark for Visual-Textual-Acoustic Alignment
par: Shinoda, Risa, et autres
Publié: (2026)

Err on the Side of Texture: Texture Bias on Real Data
par: Hoak, Blaine, et autres
Publié: (2024)

AdaCoder: Adaptive Prompt Compression for Programmatic Visual Question Answering
par: Ukai, Mahiro, et autres
Publié: (2024)

3D sans 3D Scans: Scalable Pre-training from Video-Generated Point Clouds
par: Yamada, Ryousuke, et autres
Publié: (2025)

Text-guided Synthetic Geometric Augmentation for Zero-shot 3D Understanding
par: Torimi, Kohei, et autres
Publié: (2025)

Generalizable Neural Human Renderer
par: Masuda, Mana, et autres
Publié: (2024)

CLIP-like Model as a Foundational Density Ratio Estimator
par: Uchiyama, Fumiya, et autres
Publié: (2025)