Copertina

SGD-Mix: Enhancing Domain-Specific Image Classification with Label-Preserving Data Augmentation

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Dong, Yixuan, Su, Fang-Yi, Chiang, Jung-Hsien
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computer Vision and Pattern Recognition Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Augmenting Prototype Network with TransMix for Few-shot Hyperspectral Image Classification
di: Liu, Chun, et al.
Pubblicazione: (2024)

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

Test-Time Mixup Augmentation for Data and Class-Specific Uncertainty Estimation in Deep Learning Image Classification
di: Lee, Hansang, et al.
Pubblicazione: (2022)

Diffusion Cocktail: Mixing Domain-Specific Diffusion Models for Diversified Image Generations
di: Liu, Haoming, et al.
Pubblicazione: (2023)

Decoupled Data Augmentation for Improving Image Classification
di: Chen, Ruoxin, et al.
Pubblicazione: (2024)

KeepOriginalAugment: Single Image-based Better Information-Preserving Data Augmentation Approach
di: Kumar, Teerath, et al.
Pubblicazione: (2024)

Free Performance Gain from Mixing Multiple Partially Labeled Samples in Multi-label Image Classification
di: Chong, Chak Fong, et al.
Pubblicazione: (2024)

Enhancing Whole Slide Image Classification through Supervised Contrastive Domain Adaptation
di: Carretero, Ilán, et al.
Pubblicazione: (2024)

Colorful Cutout: Enhancing Image Data Augmentation with Curriculum Learning
di: Choi, Juhwan, et al.
Pubblicazione: (2024)

HELM: Hierarchical and Explicit Label Modeling with Graph Learning for Multi-Label Image Classification
di: Stoimchev, Marjan, et al.
Pubblicazione: (2026)

Beyond One-Hot Labels: Semantic Mixing for Model Calibration
di: Luo, Haoyang, et al.
Pubblicazione: (2025)

Amnesia as a Catalyst for Enhancing Black Box Pixel Attacks in Image Classification and Object Detection
di: Song, Dongsu, et al.
Pubblicazione: (2025)

Domain-Specific Pre-training Improves Confidence in Whole Slide Image Classification
di: Chitnis, Soham Rohit, et al.
Pubblicazione: (2023)

The Effects of Mixed Sample Data Augmentation are Class Dependent
di: Lee, Haeil, et al.
Pubblicazione: (2023)

L3A: Label-Augmented Analytic Adaptation for Multi-Label Class Incremental Learning
di: Zhang, Xiang, et al.
Pubblicazione: (2025)

Deep Learning-Based Image Recognition for Soft-Shell Shrimp Classification
di: Zhang, Yun-Hao, et al.
Pubblicazione: (2026)

Domain Adaptation for Image Classification of Defects in Semiconductor Manufacturing
di: Poniatowski, Adrian, et al.
Pubblicazione: (2025)

Label-Augmented Dataset Distillation
di: Kang, Seoungyoon, et al.
Pubblicazione: (2024)

General vs Domain-Specific CNNs: Understanding Pretraining Effects on Brain MRI Tumor Classification
di: Abedini, Helia, et al.
Pubblicazione: (2025)

Enhancing the Utility of Privacy-Preserving Cancer Classification using Synthetic Data
di: Osuala, Richard, et al.
Pubblicazione: (2024)

TSynD: Targeted Synthetic Data Generation for Enhanced Medical Image Classification
di: Niemeijer, Joshua, et al.
Pubblicazione: (2024)

Semi-supervised Medical Image Segmentation Method Based on Cross-pseudo Labeling Leveraging Strong and Weak Data Augmentation Strategies
di: Chen, Yifei, et al.
Pubblicazione: (2024)

HistoSmith: Single-Stage Histology Image-Label Generation via Conditional Latent Diffusion for Enhanced Cell Segmentation and Classification
di: Vadori, Valentina, et al.
Pubblicazione: (2025)

Every Image Listens, Every Image Dances: Music-Driven Image Animation
di: Dong, Zhikang, et al.
Pubblicazione: (2025)

Contrastive-Based Deep Embeddings for Label Noise-Resilient Histopathology Image Classification
di: Dedieu, Lucas, et al.
Pubblicazione: (2024)

Topology-Preserving Polygon Augmentation for Segmentation in Structured Visual Domains
di: Laudari, Sudip, et al.
Pubblicazione: (2026)

VizECGNet: Visual ECG Image Network for Cardiovascular Diseases Classification with Multi-Modal Training and Knowledge Distillation
di: Nam, Ju-Hyeon, et al.
Pubblicazione: (2024)

Preserve or Modify? Context-Aware Evaluation for Balancing Preservation and Modification in Text-Guided Image Editing
di: Kim, Yoonjeon, et al.
Pubblicazione: (2024)

FairDomain: Achieving Fairness in Cross-Domain Medical Image Segmentation and Classification
di: Tian, Yu, et al.
Pubblicazione: (2024)

Label-Efficient Data Augmentation with Video Diffusion Models for Guidewire Segmentation in Cardiac Fluoroscopy
di: Pan, Shaoyan, et al.
Pubblicazione: (2024)

Multi-Label Scene Classification in Remote Sensing Benefits from Image Super-Resolution
di: Mudraje, Ashitha, et al.
Pubblicazione: (2025)

Superpixelwise Low-rank Approximation based Partial Label Learning for Hyperspectral Image Classification
di: Yang, Shujun, et al.
Pubblicazione: (2024)

Case-Aware Medical Image Classification with Multimodal Knowledge Graphs and Reliability-Guided Refinement
di: Xu, Yiming, et al.
Pubblicazione: (2026)

Exploring Beyond Logits: Hierarchical Dynamic Labeling Based on Embeddings for Semi-Supervised Classification
di: Ma, Yanbiao, et al.
Pubblicazione: (2024)

Enhancing Source-Free Domain Adaptive Object Detection with Low-confidence Pseudo Label Distillation
di: Yoon, Ilhoon, et al.
Pubblicazione: (2024)

DCSCR: A Class-Specific Collaborative Representation based Network for Image Set Classification
di: Gao, Xizhan, et al.
Pubblicazione: (2025)

Zero-Training Task-Specific Model Synthesis for Few-Shot Medical Image Classification
di: Qin, Yao, et al.
Pubblicazione: (2025)

Differential Privacy Image Generation with Reconstruction Loss and Noise Injection Using an Error Feedback SGD
di: Ma, Qiwei, et al.
Pubblicazione: (2026)

Ali-AUG: Innovative Approaches to Labeled Data Augmentation using One-Step Diffusion Model
di: Hamza, Ali, et al.
Pubblicazione: (2024)

Label Semantics for Robust Hyperspectral Image Classification
di: Hassan, Rafin, et al.
Pubblicazione: (2025)