Copertina

For Better or For Worse? Learning Minimum Variance Features With Label Augmentation

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Chidambaram, Muthu, Ge, Rong
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Machine Learning Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Provably Learning Diverse Features in Multi-View Data with Midpoint Mixup
di: Chidambaram, Muthu, et al.
Pubblicazione: (2022)

When Worse is Better: Navigating the compression-generation tradeoff in visual tokenization
di: Ramanujan, Vivek, et al.
Pubblicazione: (2024)

What does guidance do? A fine-grained analysis in a simple setting
di: Chidambaram, Muthu, et al.
Pubblicazione: (2024)

Cross-Class Feature Augmentation for Class Incremental Learning
di: Kim, Taehoon, et al.
Pubblicazione: (2023)

Learning from Memory: Non-Parametric Memory Augmented Self-Supervised Learning of Visual Features
di: Silva, Thalles, et al.
Pubblicazione: (2024)

Combined Image Data Augmentations diminish the benefits of Adaptive Label Smoothing
di: Siedel, Georg, et al.
Pubblicazione: (2025)

Know Yourself Better: Diverse Object-Related Features Improve Open Set Recognition
di: Xu, Jiawen, et al.
Pubblicazione: (2024)

From Variance to Veracity: Unbundling and Mitigating Gradient Variance in Differentiable Bundle Adjustment Layers
di: Gurumurthy, Swaminathan, et al.
Pubblicazione: (2024)

SeA: Semantic Adversarial Augmentation for Last Layer Features from Unsupervised Representation Learning
di: Qian, Qi, et al.
Pubblicazione: (2024)

FG-OrIU: Towards Better Forgetting via Feature-Gradient Orthogonality for Incremental Unlearning
di: Feng, Qian, et al.
Pubblicazione: (2026)

Reassessing How to Compare and Improve the Calibration of Machine Learning Models
di: Chidambaram, Muthu, et al.
Pubblicazione: (2024)

Federated Learning with Label-Masking Distillation
di: Lu, Jianghu, et al.
Pubblicazione: (2024)

Pseudo-labelling meets Label Smoothing for Noisy Partial Label Learning
di: Saravanan, Darshana, et al.
Pubblicazione: (2024)

FREE: Faster and Better Data-Free Meta-Learning
di: Wei, Yongxian, et al.
Pubblicazione: (2024)

Dens-PU: PU Learning with Density-Based Positive Labeled Augmentation
di: Sevetlidis, Vasileios, et al.
Pubblicazione: (2023)

FAGC:Feature Augmentation on Geodesic Curve in the Pre-Shape Space
di: Han, Yuexing, et al.
Pubblicazione: (2023)

Estimating Noisy Class Posterior with Part-level Labels for Noisy Label Learning
di: Zhao, Rui, et al.
Pubblicazione: (2024)

Taming Cross-Domain Representation Variance in Federated Prototype Learning with Heterogeneous Data Domains
di: Wang, Lei, et al.
Pubblicazione: (2024)

BadLabel: A Robust Perspective on Evaluating and Enhancing Label-noise Learning
di: Zhang, Jingfeng, et al.
Pubblicazione: (2023)

Uncertainty-Aware Global-View Reconstruction for Multi-View Multi-Label Feature Selection
di: Hao, Pingting, et al.
Pubblicazione: (2025)

Configuring Data Augmentations to Reduce Variance Shift in Positional Embedding of Vision Transformers
di: Kim, Bum Jun, et al.
Pubblicazione: (2024)

Exploring Transformer-Augmented LSTM for Temporal and Spatial Feature Learning in Trajectory Prediction
di: Raskoti, Chandra, et al.
Pubblicazione: (2024)

Switch EMA: A Free Lunch for Better Flatness and Sharpness
di: Li, Siyuan, et al.
Pubblicazione: (2024)

Views Can Be Deceiving: Improved SSL Through Feature Space Augmentation
di: Hamidieh, Kimia, et al.
Pubblicazione: (2024)

Provably Better Explanations with Optimized Aggregation of Feature Attributions
di: Decker, Thomas, et al.
Pubblicazione: (2024)

Intra-Cluster Mixup: An Effective Data Augmentation Technique for Complementary-Label Learning
di: Mai, Tan-Ha, et al.
Pubblicazione: (2025)

Augmenting Ground-Level PM2.5 Prediction via Kriging-Based Pseudo-Label Generation
di: Duan, Lei, et al.
Pubblicazione: (2024)

Progressive Alignment with VLM-LLM Feature to Augment Defect Classification for the ASE Dataset
di: Hsu, Chih-Chung, et al.
Pubblicazione: (2024)

GNFactor: Multi-Task Real Robot Learning with Generalizable Neural Feature Fields
di: Ze, Yanjie, et al.
Pubblicazione: (2023)

Better, Not Just More: Data-Centric Machine Learning for Earth Observation
di: Roscher, Ribana, et al.
Pubblicazione: (2023)

FAAGC: Feature Augmentation on Adaptive Geodesic Curve Based on the shape space theory
di: Han, Yuexing, et al.
Pubblicazione: (2025)

Counting Network for Learning from Majority Label
di: Shiku, Kaito, et al.
Pubblicazione: (2024)

Foster Adaptivity and Balance in Learning with Noisy Labels
di: Sheng, Mengmeng, et al.
Pubblicazione: (2024)

Federated Learning with Instance-Dependent Noisy Label
di: Wang, Lei, et al.
Pubblicazione: (2023)

Joint Asymmetric Loss for Learning with Noisy Labels
di: Wang, Jialiang, et al.
Pubblicazione: (2025)

On the Limitations of Temperature Scaling for Distributions with Overlaps
di: Chidambaram, Muthu, et al.
Pubblicazione: (2023)

Deep Learning for Multi-Label Learning: A Comprehensive Survey
di: Tarekegn, Adane Nega, et al.
Pubblicazione: (2024)

MILD: Modeling the Instance Learning Dynamics for Learning with Noisy Labels
di: Hu, Chuanyang, et al.
Pubblicazione: (2023)

Variance-Aware Adaptive Weighting for Diffusion Model Training
di: Sun, Nanlong, et al.
Pubblicazione: (2026)

Variance-Based Defense Against Blended Backdoor Attacks
di: Aseervatham, Sujeevan, et al.
Pubblicazione: (2025)