Image de couverture de livre

$ε$-Softmax: Approximating One-Hot Vectors for Mitigating Label Noise

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Wang, Jialiang, Zhou, Xiong, Zhai, Deming, Jiang, Junjun, Ji, Xiangyang, Liu, Xianming
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Joint Asymmetric Loss for Learning with Noisy Labels
par: Wang, Jialiang, et autres
Publié: (2025)

Variation-Bounded Loss for Noise-Tolerant Learning
par: Wang, Jialiang, et autres
Publié: (2025)

Mesh Denoising Transformer
par: Zhao, Wenbo, et autres
Publié: (2024)

SGCNeRF: Few-Shot Neural Rendering via Sparse Geometric Consistency Guidance
par: Xiao, Yuru, et autres
Publié: (2024)

Learning Lossless Compression for High Bit-Depth Volumetric Medical Image
par: Wang, Kai, et autres
Publié: (2024)

Enhancing Consistency and Mitigating Bias: A Data Replay Approach for Incremental Learning
par: Wang, Chenyang, et autres
Publié: (2024)

Spatial Annealing for Efficient Few-shot Neural Rendering
par: Xiao, Yuru, et autres
Publié: (2024)

MCGS: Multiview Consistency Enhancement for Sparse-View 3D Gaussian Radiance Fields
par: Xiao, Yuru, et autres
Publié: (2024)

Mitigating Instance-Dependent Label Noise: Integrating Self-Supervised Pretraining with Pseudo-Label Refinement
par: Bala, Gouranga, et autres
Publié: (2024)

Rethinking Attention: Polynomial Alternatives to Softmax in Transformers
par: Saratchandran, Hemanth, et autres
Publié: (2024)

Boosting All-in-One Image Restoration via Self-Improved Privilege Learning
par: Wu, Gang, et autres
Publié: (2025)

Understanding and Mitigating the Label Noise in Pre-training on Downstream Tasks
par: Chen, Hao, et autres
Publié: (2023)

Unveiling the Depths: A Multi-Modal Fusion Framework for Challenging Scenarios
par: Xu, Jialei, et autres
Publié: (2024)

Coordinated Sparse Recovery of Label Noise
par: Yang, Yukun, et autres
Publié: (2024)

Beyond Degradation Redundancy: Contrastive Prompt Learning for All-in-One Image Restoration
par: Wu, Gang, et autres
Publié: (2025)

NLPrompt: Noise-Label Prompt Learning for Vision-Language Models
par: Pan, Bikang, et autres
Publié: (2024)

Pairing Regularization for Mitigating Many-to-One Collapse in GANs
par: Lin, Kuan-Yu, et autres
Publié: (2026)

One-Shot Heterogeneous Federated Learning with Local Model-Guided Diffusion Models
par: Yang, Mingzhao, et autres
Publié: (2023)

SelectMix: Enhancing Label Noise Robustness through Targeted Sample Mixing
par: Liu, Qiuhao, et autres
Publié: (2025)

Drifting Preference Optimization for One-Step Generative Models
par: Jiang, Zhou, et autres
Publié: (2026)

SoliReward: Mitigating Susceptibility to Reward Hacking and Annotation Noise in Video Generation Reward Models
par: Lian, Jiesong, et autres
Publié: (2025)

SSR: An Efficient and Robust Framework for Learning with Unknown Label Noise
par: Feng, Chen, et autres
Publié: (2021)

Compressing 3D Gaussian Splatting by Noise-Substituted Vector Quantization
par: Wang, Haishan, et autres
Publié: (2025)

Softmax-free Linear Transformers
par: Lu, Jiachen, et autres
Publié: (2022)

Mitigating Instance Entanglement in Instance-Dependent Partial Label Learning
par: Zhao, Rui, et autres
Publié: (2026)

Mitigating Noisy Supervision Using Synthetic Samples with Soft Labels
par: Lu, Yangdi, et autres
Publié: (2024)

Explorations of the Softmax Space: Knowing When the Neural Network Doesn't Know
par: Sikar, Daniel, et autres
Publié: (2025)

Active Label Refinement for Robust Training of Imbalanced Medical Image Classification Tasks in the Presence of High Label Noise
par: Khanal, Bidur, et autres
Publié: (2024)

SynFog: A Photo-realistic Synthetic Fog Dataset based on End-to-end Imaging Simulation for Advancing Real-World Defogging in Autonomous Driving
par: Xie, Yiming, et autres
Publié: (2024)

VDEGaussian: Video Diffusion Enhanced 4D Gaussian Splatting for Dynamic Urban Scenes Modeling
par: Xiao, Yuru, et autres
Publié: (2025)

Beyond Softmax: Dual-Branch Sigmoid Architecture for Accurate Class Activation Maps
par: Oh, Yoojin, et autres
Publié: (2025)

Learning to Calibrate for Reliable Visual Fire Detection
par: Zhang, Ziqi, et autres
Publié: (2025)

Noise-Adaptive Regularization for Robust Multi-Label Remote Sensing Image Classification
par: Burgert, Tom, et autres
Publié: (2026)

MIND: Decoupling Model-Induced Label Noise via Latent Manifold Disentanglement
par: Ren, Dayong
Publié: (2026)

Mitigating Label Noise using Prompt-Based Hyperbolic Meta-Learning in Open-Set Domain Generalization
par: Peng, Kunyu, et autres
Publié: (2024)

Learning from History: Task-agnostic Model Contrastive Learning for Image Restoration
par: Wu, Gang, et autres
Publié: (2023)

Analytical Softmax Temperature Setting from Feature Dimensions for Model- and Domain-Robust Classification
par: Hasegawa, Tatsuhito, et autres
Publié: (2025)

Towards Fairness under Label Bias in Image Segmentation: Impact, Measurement and Mitigation
par: Parikh, Aditya, et autres
Publié: (2026)

Cross-Validation Is All You Need: A Statistical Approach To Label Noise Estimation
par: Chen, Jianan, et autres
Publié: (2023)

A Survey on All-in-One Image Restoration: Taxonomy, Evaluation and Future Trends
par: Jiang, Junjun, et autres
Publié: (2024)