Cover Image

Towards Understanding Why Label Smoothing Degrades Selective Classification and How to Fix It

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Xia, Guoxuan, Laurent, Olivier, Franchi, Gianni, Bouganis, Christos-Savvas
Format:	Preprint
Published:	2024
Subjects:	Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Towards Understanding and Quantifying Uncertainty for Text-to-Image Generation
by: Franchi, Gianni, et al.
Published: (2024)

fpgaHART: A toolflow for throughput-oriented acceleration of 3D CNNs for HAR onto FPGAs
by: Toupas, Petros, et al.
Published: (2023)

FMM-X3D: FPGA-based modeling and mapping of X3D for Human Action Recognition
by: Toupas, Petros, et al.
Published: (2023)

Cached Multi-Lora Composition for Multi-Concept Image Generation
by: Zou, Xiandong, et al.
Published: (2025)

A Geometric Unification of Concept Learning with Concept Cones
by: Rocchi--Henry, Alexandre, et al.
Published: (2025)

Concept-Based Mechanistic Interpretability Using Structured Knowledge Graphs
by: Chorna, Sofiia, et al.
Published: (2025)

COOkeD: Ensemble-based OOD detection in the era of zero-shot CLIP
by: Humblot-Renaux, Galadrielle, et al.
Published: (2025)

NECO: NEural Collapse Based Out-of-distribution detection
by: Ammar, Mouïn Ben, et al.
Published: (2023)

SMOF: Streaming Modern CNNs on FPGAs with Smart Off-Chip Eviction
by: Toupas, Petros, et al.
Published: (2024)

Beyond Interpretability: When, Why, and How Sparse Autoencoders Enable Label-Free Visual Steering
by: Chatzoudis, Gerasimos, et al.
Published: (2025)

Bayesian Modeling of Zero-Shot Classifications for Urban Flood Detection
by: Franchi, Matt, et al.
Published: (2025)

MaxSup: Overcoming Representation Collapse in Label Smoothing
by: Zhou, Yuxuan, et al.
Published: (2025)

HARFLOW3D: A Latency-Oriented 3D-CNN Accelerator Toolflow for HAR on FPGA Devices
by: Toupas, Petros, et al.
Published: (2023)

Toward Efficient Convolutional Neural Networks With Structured Ternary Patterns
by: Kyrkou, Christos
Published: (2024)

Frustratingly Easy Test-Time Adaptation of Vision-Language Models
by: Farina, Matteo, et al.
Published: (2024)

Multi-Head Encoding for Extreme Label Classification
by: Liang, Daojun, et al.
Published: (2024)

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

Beyond Classification: Evaluating Diffusion Denoised Smoothing for Security-Utility Trade off
by: Belousov, Yury, et al.
Published: (2025)

Towards Precise Action Spotting: Addressing Temporal Misalignment in Labels with Dynamic Label Assignment
by: Tamura, Masato
Published: (2025)

Understanding and Mitigating Human-Labelling Errors in Supervised Contrastive Learning
by: Long, Zijun, et al.
Published: (2024)

Understanding and Mitigating the Label Noise in Pre-training on Downstream Tasks
by: Chen, Hao, et al.
Published: (2023)

Shiva-DiT: Residual-Based Differentiable Top-$k$ Selection for Efficient Diffusion Transformers
by: Zhang, Jiaji, et al.
Published: (2026)

Sample Selection via Contrastive Fragmentation for Noisy Label Regression
by: Kim, Chris Dongjoo, et al.
Published: (2025)

Deep Dependency Networks and Advanced Inference Schemes for Multi-Label Classification
by: Arya, Shivvrat, et al.
Published: (2024)

No Labels Needed: Zero-Shot Image Classification with Collaborative Self-Learning
by: Todescato, Matheus Vinícius, et al.
Published: (2025)

Selective Classification Under Distribution Shifts
by: Liang, Hengyue, et al.
Published: (2024)

Reproducibility Study of CDUL: CLIP-Driven Unsupervised Learning for Multi-Label Image Classification
by: Shah, Manan, et al.
Published: (2024)

Exploring What Why and How: A Multifaceted Benchmark for Causation Understanding of Video Anomaly
by: Du, Hang, et al.
Published: (2024)

Uncovering What, Why and How: A Comprehensive Benchmark for Causation Understanding of Video Anomaly
by: Du, Hang, et al.
Published: (2024)

Lost in the Hype: Revealing and Dissecting the Performance Degradation of Medical Multimodal Large Language Models in Image Classification
by: Zhu, Xun, et al.
Published: (2026)

FOCUS: Efficient Keyframe Selection for Long Video Understanding
by: Zhu, Zirui, et al.
Published: (2025)

Ordinal Adaptive Correction: A Data-Centric Approach to Ordinal Image Classification with Noisy Labels
by: Moghaddam, Alireza Sedighi, et al.
Published: (2025)

Hierarchical Randomized Smoothing
by: Scholten, Yan, et al.
Published: (2023)

Towards Sample-specific Backdoor Attack with Clean Labels via Attribute Trigger
by: Zhu, Mingyan, et al.
Published: (2023)

GNNRL-Smoothing: A Prior-Free Reinforcement Learning Model for Mesh Smoothing
by: Wang, Zhichao, et al.
Published: (2024)

Video Understanding by Design: How Datasets Shape Architectures and Insights
by: Wang, Lei, et al.
Published: (2025)

Towards Multi-dimensional Explanation Alignment for Medical Classification
by: Hu, Lijie, et al.
Published: (2024)

Towards Generalisable Time Series Understanding Across Domains
by: Turgut, Özgün, et al.
Published: (2024)

Fixed Point Diffusion Models
by: Bai, Xingjian, et al.
Published: (2024)

Clinically-Inspired Hierarchical Multi-Label Classification of Chest X-rays with a Penalty-Based Loss Function
by: Asadi, Mehrdad, et al.
Published: (2025)