Image de couverture de livre

MaxSup: Overcoming Representation Collapse in Label Smoothing

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Zhou, Yuxuan, Li, Heng, Cheng, Zhi-Qi, Yan, Xudong, Dong, Yifei, Fritz, Mario, Keuper, Margret
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning Artificial Intelligence 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

Deepfakes: we need to re-think the concept of "real" images
par: Keuper, Janis, et autres
Publié: (2025)

Local Spherical Harmonics Improve Skeleton-Based Hand Action Recognition
par: Prasse, Katharina, et autres
Publié: (2023)

As large as it gets: Learning infinitely large Filters via Neural Implicit Functions in the Fourier Domain
par: Grabinski, Julia, et autres
Publié: (2023)

Unfolding Local Growth Rate Estimates for (Almost) Perfect Adversarial Detection
par: Lorenz, Peter, et autres
Publié: (2022)

Overcoming Topology Agnosticism: Enhancing Skeleton-Based Action Recognition through Redefined Skeletal Topology Awareness
par: Zhou, Yuxuan, et autres
Publié: (2023)

Know Yourself Better: Diverse Object-Related Features Improve Open Set Recognition
par: Xu, Jiawen, et autres
Publié: (2024)

Is RobustBench/AutoAttack a suitable Benchmark for Adversarial Robustness?
par: Lorenz, Peter, et autres
Publié: (2021)

Examining the Impact of Optical Aberrations to Image Classification and Object Detection Models
par: Müller, Patrick, et autres
Publié: (2025)

Corner Cases: How Size and Position of Objects Challenge ImageNet-Trained Models
par: Fatima, Mishal, et autres
Publié: (2025)

CosPGD: an efficient white-box adversarial attack for pixel-wise prediction tasks
par: Agnihotri, Shashank, et autres
Publié: (2023)

Improving Feature Stability during Upsampling -- Spectral Artifacts and the Importance of Spatial Context
par: Agnihotri, Shashank, et autres
Publié: (2023)

CROC: Evaluating and Training T2I Metrics with Pseudo- and Human-Labeled Contrastive Robustness Checks
par: Leiter, Christoph, et autres
Publié: (2025)

Fix your downsampling ASAP! Be natively more robust via Aliasing and Spectral Artifact free Pooling
par: Grabinski, Julia, et autres
Publié: (2023)

Images as Tables: In-Context Learning with TabPFN for Low-Data Detection of AI-Generated Images
par: Walter, Jan Philip, et autres
Publié: (2026)

How Do Training Methods Influence the Utilization of Vision Models?
par: Gavrikov, Paul, et autres
Publié: (2024)

Detecting AutoAttack Perturbations in the Frequency Domain
par: Lorenz, Peter, et autres
Publié: (2021)

TRIX- Trading Adversarial Fairness via Mixed Adversarial Training
par: Medi, Tejaswini, et autres
Publié: (2025)

Towards Class-wise Robustness Analysis
par: Medi, Tejaswini, et autres
Publié: (2024)

Smart Eyes for Silent Threats: VLMs and In-Context Learning for THz Imaging
par: Poggi, Nicolas, et autres
Publié: (2025)

Faithful, Interpretable Chest X-ray Diagnosis with Anti-Aliased B-cos Networks
par: Kleinmann, Marcel, et autres
Publié: (2025)

FAIR-TAT: Improving Model Fairness Using Targeted Adversarial Training
par: Medi, Tejaswini, et autres
Publié: (2024)

Informed Mixing -- Improving Open Set Recognition via Attribution-based Augmentation
par: Xu, Jiawen, et autres
Publié: (2025)

Beware of Aliases -- Signal Preservation is Crucial for Robust Image Restoration
par: Agnihotri, Shashank, et autres
Publié: (2024)

I Spy With My Little Eye: A Minimum Cost Multicut Investigation of Dataset Frames
par: Prasse, Katharina, et autres
Publié: (2024)

AIM: Amending Inherent Interpretability via Self-Supervised Masking
par: Alshami, Eyad, et autres
Publié: (2025)

Human-Aware Vision-and-Language Navigation: Bridging Simulation to Reality with Dynamic Human Interactions
par: Li, Heng, et autres
Publié: (2024)

PLReMix: Combating Noisy Labels with Pseudo-Label Relaxed Contrastive Representation Learning
par: Liu, Xiaoyu, et autres
Publié: (2024)

Vision At Night: Exploring Biologically Inspired Preprocessing For Improved Robustness Via Color And Contrast Transformations
par: Stracke, Lorena, et autres
Publié: (2025)

DCBM: Data-Efficient Visual Concept Bottleneck Models
par: Prasse, Katharina, et autres
Publié: (2024)

Adaptive Label Smoothing for Out-of-Distribution Detection
par: Xu, Mingle, et autres
Publié: (2024)

MultiMax: Sparse and Multi-Modal Attention Learning
par: Zhou, Yuxuan, et autres
Publié: (2024)

Semantic-Aware Representation Learning via Conditional Transport for Multi-Label Image Classification
par: Xie, Ren-Dong, et autres
Publié: (2025)

HA-VLN 2.0: An Open Benchmark and Leaderboard for Human-Aware Navigation in Discrete and Continuous Environments with Dynamic Multi-Human Interactions
par: Dong, Yifei, et autres
Publié: (2025)

Feature-Space Smoothing: Certified Robustness of Deep Representations
par: Xia, Song, et autres
Publié: (2026)

RAWDet-7: A Multi-Scenario Benchmark for Object Detection and Description on Quantized RAW Images
par: Fatima, Mishal, et autres
Publié: (2026)

Are Synthetic Corruptions A Reliable Proxy For Real-World Corruptions?
par: Agnihotri, Shashank, et autres
Publié: (2025)

3D-WAG: Hierarchical Wavelet-Guided Autoregressive Generation for High-Fidelity 3D Shapes
par: Medi, Tejaswini, et autres
Publié: (2024)

GeoDiv: Framework For Measuring Geographical Diversity In Text-To-Image Models
par: Basu, Abhipsa, et autres
Publié: (2026)

MixSup: Mixed-grained Supervision for Label-efficient LiDAR-based 3D Object Detection
par: Yang, Yuxue, et autres
Publié: (2024)

Missing Fine Details in Images: Last Seen in High Frequencies
par: Medi, Tejaswini, et autres
Publié: (2025)