Copertina

Rethinking Evaluation Paradigms in IBP-based Certified Training

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Kaulen, Konstantin, Shavit, Hadar, Hoos, Holger H.
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Rethinking the Evaluation Protocol of Domain Generalization
di: Yu, Han, et al.
Pubblicazione: (2023)

LipShiFT: A Certifiably Robust Shift-based Vision Transformer
di: Menon, Rohan, et al.
Pubblicazione: (2025)

Rethinking Robustness: A New Approach to Evaluating Feature Attribution Methods
di: Kiourti, Panagiota, et al.
Pubblicazione: (2025)

Pixel-level Certified Explanations via Randomized Smoothing
di: Anani, Alaa, et al.
Pubblicazione: (2025)

Rethinking Training Dynamics in Scale-wise Autoregressive Generation
di: Zhou, Gengze, et al.
Pubblicazione: (2025)

Rethinking Saliency Maps: A Cognitive Human Aligned Taxonomy and Evaluation Framework for Explanations
di: Elisha, Yehonatan, et al.
Pubblicazione: (2025)

Examining Common Paradigms in Multi-Task Learning
di: Elich, Cathrin, et al.
Pubblicazione: (2023)

How to Train your Text-to-Image Model: Evaluating Design Choices for Synthetic Training Captions
di: Brack, Manuel, et al.
Pubblicazione: (2025)

Field Matching: an Electrostatic Paradigm to Generate and Transfer Data
di: Kolesov, Alexander, et al.
Pubblicazione: (2025)

Training with Explanations Alone: A New Paradigm to Prevent Shortcut Learning
di: Bassi, Pedro R. A. S., et al.
Pubblicazione: (2024)

Rethinking VLMs and LLMs for Image Classification
di: Cooper, Avi, et al.
Pubblicazione: (2024)

Rethinking Diffusion Model in High Dimension
di: Zheng, Zhenxin, et al.
Pubblicazione: (2025)

Efficiently Integrate Large Language Models with Visual Perception: A Survey from the Training Paradigm Perspective
di: Ma, Xiaorui, et al.
Pubblicazione: (2025)

Divide and Conquer: Rethinking the Training Paradigm of Neural Radiance Fields
di: Ma, Rongkai, et al.
Pubblicazione: (2024)

MTCNET: Multi-task Learning Paradigm for Crowd Count Estimation
di: Kumar, Abhay, et al.
Pubblicazione: (2019)

On the Diversity and Realism of Distilled Dataset: An Efficient Dataset Distillation Paradigm
di: Sun, Peng, et al.
Pubblicazione: (2023)

KernelWarehouse: Rethinking the Design of Dynamic Convolution
di: Li, Chao, et al.
Pubblicazione: (2024)

Rethinking The Uniformity Metric in Self-Supervised Learning
di: Fang, Xianghong, et al.
Pubblicazione: (2024)

A Training Rate and Survival Heuristic for Inference and Robustness Evaluation (TRASHFIRE)
di: Meyers, Charles, et al.
Pubblicazione: (2024)

Rethinking the Diffusion Model from a Langevin Perspective
di: Zheng, Candi, et al.
Pubblicazione: (2026)

Quality Assured: Rethinking Annotation Strategies in Imaging AI
di: Rädsch, Tim, et al.
Pubblicazione: (2024)

Learning Private Representations through Entropy-based Adversarial Training
di: Klein, Tassilo, et al.
Pubblicazione: (2025)

VQGraph: Rethinking Graph Representation Space for Bridging GNNs and MLPs
di: Yang, Ling, et al.
Pubblicazione: (2023)

Rethinking Semi-supervised Segmentation Beyond Accuracy: Reliability and Robustness
di: Landgraf, Steven, et al.
Pubblicazione: (2025)

Rethinking Post-Unlearning Behavior of Large Vision-Language Models
di: Kim, Minsung, et al.
Pubblicazione: (2025)

Rethinking Multi-domain Generalization with A General Learning Objective
di: Tan, Zhaorui, et al.
Pubblicazione: (2024)

A Hard-to-Beat Baseline for Training-free CLIP-based Adaptation
di: Wang, Zhengbo, et al.
Pubblicazione: (2024)

Perceptual Quality-based Model Training under Annotator Label Uncertainty
di: Zhou, Chen, et al.
Pubblicazione: (2024)

Foundations of a Developmental Design Paradigm for Integrated Continual Learning, Deliberative Behavior, and Comprehensibility
di: Erden, Zeki Doruk, et al.
Pubblicazione: (2025)

Quanvolutional Neural Networks for Pneumonia Detection: An Efficient Quantum-Assisted Feature Extraction Paradigm
di: Tanbhir, Gazi, et al.
Pubblicazione: (2025)

Improving Object Detection Performance through YOLOv8: A Comprehensive Training and Evaluation Study
di: Poureskandar, Rana, et al.
Pubblicazione: (2025)

Not All Splits Are Equal: Rethinking Attribute Generalization Across Unrelated Categories
di: Fircă, Liviu Nicolae, et al.
Pubblicazione: (2025)

LSAP: Rethinking Inversion Fidelity, Perception and Editability in GAN Latent Space
di: Zhao, Xuekun, et al.
Pubblicazione: (2022)

Rethinking Metrics and Diffusion Architecture for 3D Point Cloud Generation
di: Bastico, Matteo, et al.
Pubblicazione: (2025)

Rethinking cluster-conditioned diffusion models for label-free image synthesis
di: Adaloglou, Nikolas, et al.
Pubblicazione: (2024)

Fill the GAP: A Granular Alignment Paradigm for Visual Reasoning in Multimodal Large Language Models
di: Miao, Yanting, et al.
Pubblicazione: (2026)

Text-to-CadQuery: A New Paradigm for CAD Generation with Scalable Large Model Capabilities
di: Xie, Haoyang, et al.
Pubblicazione: (2025)

Mission Critical -- Satellite Data is a Distinct Modality in Machine Learning
di: Rolf, Esther, et al.
Pubblicazione: (2024)

Rethinking Temporal Consistency in Video Object-Centric Learning: From Prediction to Correspondence
di: Li, Zhiyuan, et al.
Pubblicazione: (2026)

MoEIoU: Rethinking Bounding-Box Regression as a Mixture of Experts
di: Edula, Vinay, et al.
Pubblicazione: (2026)