Copertina

Beyond Top Activations: Efficient and Reliable Crowdsourced Evaluation of Automated Interpretability

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Oikarinen, Tuomas, Yan, Ge, Kulkarni, Akshay, Weng, Tsui-Wei
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computer Vision and Pattern Recognition Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Interpretable Generative Models through Post-hoc Concept Bottlenecks
di: Kulkarni, Akshay, et al.
Pubblicazione: (2025)

Interpreting Neurons in Deep Vision Networks with Language Models
di: Bai, Nicholas, et al.
Pubblicazione: (2024)

Linear Explanations for Individual Neurons
di: Oikarinen, Tuomas, et al.
Pubblicazione: (2024)

CI-CBM: Class-Incremental Concept Bottleneck Model for Interpretable Continual Learning
di: Javadi, Amirhosein, et al.
Pubblicazione: (2026)

Interpretability-Guided Test-Time Adversarial Defense
di: Kulkarni, Akshay, et al.
Pubblicazione: (2024)

Interpretable and Steerable Concept Bottleneck Sparse Autoencoders
di: Kulkarni, Akshay, et al.
Pubblicazione: (2025)

RAT: Boosting Misclassification Detection Ability without Extra Data
di: Yan, Ge, et al.
Pubblicazione: (2025)

VLG-CBM: Training Concept Bottleneck Models with Vision-Language Guidance
di: Srivastava, Divyansh, et al.
Pubblicazione: (2024)

Faithful and Stable Neuron Explanations for Trustworthy Mechanistic Interpretability
di: Yan, Ge, et al.
Pubblicazione: (2025)

Evaluating Neuron Explanations: A Unified Framework with Sanity Checks
di: Oikarinen, Tuomas, et al.
Pubblicazione: (2025)

Provably Robust Conformal Prediction with Improved Efficiency
di: Yan, Ge, et al.
Pubblicazione: (2024)

Crafting Large Language Models for Enhanced Interpretability
di: Sun, Chung-En, et al.
Pubblicazione: (2024)

LatentDiff: Scaling Semantic Dataset Comparison to Millions of Images
di: Flora, James, et al.
Pubblicazione: (2026)

CrossFuse: Learning Infrared and Visible Image Fusion by Cross-Sensor Top-K Vision Alignment and Beyond
di: Shi, Yukai, et al.
Pubblicazione: (2025)

Semi-Self Representation Learning for Crowdsourced WiFi Trajectories
di: Kuo, Yu-Lin, et al.
Pubblicazione: (2025)

Mixture-of-Top-k Attention: Efficient Attention via Scalable Fast Weights
di: Wen, Qishuai, et al.
Pubblicazione: (2026)

CF-CAM: Cluster Filter Class Activation Mapping for Reliable Gradient-Based Interpretability
di: He, Hongjie, et al.
Pubblicazione: (2025)

Assessing the Noise Robustness of Class Activation Maps: A Framework for Reliable Model Interpretability
di: Sarkar, Syamantak, et al.
Pubblicazione: (2025)

Enabling Fast and Accurate Crowdsourced Annotation for Elevation-Aware Flood Extent Mapping
di: Dyken, Landon, et al.
Pubblicazione: (2024)

Concept Bottleneck Large Language Models
di: Sun, Chung-En, et al.
Pubblicazione: (2024)

DRIMV_TSK: An Interpretable Surgical Evaluation Model for Incomplete Multi-View Rectal Cancer Data
di: Zhang, Wei, et al.
Pubblicazione: (2025)

VidModEx: Interpretable and Efficient Black Box Model Extraction for High-Dimensional Spaces
di: Kumar, Somnath Sendhil, et al.
Pubblicazione: (2024)

CRACKS: Crowdsourcing Resources for Analysis and Categorization of Key Subsurface faults
di: Prabhushankar, Mohit, et al.
Pubblicazione: (2024)

Automated Model Evaluation for Object Detection via Prediction Consistency and Reliability
di: Yoo, Seungju, et al.
Pubblicazione: (2025)

SemSegBench & DetecBench: Benchmarking Reliability and Generalization Beyond Classification
di: Agnihotri, Shashank, et al.
Pubblicazione: (2025)

Hierarchical Invariance for Robust and Interpretable Vision Tasks at Larger Scales
di: Qi, Shuren, et al.
Pubblicazione: (2024)

FedStyle: Style-Based Federated Learning Crowdsourcing Framework for Art Commissions
di: Ran, Changjuan, et al.
Pubblicazione: (2024)

LiDAR-based Object Detection with Real-time Voice Specifications
di: Kulkarni, Anurag
Pubblicazione: (2025)

IGenBench: Benchmarking the Reliability of Text-to-Infographic Generation
di: Tang, Yinghao, et al.
Pubblicazione: (2026)

Beyond Binary Success: A Diagnostic Meta-Evaluation Framework for Fine-Grained Manipulation
di: Xu, He-Yang, et al.
Pubblicazione: (2026)

Patronus: Interpretable Diffusion Models with Prototypes
di: Weng, Nina, et al.
Pubblicazione: (2025)

EPAS: Efficient Training with Progressive Activation Sharing
di: Karim, Rezaul, et al.
Pubblicazione: (2026)

Orchid: Image Latent Diffusion for Joint Appearance and Geometry Generation
di: Krishnan, Akshay, et al.
Pubblicazione: (2025)

Cyclic Vision-Language Manipulator: Towards Reliable and Fine-Grained Image Interpretation for Automated Report Generation
di: Fang, Yingying, et al.
Pubblicazione: (2024)

Beyond Softmax: Dual-Branch Sigmoid Architecture for Accurate Class Activation Maps
di: Oh, Yoojin, et al.
Pubblicazione: (2025)

FLIP: Towards Comprehensive and Reliable Evaluation of Federated Prompt Learning
di: Liao, Dongping, et al.
Pubblicazione: (2025)

Incorporating Crowdsourced Annotator Distributions into Ensemble Modeling to Improve Classification Trustworthiness for Ancient Greek Papyri
di: West, Graham, et al.
Pubblicazione: (2022)

Probabilistic Precision and Recall Towards Reliable Evaluation of Generative Models
di: Park, Dogyun, et al.
Pubblicazione: (2023)

An Interpretable Evaluation of Entropy-based Novelty of Generative Models
di: Zhang, Jingwei, et al.
Pubblicazione: (2024)

Towards Reliable Evaluation and Fast Training of Robust Semantic Segmentation Models
di: Croce, Francesco, et al.
Pubblicazione: (2023)