Imagen de Portada

ProDG: Prototypes for Data-Free Generative Post-Hoc Explainability

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Borycki, Piotr, Trędowicz, Magdalena, Tabor, Jacek, Struski, Łukasz, Spurek, Przemysław
Formato:	Preprint
Publicado:	2026
Materias:	Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

EPIC: Explanation of Pretrained Image Classification Networks via Prototype
por: Borycki, Piotr, et al.
Publicado: (2025)

GaMeS: Mesh-Based Adapting and Modification of Gaussian Splatting
por: Waczyńska, Joanna, et al.
Publicado: (2024)

Stop Marginalizing My Dreams: Model Inversion via Laplace Kernel for Continual Learning
por: Krukowski, Patryk, et al.
Publicado: (2026)

PrAViC: Probabilistic Adaptation Framework for Real-Time Video Classification
por: Trędowicz, Magdalena, et al.
Publicado: (2024)

InfoDisent: Explainability of Image Classification Models by Information Disentanglement
por: Struski, Łukasz, et al.
Publicado: (2024)

DIAMOND: Directed Inference for Artifact Mitigation in Flow Matching Models
por: Polowczyk, Alicja, et al.
Publicado: (2026)

ProtoSeg: Interpretable Semantic Segmentation with Prototypical Parts
por: Sacha, Mikołaj, et al.
Publicado: (2023)

GeoGuide: Geometric guidance of diffusion models
por: Poleski, Mateusz, et al.
Publicado: (2024)

SIDE: Sparse Information Disentanglement for Explainable Artificial Intelligence
por: Dubovik, Viktar, et al.
Publicado: (2025)

XSPLAIN: XAI-enabling Splat-based Prototype Learning for Attribute-aware INterpretability
por: Galus, Dominik, et al.
Publicado: (2026)

CEC-MMR: Cross-Entropy Clustering Approach to Multi-Modal Regression
por: Byrski, Krzysztof, et al.
Publicado: (2025)

SMAL-pets: SMAL Based Avatars of Pets from Single Image
por: Borycki, Piotr, et al.
Publicado: (2026)

D-MiSo: Editing Dynamic 3D Scenes using Multi-Gaussians Soup
por: Waczyńska, Joanna, et al.
Publicado: (2024)

SoftSAE: Dynamic Top-K Selection for Adaptive Sparse Autoencoders
por: Stępień, Jakub, et al.
Publicado: (2026)

ProMIL: Probabilistic Multiple Instance Learning for Medical Imaging
por: Struski, Łukasz, et al.
Publicado: (2023)

Conceptualizing Embeddings: Sparse Disentanglement for Vision-Language Models
por: Kubaty, Piotr, et al.
Publicado: (2026)

Deepfake for the Good: Generating Avatars through Face-Swapping with Implicit Deepfake Generation
por: Stanishevskii, Georgii, et al.
Publicado: (2024)

Classifier-free Guidance with Adaptive Scaling
por: Malarz, Dawid, et al.
Publicado: (2025)

Gaussian Splatting with NeRF-based Color and Opacity
por: Malarz, Dawid, et al.
Publicado: (2023)

GASP: Gaussian Splatting for Physic-Based Simulations
por: Borycki, Piotr, et al.
Publicado: (2024)

CLIPGaussian: Universal and Multimodal Style Transfer Based on Gaussian Splatting
por: Howil, Kornel, et al.
Publicado: (2025)

MiraGe: Editable 2D Images using Gaussian Splatting
por: Waczyńska, Joanna, et al.
Publicado: (2024)

GS-Verse: Mesh-based Gaussian Splatting for Physics-aware Interaction in Virtual Reality
por: Pechko, Anastasiya, et al.
Publicado: (2025)

REdiSplats: Ray Tracing for Editable Gaussian Splatting
por: Byrski, Krzysztof, et al.
Publicado: (2025)

HuSc3D: Human Sculpture dataset for 3D object reconstruction
por: Smolak-Dyżewska, Weronika, et al.
Publicado: (2025)

RaySplats: Ray Tracing based Gaussian Splatting
por: Byrski, Krzysztof, et al.
Publicado: (2025)

MultiPlaneNeRF: Neural Radiance Field with Non-Trainable Representation
por: Zimny, Dominik, et al.
Publicado: (2023)

UnGuide: Learning to Forget with LoRA-Guided Diffusion Models
por: Polowczyk, Agnieszka, et al.
Publicado: (2025)

AEGIS: Preserving privacy of 3D Facial Avatars with Adversarial Perturbations
por: Wolkiewicz, Dawid, et al.
Publicado: (2025)

UnHype: CLIP-Guided Hypernetworks for Dynamic LoRA Unlearning
por: Wójcik, Piotr, et al.
Publicado: (2026)

Points2NeRF: Generating Neural Radiance Fields from 3D point cloud
por: Zimny, Dominik, et al.
Publicado: (2022)

As Good as It KAN Get: High-Fidelity Audio Representation
por: Marszałek, Patryk, et al.
Publicado: (2025)

Mind the Gap: Geometrically Accurate Generative Reconstruction from Disjoint Views
por: Wilczynski, Grzegorz, et al.
Publicado: (2026)

From Unlearning to UNBRANDING: A Benchmark for Trademark-Safe Text-to-Image Generation
por: Malarz, Dawid, et al.
Publicado: (2025)

Bounding Evidence and Estimating Log-Likelihood in VAE
por: Struski, Łukasz, et al.
Publicado: (2022)

LucidPPN: Unambiguous Prototypical Parts Network for User-centric Interpretable Computer Vision
por: Pach, Mateusz, et al.
Publicado: (2024)

Pro-DG: Procedural Diffusion Guidance for Architectural Facade Generation
por: Plocharski, Aleksander, et al.
Publicado: (2025)

Discriminative Feature Attributions: Bridging Post Hoc Explainability and Inherent Interpretability
por: Bhalla, Usha, et al.
Publicado: (2023)

StyleAutoEncoder for manipulating image attributes using pre-trained StyleGAN
por: Bedychaj, Andrzej, et al.
Publicado: (2024)

PR-ENDO: Physically Based Relightable Gaussian Splatting for Endoscopy
por: Kaleta, Joanna, et al.
Publicado: (2024)