Copertina

An accuracy-aware extension to LRP-based pruning for CNNs to prevent cascading accuracy degradation in data-scarce transfer learning

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Yasui, Daisuke, Matsuki, Toshitaka, Sato, Hiroshi
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Uncovering Latent Phase Structures and Branching Logic in Locomotion Policies: A Case Study on HalfCheetah
di: Yasui, Daisuke, et al.
Pubblicazione: (2026)

EVO-LRP: Evolutionary Optimization of LRP for Interpretable Model Explanations
di: Zhang, Emerald, et al.
Pubblicazione: (2025)

PAS: Estimating the target accuracy before domain adaptation
di: Diniz, Raphaella, et al.
Pubblicazione: (2026)

Visualizing Latent Phase Structures in Locomotion Policies: A Multi-Environment Study with Temporal Feature Extension
di: Yasui, Daisuke, et al.
Pubblicazione: (2026)

Breaking the accuracy-resource dilemma: a lightweight adaptive video inference enhancement
di: Ma, Wei, et al.
Pubblicazione: (2026)

One-shot synthesis of rare gastrointestinal lesions improves diagnostic accuracy and clinical training
di: Yu, Jia, et al.
Pubblicazione: (2025)

Analysis of human visual field information using machine learning methods and assessment of their accuracy
di: Medvedeva, A. I., et al.
Pubblicazione: (2025)

Precise classification of low quality G-banded Chromosome Images by reliability metrics and data pruning classifier
di: Moattari, Mojtaba
Pubblicazione: (2025)

Automated Image Captioning with CNNs and Transformers
di: Cahyono, Joshua Adrian, et al.
Pubblicazione: (2024)

NeuFlow: Real-time, High-accuracy Optical Flow Estimation on Robots Using Edge Devices
di: Zhang, Zhiyong, et al.
Pubblicazione: (2024)

PQ-DAF: Pose-driven Quality-controlled Data Augmentation for Data-scarce Driver Distraction Detection
di: Sun, Haibin, et al.
Pubblicazione: (2025)

Less is More: The Influence of Pruning on the Explainability of CNNs
di: Merkle, Florian, et al.
Pubblicazione: (2023)

Hidden flaws behind expert-level accuracy of multimodal GPT-4 vision in medicine
di: Jin, Qiao, et al.
Pubblicazione: (2024)

Facial beauty prediction fusing transfer learning and broad learning system
di: Gan, Junying, et al.
Pubblicazione: (2026)

Integrative CAM: Adaptive Layer Fusion for Comprehensive Interpretation of CNNs
di: Singh, Aniket K., et al.
Pubblicazione: (2024)

Enhancing CNNs robustness to occlusions with bioinspired filters for border completion
di: Coutinho, Catarina P., et al.
Pubblicazione: (2025)

Deep transfer learning for image classification: a survey
di: Plested, Jo, et al.
Pubblicazione: (2022)

Structure-aware Contrastive Learning for Diagram Understanding of Multimodal Models
di: Sasaki, Hiroshi
Pubblicazione: (2025)

Distill-then-prune: An Efficient Compression Framework for Real-time Stereo Matching Network on Edge Devices
di: Pan, Baiyu, et al.
Pubblicazione: (2024)

Minimal Sufficient Views: A DNN model making predictions with more evidence has higher accuracy
di: Kawano, Keisuke, et al.
Pubblicazione: (2024)

Reliable or Deceptive? Investigating Gated Features for Smooth Visual Explanations in CNNs
di: Mitra, Soham, et al.
Pubblicazione: (2024)

Evaluating the Impact of Compression Techniques on the Robustness of CNNs under Natural Corruptions
di: Da Silva, Itallo Patrick Castro Alves, et al.
Pubblicazione: (2025)

An efficient plant disease detection using transfer learning approach
di: Sambana, Bosubabu, et al.
Pubblicazione: (2025)

Dermatologist-like explainable AI enhances melanoma diagnosis accuracy: eye-tracking study
di: Chanda, Tirtha, et al.
Pubblicazione: (2024)

Sauron U-Net: Simple automated redundancy elimination in medical image segmentation via filter pruning
di: Valverde, Juan Miguel, et al.
Pubblicazione: (2022)

Towards Optimal Trade-offs in Knowledge Distillation for CNNs and Vision Transformers at the Edge
di: Violos, John, et al.
Pubblicazione: (2024)

Multi-Head Explainer: A General Framework to Improve Explainability in CNNs and Transformers
di: Sun, Bohang, et al.
Pubblicazione: (2025)

Promoting Shape Bias in CNNs: Frequency-Based and Contrastive Regularization for Corruption Robustness
di: Ranabhat, Robin Narsingh, et al.
Pubblicazione: (2025)

Xeno-learning: knowledge transfer across species in deep learning-based spectral image analysis
di: Sellner, Jan, et al.
Pubblicazione: (2024)

Efficient Hyperparameter Importance Assessment for CNNs
di: Wang, Ruinan, et al.
Pubblicazione: (2024)

Vehicle Classification under Extreme Imbalance: A Comparative Study of Ensemble Learning and CNNs
di: Syarubany, Abu Hanif Muhammad
Pubblicazione: (2025)

The Effective Depth Paradox: Evaluating the Relationship between Architectural Topology and Trainability in Deep CNNs
di: Fischer, Manfred M., et al.
Pubblicazione: (2026)

Top-GAP: Integrating Size Priors in CNNs for more Interpretability, Robustness, and Bias Mitigation
di: Nieradzik, Lars, et al.
Pubblicazione: (2024)

Advancing Green AI: Efficient and Accurate Lightweight CNNs for Rice Leaf Disease Identification
di: Saddami, Khairun, et al.
Pubblicazione: (2024)

When CNNs Outperform Transformers and Mambas: Revisiting Deep Architectures for Dental Caries Segmentation
di: Ghimire, Aashish, et al.
Pubblicazione: (2025)

Taking it further: leveraging pseudo labels for field delineation across label-scarce smallholder regions
di: Rufin, Philippe, et al.
Pubblicazione: (2023)

AttnLRP: Attention-Aware Layer-Wise Relevance Propagation for Transformers
di: Achtibat, Reduan, et al.
Pubblicazione: (2024)

General vs Domain-Specific CNNs: Understanding Pretraining Effects on Brain MRI Tumor Classification
di: Abedini, Helia, et al.
Pubblicazione: (2025)

CNNs Avoid Curse of Dimensionality by Learning on Patches
di: Madala, Vamshi C., et al.
Pubblicazione: (2022)

Explaning with trees: interpreting CNNs using hierarchies
di: Rodrigues, Caroline Mazini, et al.
Pubblicazione: (2024)