Copertina

What do CNNs Learn in the First Layer and Why? A Linear Systems Perspective

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Chowers, Rhea, Weiss, Yair
Natura:	Preprint
Pubblicazione:	2022
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Is the Modality Gap a Bug or a Feature? A Robustness Perspective
di: Chowers, Rhea, et al.
Pubblicazione: (2026)

Control+Shift: Generating Controllable Distribution Shifts
di: Friedman, Roy, et al.
Pubblicazione: (2024)

Lost in Translation: Modern Neural Networks Still Struggle With Small Realistic Image Transformations
di: Shifman, Ofir, et al.
Pubblicazione: (2024)

Revising the Problem of Partial Labels from the Perspective of CNNs' Robustness
di: Zhang, Xin, et al.
Pubblicazione: (2024)

Intriguing Properties of Modern GANs
di: Friedman, Roy, et al.
Pubblicazione: (2024)

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

OA-CNNs: Omni-Adaptive Sparse CNNs for 3D Semantic Segmentation
di: Peng, Bohao, et al.
Pubblicazione: (2024)

CAM Back Again: Large Kernel CNNs from a Weakly Supervised Object Localization Perspective
di: Yasuki, Shunsuke, et al.
Pubblicazione: (2024)

Robust Experts: the Effect of Adversarial Training on CNNs with Sparse Mixture-of-Experts Layers
di: Pavlitska, Svetlana, et al.
Pubblicazione: (2025)

Lightweight Channel Attention for Efficient CNNs
di: Kanaparthi, Prem Babu, et al.
Pubblicazione: (2026)

Bioinspired CNNs for border completion in occluded images
di: Coutinho, Catarina P., et al.
Pubblicazione: (2026)

CNNs for Style Transfer of Digital to Film Photography
di: Mackenzie, Pierre, et al.
Pubblicazione: (2024)

Parameter-Efficient Architectural Modifications for Translation-Invariant CNNs
di: Alabau-Bosque, Nuria, et al.
Pubblicazione: (2026)

Assessing the Alignment of Popular CNNs to the Brain for Valence Appraisal
di: Mertens, Laurent, et al.
Pubblicazione: (2025)

The Quest for Universal Master Key Filters in DS-CNNs
di: Babaiee, Zahra, et al.
Pubblicazione: (2025)

Automatic Complementary Separation Pruning Toward Lightweight CNNs
di: Levin, David, et al.
Pubblicazione: (2025)

Partial Large Kernel CNNs for Efficient Super-Resolution
di: Lee, Dongheon, et al.
Pubblicazione: (2024)

Understanding and Improving CNNs with Complex Structure Tensor: A Biometrics Study
di: Hernandez-Diaz, Kevin, et al.
Pubblicazione: (2024)

Deep Network Pruning: A Comparative Study on CNNs in Face Recognition
di: Alonso-Fernandez, Fernando, et al.
Pubblicazione: (2024)

Where, What, Why: Towards Explainable Driver Attention Prediction
di: Zhou, Yuchen, et al.
Pubblicazione: (2025)

Mixture of Mini Experts: Overcoming the Linear Layer Bottleneck in Multiple Instance Learning
di: Shao, Daniel, et al.
Pubblicazione: (2026)

B-cos Alignment for Inherently Interpretable CNNs and Vision Transformers
di: Böhle, Moritz, et al.
Pubblicazione: (2023)

Investigating and unmasking feature-level vulnerabilities of CNNs to adversarial perturbations
di: Coppola, Davide, et al.
Pubblicazione: (2024)

Joint Point Cloud Upsampling and Cleaning with Octree-based CNNs
di: Li, Jihe, et al.
Pubblicazione: (2024)

Designing Extremely Memory-Efficient CNNs for On-device Vision Tasks
di: Lee, Jaewook, et al.
Pubblicazione: (2024)

Investigating Market Strength Prediction with CNNs on Candlestick Chart Images
di: Duong, Thanh Nam, et al.
Pubblicazione: (2025)

Exploring Synergistic Ensemble Learning: Uniting CNNs, MLP-Mixers, and Vision Transformers to Enhance Image Classification
di: Bashar, Mk, et al.
Pubblicazione: (2025)

Where, What, Why: Toward Explainable 3D-GS Watermarking
di: Cai, Mingshu, et al.
Pubblicazione: (2026)

Understanding CNNs from excitations
di: Ying, Zijian, et al.
Pubblicazione: (2022)

On the universality of neural encodings in CNNs
di: Guth, Florentin, et al.
Pubblicazione: (2024)

Adapting CNNs for Fisheye Cameras without Retraining
di: Griffiths, Ryan, et al.
Pubblicazione: (2024)

Demystify Mamba in Vision: A Linear Attention Perspective
di: Han, Dongchen, et al.
Pubblicazione: (2024)

Comparing the Decision-Making Mechanisms by Transformers and CNNs via Explanation Methods
di: Jiang, Mingqi, et al.
Pubblicazione: (2022)

Data-Agnostic Face Image Synthesis Detection Using Bayesian CNNs
di: Leyva, Roberto, et al.
Pubblicazione: (2024)

Jointly Training and Pruning CNNs via Learnable Agent Guidance and Alignment
di: Ganjdanesh, Alireza, et al.
Pubblicazione: (2024)

Exploring Complementarity and Explainability in CNNs for Periocular Verification Across Acquisition Distances
di: Alonso-Fernandez, Fernando, et al.
Pubblicazione: (2025)

CNNs, Transformers, Hybrid, and Vision Language Models for Skin Cancer Detection
di: Dey, Durjoy, et al.
Pubblicazione: (2026)

EgoIntent: An Egocentric Step-level Benchmark for Understanding What, Why, and Next
di: Pan, Ye, et al.
Pubblicazione: (2026)

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

Post-hoc Self-explanation of CNNs
di: Boubekki, Ahcène, et al.
Pubblicazione: (2026)