Imagen de Portada

Role of Locality and Weight Sharing in Image-Based Tasks: A Sample Complexity Separation between CNNs, LCNs, and FCNs

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Lahoti, Aakash, Karp, Stefani, Winston, Ezra, Singh, Aarti, Li, Yuanzhi
Formato:	Preprint
Publicado:	2024
Materias:	Machine Learning Artificial Intelligence 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

Detection Limits and Statistical Separability of Tree Ring Watermarks in Rectified Flow-based Text-to-Image Generation Models
por: Umrajkar, Ved, et al.
Publicado: (2025)

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

MRI Volume-Based Robust Brain Age Estimation Using Weight-Shared Spatial Attention in 3D CNNs
por: Kancharla, Vamshi Krishna, et al.
Publicado: (2024)

Pixels to Prose: Understanding the art of Image Captioning
por: Singh, Hrishikesh, et al.
Publicado: (2024)

A Hybrid Transformer-Sequencer approach for Age and Gender classification from in-wild facial images
por: Singh, Aakash, et al.
Publicado: (2024)

Synthesizer Based Efficient Self-Attention for Vision Tasks
por: Zhu, Guangyang, et al.
Publicado: (2022)

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

SpatialLock: Precise Spatial Control in Text-to-Image Synthesis
por: Liu, Biao, et al.
Publicado: (2025)

Regularizing CNNs using Confusion Penalty Based Label Smoothing for Histopathology Images
por: Kuiry, Somenath, et al.
Publicado: (2024)

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

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

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

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

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

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

SeaS: Few-shot Industrial Anomaly Image Generation with Separation and Sharing Fine-tuning
por: Dai, Zhewei, et al.
Publicado: (2024)

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

Rethinking Where to Edit: Task-Aware Localization for Instruction-Based Image Editing
por: He, Jingxuan, et al.
Publicado: (2026)

From CNNs to Shift-Invariant Twin Models Based on Complex Wavelets
por: Leterme, Hubert, et al.
Publicado: (2022)

Systematic Integration of Attention Modules into CNNs for Accurate and Generalizable Medical Image Diagnosis
por: Ullah, Zahid, et al.
Publicado: (2025)

ACM-UNet: Adaptive Integration of CNNs and Mamba for Efficient Medical Image Segmentation
por: Huang, Jing, et al.
Publicado: (2025)

SceneFunRI: Reasoning the Invisible for Task-Driven Functional Object Localization
por: Chen, Posheng, et al.
Publicado: (2026)

VistaFormer: Scalable Vision Transformers for Satellite Image Time Series Segmentation
por: MacDonald, Ezra, et al.
Publicado: (2024)

Efficient CNNs via Passive Filter Pruning
por: Singh, Arshdeep, et al.
Publicado: (2023)

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

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

Neural Bloom: A Deep Learning Approach to Real-Time Lighting
por: Karp, Rafal, et al.
Publicado: (2025)

Seeing Beyond Redundancy: Task Complexity's Role in Vision Token Specialization in VLLMs
por: Hannan, Darryl, et al.
Publicado: (2026)

Underwater Image Restoration via Polymorphic Large Kernel CNNs
por: Guo, Xiaojiao, et al.
Publicado: (2024)

Complexity Experts are Task-Discriminative Learners for Any Image Restoration
por: Zamfir, Eduard, et al.
Publicado: (2024)

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

Breaking Shallow Limits: Task-Driven Pixel Fusion for Gap-free RGBT Tracking
por: Lu, Andong, et al.
Publicado: (2025)

Polar Separable Transform for Efficient Orthogonal Rotation-Invariant Image Representation
por: Singh, Satya P., et al.
Publicado: (2025)

Uncertainty-Aware Dual-Student Knowledge Distillation for Efficient Image Classification
por: Gore, Aakash, et al.
Publicado: (2025)

Geo-Localization Based on Dynamically Weighted Factor-Graph
por: Muñoz-Bañón, Miguel Ángel, et al.
Publicado: (2023)

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

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

A Novel State Space Model with Local Enhancement and State Sharing for Image Fusion
por: Cao, Zihan, et al.
Publicado: (2024)

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

Understanding CNNs from excitations
por: Ying, Zijian, et al.
Publicado: (2022)