Imagen de Portada

DEX: Data Channel Extension for Efficient CNN Inference on Tiny AI Accelerators

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Gong, Taesik, Kawsar, Fahim, Min, Chulhong
Formato:	Preprint
Publicado:	2024
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Synergy: Towards On-Body AI via Tiny AI Accelerator Collaboration on Wearables
por: Gong, Taesik, et al.
Publicado: (2023)

Time-bound Contextual Bio-ID Generation for Minimalist Wearables
por: Orzikulova, Adiba, et al.
Publicado: (2024)

Salted Inference: Enhancing Privacy while Maintaining Efficiency of Split Inference in Mobile Computing
por: Malekzadeh, Mohammad, et al.
Publicado: (2023)

AdaBet: Gradient-free Layer Selection for Efficient Training of Deep Neural Networks
por: Tenison, Irene, et al.
Publicado: (2025)

An AI-Native Runtime for Multi-Wearable Environments
por: Min, Chulhong, et al.
Publicado: (2024)

Enhancing Efficiency in Multidevice Federated Learning through Data Selection
por: Mo, Fan, et al.
Publicado: (2022)

Accelerating TinyML Inference on Microcontrollers through Approximate Kernels
por: Armeniakos, Giorgos, et al.
Publicado: (2024)

Enabling Cross-Camera Collaboration for Video Analytics on Distributed Smart Cameras
por: Min, Chulhong, et al.
Publicado: (2024)

PaPaGei: Open Foundation Models for Optical Physiological Signals
por: Pillai, Arvind, et al.
Publicado: (2024)

Revealing CNN Architectures via Side-Channel Analysis in Dataflow-based Inference Accelerators
por: Weerasena, Hansika, et al.
Publicado: (2023)

Evaluating Fairness in Self-supervised and Supervised Models for Sequential Data
por: Yfantidou, Sofia, et al.
Publicado: (2024)

PRIMUS: Pretraining IMU Encoders with Multimodal Self-Supervision
por: Das, Arnav M., et al.
Publicado: (2024)

A Hybrid Edge Classifier: Combining TinyML-Optimised CNN with RRAM-CMOS ACAM for Energy-Efficient Inference
por: Woodward, Kieran, et al.
Publicado: (2025)

AI Should Sense Better, Not Just Scale Bigger: Adaptive Sensing as a Paradigm Shift
por: Baek, Eunsu, et al.
Publicado: (2025)

(Un)fair devices: Moving beyond AI accuracy in personal sensing
por: Yfantidou, Sofia, et al.
Publicado: (2023)

Using Self-supervised Learning Can Improve Model Fairness
por: Yfantidou, Sofia, et al.
Publicado: (2024)

CroSSL: Cross-modal Self-Supervised Learning for Time-series through Latent Masking
por: Deldari, Shohreh, et al.
Publicado: (2023)

From Volume to Value: Preference-Aligned Memory Construction for On-Device RAG
por: Lee, Changmin, et al.
Publicado: (2026)

SNAP: Low-Latency Test-Time Adaptation with Sparse Updates
por: Cha, Hyeongheon, et al.
Publicado: (2025)

CLEF: Clinically-Guided Contrastive Learning for Electrocardiogram Foundation Models
por: Shu, Yuxuan, et al.
Publicado: (2025)

MicroFlow: An Efficient Rust-Based Inference Engine for TinyML
por: Carnelos, Matteo, et al.
Publicado: (2024)

Kaizen: Practical Self-supervised Continual Learning with Continual Fine-tuning
por: Tang, Chi Ian, et al.
Publicado: (2023)

Energy-Efficient Power Control for Multiple-Task Split Inference in UAVs: A Tiny Learning-Based Approach
por: Zhao, Chenxi, et al.
Publicado: (2023)

AdaNODEs: Test Time Adaptation for Time Series Forecasting Using Neural ODEs
por: Dang, Ting, et al.
Publicado: (2026)

Contrastive Self-Supervised Learning at the Edge: An Energy Perspective
por: Famá, Fernanda, et al.
Publicado: (2025)

TinyFormer: Efficient Transformer Design and Deployment on Tiny Devices
por: Yang, Jianlei, et al.
Publicado: (2023)

Characterizing and Efficiently Accelerating Multimodal Generation Model Inference
por: Lee, Yejin, et al.
Publicado: (2024)

Balancing Continual Learning and Fine-tuning for Human Activity Recognition
por: Tang, Chi Ian, et al.
Publicado: (2024)

Once-for-All Channel Mixers (HYPERTINYPW): Generative Compression for TinyML
por: Shaalan, Yassien
Publicado: (2026)

msf-CNN: Patch-based Multi-Stage Fusion with Convolutional Neural Networks for TinyML
por: Huang, Zhaolan, et al.
Publicado: (2025)

Data-Rate-Aware High-Speed CNN Inference on FPGAs
por: Habermann, Tobias, et al.
Publicado: (2026)

Slim Scheduler: A Runtime-Aware RL and Scheduler System for Efficient CNN Inference
por: Harshbarger, Ian, et al.
Publicado: (2025)

LLM-Inference-Bench: Inference Benchmarking of Large Language Models on AI Accelerators
por: Chitty-Venkata, Krishna Teja, et al.
Publicado: (2024)

Prototyping an End-to-End Multi-Modal Tiny-CNN for Cardiovascular Sensor Patches
por: Ibrahim, Mustafa Fuad Rifet, et al.
Publicado: (2025)

Efficient and Verifiable Privacy-Preserving Convolutional Computation for CNN Inference with Untrusted Clouds
por: Lu, Jinyu, et al.
Publicado: (2025)

TinyGraphEstimator: Adapting Lightweight Language Models for Graph Structure Inference
por: Podstawski, Michal
Publicado: (2025)

Inference Optimization of Foundation Models on AI Accelerators
por: Park, Youngsuk, et al.
Publicado: (2024)

Continuous-Flow Data-Rate-Aware CNN Inference on FPGA
por: Habermann, Tobias, et al.
Publicado: (2026)

AETTA: Label-Free Accuracy Estimation for Test-Time Adaptation
por: Lee, Taeckyung, et al.
Publicado: (2024)

Fully Autonomous Z-Score-Based TinyML Anomaly Detection on Resource-Constrained MCUs Using Power Side-Channel Data
por: Albaiz, Abdulrahman, et al.
Publicado: (2026)