Image de couverture de livre

Double-Exponential Increases in Inference Energy: The Cost of the Race for Accuracy

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Yang, Zeyu, Adamek, Karel, Armour, Wesley
Format:	Preprint
Publié:	2024
Sujets:	Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Adaptive Illumination-Invariant Synergistic Feature Integration in a Stratified Granular Framework for Visible-Infrared Re-Identification
par: Jia, Yuheng, et autres
Publié: (2025)

Part-time Power Measurements: nvidia-smi's Lack of Attention
par: Yang, Zeyu, et autres
Publié: (2023)

Second-Order Multi-Level Variance Correction for Modality Competition in Multimodal Models
par: Lu, Yishun, et autres
Publié: (2026)

OCCAM: Towards Cost-Efficient and Accuracy-Aware Classification Inference
par: Ding, Dujian, et autres
Publié: (2024)

DCVSMNet: Double Cost Volume Stereo Matching Network
par: Tahmasebi, Mahmoud, et autres
Publié: (2024)

Towards Energy-Efficiency by Navigating the Trilemma of Energy, Latency, and Accuracy
par: Tian, Boyuan, et autres
Publié: (2024)

Using Deep Learning to Increase Eye-Tracking Robustness, Accuracy, and Precision in Virtual Reality
par: Barkevich, Kevin, et autres
Publié: (2024)

Training Image Derivatives: Increased Accuracy and Universal Robustness
par: Avrutskiy, Vsevolod I.
Publié: (2023)

Double Visual Defense: Adversarial Pre-training and Instruction Tuning for Improving Vision-Language Model Robustness
par: Wang, Zeyu, et autres
Publié: (2025)

Token Compensator: Altering Inference Cost of Vision Transformer without Re-Tuning
par: Jie, Shibo, et autres
Publié: (2024)

Path-Adaptive Matting for Efficient Inference Under Various Computational Cost Constraints
par: Liu, Qinglin, et autres
Publié: (2025)

CAIT: Triple-Win Compression towards High Accuracy, Fast Inference, and Favorable Transferability For ViTs
par: Wang, Ao, et autres
Publié: (2023)

Spiking GS: Towards High-Accuracy and Low-Cost Surface Reconstruction via Spiking Neuron-based Gaussian Splatting
par: Zhang, Weixing, et autres
Publié: (2024)

JDCNet: Confidence-Gated Privileged-Modality Distillation for Cost-Preserving X-ray Inference
par: Ma, Bo, et autres
Publié: (2026)

Toward using GANs in astrophysical Monte-Carlo simulations
par: Isaac, Ahab, et autres
Publié: (2024)

Distribution of the Högbom CLEAN Algorithm Using Tiled Images with Feedback
par: Wright, Daniel, et autres
Publié: (2024)

CLEAN algorithm implementation comparisons between popular software packages
par: Wright, Daniel, et autres
Publié: (2024)

Minimizing Energy Costs in Deep Learning Model Training: The Gaussian Sampling Approach
par: Revanth, Challapalli Phanindra, et autres
Publié: (2024)

FusionForce: End-to-end Differentiable Neural-Symbolic Layer for Trajectory Prediction
par: Agishev, Ruslan, et autres
Publié: (2025)

TextBite: A Historical Czech Document Dataset for Logical Page Segmentation
par: Kostelník, Martin, et autres
Publié: (2025)

DemaFormer: Damped Exponential Moving Average Transformer with Energy-Based Modeling for Temporal Language Grounding
par: Nguyen, Thong, et autres
Publié: (2023)

Point-based Instance Completion with Scene Constraints
par: Khademi, Wesley, et autres
Publié: (2025)

Training and Inference within 1 Second -- Tackle Cross-Sensor Degradation of Real-World Pansharpening with Efficient Residual Feature Tailoring
par: Xin, Tianyu, et autres
Publié: (2025)

Training-Free and Interpretable Hateful Video Detection via Multi-stage Adversarial Reasoning
par: Yang, Shuonan, et autres
Publié: (2026)

LightFusion: A Light-weighted, Double Fusion Framework for Unified Multimodal Understanding and Generation
par: Wang, Zeyu, et autres
Publié: (2025)

VisTA-SR: Improving the Accuracy and Resolution of Low-Cost Thermal Imaging Cameras for Agriculture
par: Yun, Heesup, et autres
Publié: (2024)

MatE: Material Extraction from Single-Image via Geometric Prior
par: Zhang, Zeyu, et autres
Publié: (2025)

Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian Splatting
par: Yang, Zeyu, et autres
Publié: (2023)

Increasing Rosacea Awareness Among Population Using Deep Learning and Statistical Approaches
par: Yang, Chengyu, et autres
Publié: (2024)

Beyond the Mud: Datasets and Benchmarks for Computer Vision in Off-Road Racing
par: Tyo, Jacob, et autres
Publié: (2024)

Visual Cues of Gender and Race are Associated with Stereotyping in Vision-Language Models
par: Lee, Messi H. J., et autres
Publié: (2025)

Steering Prediction via a Multi-Sensor System for Autonomous Racing
par: Zhou, Zhuyun, et autres
Publié: (2024)

GS-Cache: A GS-Cache Inference Framework for Large-scale Gaussian Splatting Models
par: Tao, Miao, et autres
Publié: (2025)

StrengthSense: A Dataset of IMU Signals Capturing Everyday Strength-Demanding Activities
par: Yang, Zeyu, et autres
Publié: (2025)

Beyond Full Labels: Energy-Double-Guided Single-Point Prompt for Infrared Small Target Label Generation
par: Yuan, Shuai, et autres
Publié: (2024)

CHURRO: Making History Readable with an Open-Weight Large Vision-Language Model for High-Accuracy, Low-Cost Historical Text Recognition
par: Semnani, Sina J., et autres
Publié: (2025)

Let-It-Flow: Simultaneous Optimization of 3D Flow and Object Clustering
par: Vacek, Patrik, et autres
Publié: (2024)

A Race Bias Free Face Aging Model for Reliable Kinship Verification
par: Nazari, Ali, et autres
Publié: (2025)

Linking Perception, Confidence and Accuracy in MLLMs
par: Du, Yuetian, et autres
Publié: (2026)

HexFormer: Hyperbolic Vision Transformer with Exponential Map Aggregation
par: Alyoussef, Haya, et autres
Publié: (2026)