SGAD: Soft-Guided Adaptively-Dropped Neural Network
Deep neural networks (DNNs) have been proven to have many redundancies. Hence, many efforts have been made to compress DNNs. However, the existing model compression methods treat all the input samples equally while ignoring the fact that the difficulties of various input samples being correctly classified are different. To address this problem, DNNs with adaptive dropping mechanism are well explored in this work. To inform the DNNs how difficult the input samples can be classified, a guideline that contains the information of input samples is introduced to improve the performance. Based on the developed guideline and adaptive dropping mechanism, an innovative soft-guided adaptively-dropped (SGAD) neural network is proposed in this paper. Compared with the 32 layers residual neural networks, the presented SGAD can reduce the FLOPs by 77% with less than 1% drop in accuracy on CIFAR-10.
Code (0)
등록된 구현이 없습니다.
Tasks
Model CompressionSimilar Papers 제목 키워드 기반
Q-GADMM: Quantized Group ADMM for Communication Efficient Decentralized Machine Learning
In this article, we propose a communication-efficient decentralized machine learning (ML) algorithm, coined quantized group ADMM (Q-GADMM). To reduce the number of communication links, every worker in Q-GADMM communicate…
BIG-bench Machine Learningimage-classificationImage ClassificationQuantizationAn Exploratory Study on Human-Centric Video Anomaly Detection through Variational Autoencoders and Trajectory Prediction
Video Anomaly Detection (VAD) represents a challenging and prominent research task within computer vision. In recent years, Pose-based Video Anomaly Detection (PAD) has drawn considerable attention from the research comm…
Anomaly DetectionTrajectory PredictionVideo Anomaly DetectionSGAD: Semantic and Geometric-aware Descriptor for Local Feature Matching
Local feature matching remains a fundamental challenge in computer vision. Recent Area to Point Matching (A2PM) methods have improved matching accuracy. However, existing research based on this framework relies on ineffi…
Pose EstimationGraph MatchingAltitude-Dependent Cellular Spectrum Occupancy: from Measurements to Stochastic Geometry Models
The growing demand for aerial connectivity with unmanned aerial vehicles (UAVs) across diverse settings, ranging from urban to rural scenarios, requires developing a better understanding of spectrum occupancy at aerial c…
CRC-SGAD: Conformal Risk Control for Supervised Graph Anomaly Detection
Graph Anomaly Detection (GAD) is critical in security-sensitive domains, yet faces reliability challenges: miscalibrated confidence estimation (underconfidence in normal nodes, overconfidence in anomalies), adversarial v…
Anomaly DetectionGraph Anomaly DetectionPrediction