Lightweight CNNs

CNN: Convolutional Neural Network

Overview

Lightweight CNN research seeks to retain useful accuracy while reducing parameters, computation, memory use, and inference time, especially on mobile and embedded hardware. Common approaches include depthwise-separable and grouped convolutions, compact encoder-decoder designs, pruning, quantization, knowledge distillation, and hardware-aware architecture search. These models are used for image classification, segmentation, restoration, and time-series tasks, with evaluation on both standard benchmarks and target devices. A central challenge is balancing accuracy and robustness with real deployment costs: fewer parameters or FLOPs do not always mean lower latency, and performance can drop when models meet varied data or hardware.

Latest papers

61 papers8 papers in the last four weeks, level with the four weeks before. 0.1% of all new papers.

Mar 6, 2023

Evolutionary Deep Nets for Non-Intrusive Load Monitoring

Compact appliance classifiers can support local electricity-load monitoring where memory and computation are constrained. We evaluate adaptive sparse evolutionary training and warm-start compression using synthetic aggregate windows derived from household appliance recordings. A completed convolutional network study trains 120 models over four targets and three seeds with validation-only model selection. Two analyses examine compression with approximately preserved binary accuracy and joint improvement in positive-class F1 and sparsity. Relative to a newly trained fixed sparse evolutionary baseline, the selected compressed policy changes accuracy from 91.53%, while increasing macro F1 to 92.40%. Stored weights decrease by 17.36% and active first-layer connections by 23.93%. Refinement requires additional training. Three seeds and unverified source-window independence prevent claims of statistical equivalence or unseen-house performance.