Controlled benchmarks of nine lightweight CNNs find that newer architectures deliver selective rather than universal improvements in accuracy and efficiency under fixed training protocols.
Decoupled weight decay regularization
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
MicroBi-ConvLSTM is a convolutional-recurrent model with 11.4K parameters that delivers competitive accuracy on eight HAR benchmarks and full INT8 deployment coverage on Raspberry Pi Pico 2 and ESP32.
citing papers explorer
-
Do Newer Lightweight CNNs Perform Better Under Resource Constraints? A Controlled Multigenerational Study of Architecture, Initialization, Training Budget, and Efficiency
Controlled benchmarks of nine lightweight CNNs find that newer architectures deliver selective rather than universal improvements in accuracy and efficiency under fixed training protocols.
-
MicroBi-ConvLSTM: An Ultra-Lightweight Efficient Model for Human Activity Recognition on Resource Constrained Devices
MicroBi-ConvLSTM is a convolutional-recurrent model with 11.4K parameters that delivers competitive accuracy on eight HAR benchmarks and full INT8 deployment coverage on Raspberry Pi Pico 2 and ESP32.