Stochastic-depth-trained ResNets can skip many residual blocks at inference with small accuracy loss, and sensitivity-based selection of which blocks to skip enables zero-overhead adaptive inference.
Skipnet: Learning dynamic routing in convolutional networks,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Leveraging Stochastic Depth Training for Adaptive Inference
Stochastic-depth-trained ResNets can skip many residual blocks at inference with small accuracy loss, and sensitivity-based selection of which blocks to skip enables zero-overhead adaptive inference.