AI RESEARCH

CalexNet: Soft Cascade-Aligned Training and Calibration for Lightweight Early-Exit Branches

arXiv CS.CV

ArXi:2509.08318v2 Announce Type: replace Early-exit cascades over a frozen convolutional backbone enable adaptive inference but suffer from three sources of train-inference mismatch: branches train on samples they will never see at inference, their per-class precision thresholds are calibrated on the wrong distribution, and the standard cross-entropy target on backbone argmax labels discards the backbone's uncertainty signal. We close all three gaps with CalexNet (Cascade-Aligned Early eXits), a.