Skip to main content
Search

# Angular Coordinate Interface

1 related articles

Subscribe to updates
  1. arXiv

    Swapping the student classifier for angular coordinates: ACD lifts homogeneous distillation by 2.51 points and heterogeneous pairs by 4.19

    Knowledge distillation usually has students imitate a teacher's classifier outputs, but raw logits entangle transferable inter-class directional relations with parameterization artifacts such as feature magnitudes, weight norms and biases, producing a classifier geometry mismatch. Angular Conditional Distillation (ACD) rebuilds the student head as a normalized cosine readout that removes magnitudes and biases, then distills standardized conditional non-target relations, passing relative class relations without absolute confidence. On six homogeneous CIFAR-100 teacher-student pairs ACD improves on ordinary KD by 2.51 percentage points on average, and on five heterogeneous pairs it exceeds the strongest competing methods by 4.19 points on average.

You’re all caught up