Sample-Conditioned Representation Selection for Audio Few-Shot Learning
Few-shot audio classifiers may rely on foreground-background co-occurrences and fail when those correlations shift. On SpurAudio, the resulting representation shift is concentrated and class dependent: for ResNet12, the top 10 percent of channels explain 82.80 percent of the null-corrected shift contribution. We propos...
Feng-Rui Liu, Ning-Xin Shen, Yi Li et al.
· 0 citations