Deep Learning (DL) has revolutionized computer vision, enabling machines to identify objects, segment images, and drive cars with astonishing accuracy. Yet, a critical Achilles’ heel remains: these models often fail dramatically when faced with data that deviates even slightly from…
There is a quiet frustration in the spiking neural network community. These networks, modelled on the actual signalling behaviour of biological neurons, consume a fraction of the energy that conventional deep learning demands. Yet whenever researchers run the numbers, standard…
Head-Tail Aware KL Divergence for Spiking Neural Networks Read More »
Every knowledge distillation paper eventually asks the same question a cash strapped engineering team asks first. Do we really need a giant teacher model sitting around just so a small model can learn from it, or can the small model…
Instead of relying on a hard confidence cutoff, UES introduces long tailed weights derived from ensemble uncertainty, ensuring even the least trustworthy pseudo labels still contribute valuable signal to training. Pick a confidence threshold too low and a semi supervised…
Long Tailed Weights Beat Thresholds For Pseudo Labels Read More »