Most existing distillation methods ignore the flexible role of the temperature in the loss
function and fix it as a hyper-parameter that can be decided by an inefficient grid search. In …

For speaker recognition, it is difficult to extract an accurate speaker representation from
speech because of its mixture of speaker traits and content. This paper proposes a …

Abstract Knowledge distillation can be generally divided into offline and online categories
according to whether teacher model is pre-trained and persistent during the distillation …

Abstract Knowledge distillation involves transferring soft labels from a teacher to a student
using a shared temperature-based softmax function. However the assumption of a shared …

Few-shot image generation (FSIG) aims to learn to generate new and diverse samples given
an extremely limited number of samples from a domain, eg, 10 training samples. Recent …

Abstract Model inversion (MI) attacks aim to infer and reconstruct private training data by
abusing access to a model. MI attacks have raised concerns about the leaking of sensitive …

Visual counterfeits (We refer to CNN-generated images as counterfeits throughout this
paper.) are increasingly causing an existential conundrum in mainstream media with rapid …

Few-shot image generation (FSIG) learns to generate diverse and high-fidelity images from
a target domain using a few (eg, 10) reference samples. Existing FSIG methods select …

Previous arts built an intimate link between knowledge distillation (KD) and label smoothing
(LS) that they both impose regularization on the model training. In this paper, we delve …

One of the core challenges of deep learning in medical image analysis is data insufficiency,
especially for 3D brain imaging, which may lead to model over-fitting and poor …