Learning image representations without human supervision is an important and active
research field. Several recent approaches have successfully leveraged the idea of making …

While fine-tuning based methods for few-shot object detection have achieved remarkable
progress, a crucial challenge that has not been addressed well is the potential class-specific …

Recently published graph neural networks (GNNs) show promising performance at social
event detection tasks. However, most studies are oriented toward monolingual data in …

Existing knowledge distillation methods mostly focus on distillation of teacher's prediction
and intermediate activation. However, the structured representation, which arguably is one …

Typical technique in knowledge distillation (KD) is regularizing the learning of a limited
capacity model (student) by pushing its responses to match a powerful model's (teacher) …

With the increasing computational power of computing devices, the pre-training of large
deep-learning models has become prevalent. However, deploying such models on edge …

Despite that deep neural networks have achieved satisfactory performance, they rely on
powerful hardware for training, which is expensive and not easy to get. Therefore, the …

Face recognition has attracted particular interest in biometric recognition with wide
applications in security, entertainment, health, marketing. Recent years have witnessed …

Knowledge Distillation refers to a class of methods that transfers the knowledge from a
teacher network to a student network. In this paper, we propose Sparse Representation …