This paper tackles the problem of semi-supervised video object segmentation on resource-
constrained devices, such as mobile phones. We formulate this problem as a distillation …

Despite exciting progress in pre-training for visual-linguistic (VL) representations, very few
aspire to a small VL model. In this paper, we study knowledge distillation (KD) to effectively …

The success of deep learning is usually accompanied by the growth in neural network
depth. However, the traditional training method only supervises the neural network at its last …

Knowledge distillation (KD) is a learning paradigm for boosting resource-efficient graph
neural networks (GNNs) using more expressive yet cumbersome teacher models. Past work …

Scene matching involves establishing a mapping relationship between heterogeneous
images, which is crucial for drone visual geo-localization. However, it poses a significant …

Neural network binarization accelerates deep models by quantizing their weights and
activations into 1-bit. However, there is still a huge performance gap between Binary Neural …

Weakly-supervised audio-visual violence detection aims to distinguish snippets containing
multimodal violence events with video-level labels. Many prior works perform audio-visual …

Abstract Knowledge Distillation (KD) transfers the knowledge from a high-capacity teacher
network to strengthen a smaller student. Existing methods focus on excavating the …

Previous knowledge distillation (KD) methods mostly focus on compressing network
architectures, which is not thorough enough in deployment as some costs like transmission …

In this article, we adopt the maximizing mutual information (MI) approach to tackle the
problem of unsupervised learning of binary hash codes for efficient cross-modal retrieval …