Related papers: One-Shot Knowledge Transfer for Scalable Person Re…

Accelerating learning processes for complex tasks by leveraging previously learned tasks has been one of the most challenging problems in reinforcement learning, especially when the similarity between source and target tasks is low. This…

Large language models (LLMs) can acquire strong code-generation capabilities through few-shot learning. In contrast, supervised fine-tuning is still needed for smaller models to achieve good performance. Such fine-tuning demands a large…

Cloth-Changing Person Re-Identification (CC-ReID) is a common and realistic problem since fashion constantly changes over time and people's aesthetic preferences are not set in stone. While most existing cloth-changing ReID methods focus on…

Knowledge tracing (KT) aims to leverage students' learning histories to estimate their mastery levels on a set of pre-defined skills, based on which the corresponding future performance can be accurately predicted. As an important way of…

Model quantization is considered as a promising method to greatly reduce the resource requirements of deep neural networks. To deal with the performance drop induced by quantization errors, a popular method is to use training data to…

Most teacher-student frameworks based on knowledge distillation (KD) depend on a strong congruent constraint on instance level. However, they usually ignore the correlation between multiple instances, which is also valuable for knowledge…

The ubiquitous use of IoT and machine learning applications is creating large amounts of data that require accurate and real-time processing. Although edge-based smart data processing can be enabled by deploying pretrained models, the…

Cross-media retrieval is a research hotspot in multimedia area, which aims to perform retrieval across different media types such as image and text. The performance of existing methods usually relies on labeled data for model training.…

Current state-of-the-art object detectors are at the expense of high computational costs and are hard to deploy to low-end devices. Knowledge distillation, which aims at training a smaller student network by transferring knowledge from a…

Decentralized collaborative learning under data heterogeneity and privacy constraints has rapidly advanced. However, existing solutions like federated learning, ensembles, and transfer learning, often fail to adequately serve the unique…

Person re-identification (ReID) under occlusions is a challenging problem in video surveillance. Most of existing person ReID methods take advantage of local features to deal with occlusions. However, these methods usually independently…

Pre-trained models have become the preferred backbone due to the increasing complexity of model parameters. However, traditional pre-trained models often face deployment challenges due to their fixed sizes, and are prone to negative…

Knowledge Distillation (KD) methods are capable of transferring the knowledge encoded in a large and complex teacher into a smaller and faster student. Early methods were usually limited to transferring the knowledge only between the last…

Person re-identification (re-ID) in first-person (egocentric) vision is a fairly new and unexplored problem. With the increase of wearable video recording devices, egocentric data becomes readily available, and person re-identification has…

Knowledge distillation (KD) is a technique used to transfer knowledge from an overparameterized teacher network to a less-parameterized student network, thereby minimizing the incurred performance loss. KD methods can be categorized into…

Typically, the significant efficiency can be achieved by deploying different edge AI models in various real world scenarios while a few large models manage those edge AI models remotely from cloud servers. However, customizing edge AI…

Developing algorithms that are able to generalize to a novel task given only a few labeled examples represents a fundamental challenge in closing the gap between machine- and human-level performance. The core of human cognition lies in the…

How can we efficiently compress a model while maintaining its performance? Knowledge Distillation (KD) is one of the widely known methods for model compression. In essence, KD trains a smaller student model based on a larger teacher model…

Unsupervised domain adaptive person Re-IDentification (ReID) is challenging because of the large domain gap between source and target domains, as well as the lackage of labeled data on the target domain. This paper tackles this challenge…

In recent years, there has been a great deal of research in developing end-to-end speech recognition models, which enable simplifying the traditional pipeline and achieving promising results. Despite their remarkable performance…