Traditionally, distillation has been used to train a student model to emulate the input/output functionality of a teacher. A more useful goal than emulation, yet under-explored, is for the student to learn feature representations that transfer well to future tasks. However, we observe that standard distillation of task-specific teachers actually *reduces* the transferability of student representations to downstream tasks. We show that a multi-head, multi-task distillation method using an unlabeled proxy dataset and a generalist teacher is sufficient to consolidate representations from task-specific teacher(s) and improve downstream performance, outperforming the teacher(s) and the strong baseline of ImageNet pretrained features. Our method can also combine the representational knowledge of multiple teachers trained on one or multiple domains into a single model, whose representation is improved on all teachers' domain(s).
National University of Singapore（新加坡国立大学）；Huawei Noah’s Ark Lab（华为诺亚方舟实验室）
Human education system trains one student by multiple experts. Mixture-of-experts (MoE) is a powerful sparse architecture including multiple experts. However, sparse MoE model is easy to overfit, hard to deploy, and not hardware-friendly for practitioners. In this work, inspired by the human education model, we propose a novel task, knowledge integration, to obtain a dense student model (OneS) as knowledgeable as one sparse MoE. We investigate this task by proposing a general training framework including knowledge gathering and knowledge distillation. Specifically, to gather key knowledge from…
Knowledge distillation (KD) is an effective tool for compressing deep classification models for edge devices. However, the performance of KD is affected by the large capacity gap between the teacher and student networks. Recent methods have resorted to a multiple teacher assistant (TA) setting for KD, which sequentially decreases the size of the teacher model to relatively bridge the size gap between these models. This paper proposes a new technique called Curriculum Expert Selection for Knowledge Distillation (CES-KD) to efficiently enhance the learning of a compact student under the capacity…
Compared to machines, humans are extremely good at classifying images into categories, especially when they possess prior knowledge of the categories at hand. If this prior information is not available, supervision in the form of teaching images is required. To learn categories more quickly, people should see important and representative images first, followed by less important images later - or not at all. However, image-importance is individual-specific, i.e. a teaching image is important to a student if it changes their overall ability to discriminate between classes. Further, students keep…
Multi-level Collaborative Distillation Meets Global Workspace Model: A Unified Framework for OCIL
School of Computer Science, Northwestern Polytechnical University（西北工业大学计算机学院）；School of Telecommunications Engineering, Xidian University（西安电子科技大学电信工程学院）
Tsinghua University（清华大学）；Beijing National Research Center for Information Science and Technology (BNRist)（北京信息科学与技术国家研究中心）；Aberystwyth University（阿伯里斯特威斯大学）
In real-world scenarios, data tends to exhibit a long-tailed distribution, which increases the difficulty of training deep networks. In this paper, we propose a novel self-paced knowledge distillation framework, termed Learning From Multiple Experts (LFME). Our method is inspired by the observation that networks trained on less imbalanced subsets of the distribution often yield better performances than their jointly-trained counterparts. We refer to these models as 'Experts', and the proposed LFME framework aggregates the knowledge from multiple 'Experts' to learn a unified student model. Spec…
Zhejiang University（浙江大学）；Stevens Institute of Technology（史蒂文斯理工学院）；Alibaba Group（阿里巴巴集团）；Yunnan University（云南大学）
In this paper, we investigate a novel deep-model reusing task. Our goal is to train a lightweight and versatile student model, without human-labelled annotations, that amalgamates the knowledge and masters the expertise of two pretrained teacher models working on heterogeneous problems, one on scene parsing and the other on depth estimation. To this end, we propose an innovative training strategy that learns the parameters of the student intertwined with the teachers, achieved by 'projecting' its amalgamated features onto each teacher's domain and computing the loss. We also introduce two opti…
DrawEduMath: Evaluating Vision Language Models with Expert-Annotated Students' Hand-Drawn Math Images
Worcester Polytechnic Institute（伍斯特理工学院）；University of California Berkeley（加州大学伯克利分校）；Insource Services（Insource服务公司）；Teaching Lab（教学实验室）；Allen Institute for AI（艾伦人工智能研究所）
This paper presents a study on semi-supervised learning to solve the visual attribute prediction problem. In many applications of vision algorithms, the precise recognition of visual attributes of objects is important but still challenging. This is because defining a class hierarchy of attributes is ambiguous, so training data inevitably suffer from class imbalance and label sparsity, leading to a lack of effective annotations. An intuitive solution is to find a method to effectively learn image representations by utilizing unlabeled images. With that in mind, we propose a multi-teacher-single…
Recently, Cross-Domain Few-Shot Learning (CD-FSL) which aims at addressing the Few-Shot Learning (FSL) problem across different domains has attracted rising attention. The core challenge of CD-FSL lies in the domain gap between the source and novel target datasets. Though many attempts have been made for CD-FSL without any target data during model training, the huge domain gap makes it still hard for existing CD-FSL methods to achieve very satisfactory results. Alternatively, learning CD-FSL models with few labeled target domain data which is more realistic and promising is advocated in previo…
TIB—Leibniz Information Centre for Science and Technology（莱布尼茨科学技术信息中心（TIB））；L3S Research Center（L3S研究中心）；Leibniz University Hannover（汉诺威莱布尼茨大学）
Illustrations are widely used in education, and sometimes, alternatives are not available for visually impaired students. Therefore, those students would benefit greatly from an automatic illustration description system, but only if those descriptions were complete, correct, and easily understandable using a screenreader. In this paper, we report on a study for the assessment of automated image descriptions. We interviewed experts to establish evaluation criteria, which we then used to create an evaluation questionnaire for sighted non-expert raters, and description templates. We used this que…
