Related papers: Better Supervisory Signals by Observing Learning P…
Deep neural models in recent years have been successful in almost every field, including extremely complex problem statements. However, these models are huge in size, with millions (and even billions) of parameters, thus demanding more…
In recent years, many explanation methods have been proposed to explain individual classifications of deep neural networks. However, how to leverage the created explanations to improve the learning process has been less explored. As the…
The outpouring of various pre-trained models empowers knowledge distillation by providing abundant teacher resources, but there lacks a developed mechanism to utilize these teachers adequately. With a massive model repository composed of…
We investigate cross-quality knowledge distillation (CQKD), a knowledge distillation method where knowledge from a teacher network trained with full-resolution images is transferred to a student network that takes as input low-resolution…
Knowledge distillation, i.e., one classifier being trained on the outputs of another classifier, is an empirically very successful technique for knowledge transfer between classifiers. It has even been observed that classifiers learn much…
This work investigates the compatibility between label smoothing (LS) and knowledge distillation (KD). Contemporary findings addressing this thesis statement take dichotomous standpoints: Muller et al. (2019) and Shen et al. (2021b).…
We present Knowledge Distillation with Meta Learning (MetaDistil), a simple yet effective alternative to traditional knowledge distillation (KD) methods where the teacher model is fixed during training. We show the teacher network can learn…
Video representation learning is a vital problem for classification task. Recently, a promising unsupervised paradigm termed self-supervised learning has emerged, which explores inherent supervisory signals implied in massive data for…
We survey various knowledge distillation (KD) strategies for simple classification tasks and implement a set of techniques that claim state-of-the-art accuracy. Our experiments using standardized model architectures, fixed compute budgets,…
Knowledge distillation (KD) is an efficient approach to transfer the knowledge from a large "teacher" network to a smaller "student" network. Traditional KD methods require lots of labeled training samples and a white-box teacher…
Knowledge Distillation (KD) is a widely-used technology to inherit information from cumbersome teacher models to compact student models, consequently realizing model compression and acceleration. Compared with image classification, object…
Iterative self-training (self-distillation) repeatedly refits a model on pseudo-labels generated by its own predictions. We study this procedure in overparameterized linear regression: an initial estimator is trained on noisy labels, and…
Deep learning for Information Retrieval (IR) requires a large amount of high-quality query-document relevance labels, but such labels are inherently sparse. Label smoothing redistributes some observed probability mass over unobserved…
Deep learning methods show promising results for overlapping cervical cell instance segmentation. However, in order to train a model with good generalization ability, voluminous pixel-level annotations are demanded which is quite expensive…
Knowledge Distillation (KD) aims to transfer a more capable teacher model's knowledge to a lighter student model in order to improve the efficiency of the model, making it faster and more deployable. However, the student model's…
Several recent studies have elucidated why knowledge distillation (KD) improves model performance. However, few have researched the other advantages of KD in addition to its improving model performance. In this study, we have attempted to…
Many recent breakthroughs in machine learning have been enabled by the pre-trained foundation models. By scaling up model parameters, training data, and computation resources, foundation models have significantly advanced the…
Knowledge distillation aims to compress a powerful yet cumbersome teacher model into a lightweight student model without much sacrifice of performance. For this purpose, various approaches have been proposed over the past few years,…
Existing knowledge distillation methods mostly focus on distillation of teacher's prediction and intermediate activation. However, the structured representation, which arguably is one of the most critical ingredients of deep models, is…
We present DistillFlow, a knowledge distillation approach to learning optical flow. DistillFlow trains multiple teacher models and a student model, where challenging transformations are applied to the input of the student model to generate…