Related papers: Adaptive Weighting in Knowledge Distillation: An A…
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). Albeit useful especially in the penultimate layer and…
Data selection is a key component of efficient instruction tuning for large language models, as recent work has shown that data quality often matters more than data quantity. Accordingly, prior studies have introduced various…
Knowledge transfer between artificial neural networks has become an important topic in deep learning. Among the open questions are what kind of knowledge needs to be preserved for the transfer, and how it can be effectively achieved.…
Knowledge distillation between machine learning models has opened many new avenues for parameter count reduction, performance improvements, or amortizing training time when changing architectures between the teacher and student network. In…
Multimodal Deep Learning has garnered much interest, and transformers have triggered novel approaches, thanks to the cross-attention mechanism. Here we propose an approach to deal with two key existing challenges: the high computational…
In recent years, deep neural networks have achieved remarkable accuracy in computer vision tasks. With inference time being a crucial factor, particularly in dense prediction tasks such as semantic segmentation, knowledge distillation has…
Modern neural networks do not always produce well-calibrated predictions, even when trained with a proper scoring function such as cross-entropy. In classification settings, simple methods such as isotonic regression or temperature scaling…
Knowledge Distillation (KD) is a powerful technique for transferring knowledge between neural network models, where a pre-trained teacher model is used to facilitate the training of the target student model. However, the availability of a…
In instance-level detection tasks (e.g., object detection), reducing input resolution is an easy option to improve runtime efficiency. However, this option traditionally hurts the detection performance much. This paper focuses on boosting…
Accurate uncertainty quantification remains a key challenge for standard LLMs, prompting the adoption of Bayesian and ensemble-based methods. However, such methods typically necessitate computationally expensive sampling, involving multiple…
Tabular foundation models (TFMs) achieve strong performance on health datasets, but their inference cost and infrastructure requirements limit practical use. We study whether their predictive behavior can be transferred to lightweight…
Although large foundation models pre-trained by self-supervised learning have achieved state-of-the-art performance in many tasks including automatic speech recognition (ASR), knowledge distillation (KD) is often required in practice to…
Knowledge Distillation (KD) has made remarkable progress in the last few years and become a popular paradigm for model compression and knowledge transfer. However, almost all existing KD algorithms are data-driven, i.e., relying on a large…
Enhancing small language models for real-life application deployment is a significant challenge facing the research community. Due to the difficulties and costs of using large language models, researchers are seeking ways to effectively…
This paper addresses the limitations of large-scale language models in safety alignment and robustness by proposing a fine-tuning method that combines contrastive distillation with noise-robust training. The method freezes the backbone…
Knowledge Distillation (KD) has been used in image classification for model compression. However, rare studies apply this technology on single-stage object detectors. Focal loss shows that the accumulated errors of easily-classified samples…
Knowledge Distillation (KD) transfers the knowledge from a high-capacity teacher model to promote a smaller student model. Existing efforts guide the distillation by matching their prediction logits, feature embedding, etc., while leaving…
In this work, we explore data augmentations for knowledge distillation on semantic segmentation. To avoid over-fitting to the noise in the teacher network, a large number of training examples is essential for knowledge distillation.…
Knowledge Distillation (KD) aims at improving the performance of a low-capacity student model by inheriting knowledge from a high-capacity teacher model. Previous KD methods typically train a student by minimizing a task-related loss and…
Pre-trained language-vision models have shown remarkable performance on the visual question answering (VQA) task. However, most pre-trained models are trained by only considering monolingual learning, especially the resource-rich language…