相关论文: Leave No Knowledge Behind During Knowledge Distill…

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…

Increased training parameters have enabled large pre-trained models to excel in various downstream tasks. Nevertheless, the extensive computational requirements associated with these models hinder their widespread adoption within the…

Large language models (LLMs) learn contextual embeddings that capture rich semantic information, yet they often overlook structured lexical knowledge such as word senses and relationships. Prior work has shown that incorporating sense…

Existing data-dependent hashing methods use large backbone networks with millions of parameters and are computationally complex. Existing knowledge distillation methods use logits and other features of the deep (teacher) model and as…

Deep Neural Networks (DNNs) have achieved notable performance in the fields of computer vision and natural language processing with various applications in both academia and industry. However, with recent advancements in DNNs and…

Speech emotion recognition (SER) performance deteriorates significantly in the presence of noise, making it challenging to achieve competitive performance in noisy conditions. To this end, we propose a multi-level knowledge distillation…

Knowledge distillation, the technique of transferring knowledge from large, complex models to smaller ones, marks a pivotal step towards efficient AI deployment. Distilling Step-by-Step~(DSS), a novel method utilizing chain-of-thought~(CoT)…

Knowledge distillation (KD) exploits a large well-trained model (i.e., teacher) to train a small student model on the same dataset for the same task. Treating teacher features as knowledge, prevailing methods of knowledge distillation train…

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…

Cued Speech (CS) is a visual communication system for the deaf or hearing impaired people. It combines lip movements with hand cues to obtain a complete phonetic repertoire. Current deep learning based methods on automatic CS recognition…

Large Vision-Language Models (VLMs) are successful in addressing a multitude of vision-language understanding tasks, such as Visual Question Answering (VQA), but their memory and compute requirements remain a concern for practical…

Small language models (SLMs) are crucial for applications with strict latency and computational constraints, yet achieving high performance remains challenging. Knowledge distillation (KD) can transfer capabilities from large teacher…

In the era of Large Language Models (LLMs), Knowledge Distillation (KD) emerges as a pivotal methodology for transferring advanced capabilities from leading proprietary LLMs, such as GPT-4, to their open-source counterparts like LLaMA and…

Knowledge Distillation (KD) is a fundamental technique for compressing large language models (LLMs) into compact, efficient student models. However, existing white-box KD methods mainly focus on balancing ground truth and student-generated…

Pre-trained language models such as BERT have proven to be highly effective for natural language processing (NLP) tasks. However, the high demand for computing resources in training such models hinders their application in practice. In…

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, aimed at transferring the knowledge from a heavy teacher network to a lightweight student network, has emerged as a promising technique for compressing neural networks. However, due to the capacity gap between the…

Representation knowledge distillation aims at transferring rich information from one model to another. Common approaches for representation distillation mainly focus on the direct minimization of distance metrics between the models'…

Knowledge distillation deals with the problem of training a smaller model (Student) from a high capacity source model (Teacher) so as to retain most of its performance. Existing approaches use either the training data or meta-data extracted…

Voice interfaces integral to the human-computer interaction systems can benefit from speech emotion recognition (SER) to customize responses based on user emotions. Since humans convey emotions through multi-modal audio-visual cues,…