Related papers: Structural and Statistical Texture Knowledge Disti…
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…
Knowledge distillation aims at transferring the knowledge from a large teacher model to a small student model with great improvements of the performance of the student model. Therefore, the student network can replace the teacher network to…
Foundation models deliver strong perception but are often too computationally heavy to deploy, and adapting them typically requires costly annotations. We introduce a semi-supervised knowledge distillation (SSKD) framework that compresses…
The balance between high accuracy and high speed has always been a challenging task in semantic image segmentation. Compact segmentation networks are more widely used in the case of limited resources, while their performances are…
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…
Few-shot Class-Incremental Learning (FSCIL) addresses the challenges of evolving data distributions and the difficulty of data acquisition in real-world scenarios. To counteract the catastrophic forgetting typically encountered in FSCIL,…
Transformer-based encoder-decoder models have achieved remarkable success in image-to-image transfer tasks, particularly in image restoration. However, their high computational complexity-manifested in elevated FLOPs and parameter…
In this paper, we tackle a new problem: how to transfer knowledge from the pre-trained cumbersome yet well-performed CNN-based model to learn a compact Vision Transformer (ViT)-based model while maintaining its learning capacity? Due to the…
Sequence-level knowledge distillation (SLKD) is a model compression technique that leverages large, accurate teacher models to train smaller, under-parameterized student models. Why does pre-processing MT data with SLKD help us train…
Knowledge distillation has become widely recognized for its ability to transfer knowledge from a large teacher network to a compact and more streamlined student network. Traditional knowledge distillation methods primarily follow a…
The quantization of deep neural networks (QDNNs) has been actively studied for deployment in edge devices. Recent studies employ the knowledge distillation (KD) method to improve the performance of quantized networks. In this study, we…
Object detection has advanced significantly with Detection Transformers (DETRs). However, these models are computationally demanding, posing challenges for deployment in resource-constrained environments (e.g., self-driving cars). Knowledge…
Online HD map construction is a fundamental task in autonomous driving systems, aiming to acquire semantic information of map elements around the ego vehicle based on real-time sensor inputs. Recently, several approaches have achieved…
Existing Knowledge Distillation (KD) methods often align feature information between teacher and student by exploring meaningful feature processing and loss functions. However, due to the difference in feature distributions between the…
Recent knowledge distillation (KD) methods for semantic segmentation introduce increasingly complex hand-crafted objectives, yet are typically evaluated under fixed iteration schedules. These objectives substantially increase per-iteration…
Knowledge distillation has become a cornerstone technique in deep learning, facilitating the transfer of knowledge from complex models to lightweight counterparts. Traditional distillation approaches focus on transferring knowledge at the…
Recent advances in knowledge distillation have emphasized the importance of decoupling different knowledge components. While existing methods utilize momentum mechanisms to separate task-oriented and distillation gradients, they overlook…
Knowledge distillation is the process of transferring knowledge from a more powerful large model (teacher) to a simpler counterpart (student). Numerous current approaches involve the student imitating the knowledge of the teacher directly.…
Segmenting dental plaque from images of medical reagent staining provides valuable information for diagnosis and the determination of follow-up treatment plan. However, accurate dental plaque segmentation is a challenging task that requires…
Knowledge distillation (KD) is an effective model compression technique that transfers knowledge from a high-performance teacher to a lightweight student, reducing computational and storage costs while maintaining competitive accuracy.…