Related papers: FAKD: Feature Augmented Knowledge Distillation for…
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…
Recent advances in collaborative knowledge distillation have demonstrated cutting-edge performance for resource-constrained distributed multimedia learning scenarios. However, achieving such competitiveness requires addressing a fundamental…
We introduce Layered Self-Supervised Knowledge Distillation (LSSKD) framework for training compact deep learning models. Unlike traditional methods that rely on pre-trained teacher networks, our approach appends auxiliary classifiers to…
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…
In this paper, we propose a feature affinity (FA) assisted knowledge distillation (KD) method to improve quantization-aware training of deep neural networks (DNN). The FA loss on intermediate feature maps of DNNs plays the role of teaching…
Class-incremental semantic segmentation (CISS) labels each pixel of an image with a corresponding object/stuff class continually. To this end, it is crucial to learn novel classes incrementally without forgetting previously learned…
Current knowledge distillation (KD) methods primarily focus on transferring various structured knowledge and designing corresponding optimization goals to encourage the student network to imitate the output of the teacher network. However,…
In this paper, we analyze the feature-based knowledge distillation for recommendation from the frequency perspective. By defining knowledge as different frequency components of the features, we theoretically demonstrate that regular…
In this research, we propose an innovative method to boost Knowledge Distillation efficiency without the need for resource-heavy teacher models. Knowledge Distillation trains a smaller ``student'' model with guidance from a larger…
Recent advances in knowledge distillation (KD) predominantly emphasize feature-level knowledge transfer, frequently overlooking critical information embedded within the teacher's logit distributions. In this paper, we revisit logit-based…
The representation gap between teacher and student is an emerging topic in knowledge distillation (KD). To reduce the gap and improve the performance, current methods often resort to complicated training schemes, loss functions, and feature…
Test-Time Training (TTT) proposes to adapt a pre-trained network to changing data distributions on-the-fly. In this work, we propose the first TTT method for 3D semantic segmentation, TTT-KD, which models Knowledge Distillation (KD) from…
Knowledge distillation (KD) is a promising yet challenging model compression technique that transfers rich learning representations from a well-performing but cumbersome teacher model to a compact student model. Previous methods for image…
Collecting and annotating datasets for pixel-level semantic segmentation tasks are highly labor-intensive. Data augmentation provides a viable solution by enhancing model generalization without additional real-world data collection.…
The state of the art in semantic segmentation is steadily increasing in performance, resulting in more precise and reliable segmentations in many different applications. However, progress is limited by the cost of generating labels for…
Previous knowledge distillation (KD) methods mostly focus on compressing network architectures, which is not thorough enough in deployment as some costs like transmission bandwidth and imaging equipment are related to the image size.…
Distilling knowledge from huge pre-trained networks to improve the performance of tiny networks has favored deep learning models to be used in many real-time and mobile applications. Several approaches that demonstrate success in this field…
Pre-trained multilingual language models play an important role in cross-lingual natural language understanding tasks. However, existing methods did not focus on learning the semantic structure of representation, and thus could not optimize…
Crossmodal knowledge distillation (KD) aims to enhance a unimodal student using a multimodal teacher model. In particular, when the teacher's modalities include the student's, additional complementary information can be exploited to improve…
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…