Related papers: Asymmetric Cross-Modal Knowledge Distillation: Bri…
In practical applications of human pose estimation, low-resolution inputs frequently occur, and existing state-of-the-art models perform poorly with low-resolution images. This work focuses on boosting the performance of low-resolution…
Human activity recognition (HAR) based on multi-modal approach has been recently shown to improve the accuracy performance of HAR. However, restricted computational resources associated with wearable devices, i.e., smartwatch, failed to…
The advent of scalable deep models and large datasets has improved the performance of Neural Machine Translation. Knowledge Distillation (KD) enhances efficiency by transferring knowledge from a teacher model to a more compact student…
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…
Many existing studies on knowledge distillation have focused on methods in which a student model mimics a teacher model well. Simply imitating the teacher's knowledge, however, is not sufficient for the student to surpass that of the…
Due to the data imbalance and the diversity of defects, student-teacher networks (S-T) are favored in unsupervised anomaly detection, which explores the discrepancy in feature representation derived from the knowledge distillation process…
Compact models can be effectively trained through Knowledge Distillation (KD), a technique that transfers knowledge from larger, high-performing teacher models. Two key challenges in Knowledge Distillation (KD) are: 1) balancing learning…
Semantic segmentation of 3D LiDAR data plays a pivotal role in autonomous driving. Traditional approaches rely on extensive annotated data for point cloud analysis, incurring high costs and time investments. In contrast, realworld image…
Both accuracy and efficiency are of significant importance to the task of semantic segmentation. Existing deep FCNs suffer from heavy computations due to a series of high-resolution feature maps for preserving the detailed knowledge in…
Recent advances in knowledge distillation (KD) have enabled smaller student models to approach the performance of larger teacher models. However, popular methods such as supervised KD and on-policy KD, are adversely impacted by the…
Efficient Multimodal Large Language Models (MLLMs) compress vision tokens to reduce resource consumption, but the loss of visual information can degrade comprehension capabilities. Although some priors introduce Knowledge Distillation to…
Existing techniques often attempt to make knowledge transfer from a powerful machine translation (MT) to speech translation (ST) model with some elaborate techniques, which often requires transcription as extra input during training.…
Knowledge Distillation (KD) has emerged as a prominent technique for model compression. However, conventional KD approaches primarily focus on homogeneous architectures with identical tokenizers, constraining their applicability in…
Crossmodal knowledge distillation (KD) extends traditional knowledge distillation to the area of multimodal learning and demonstrates great success in various applications. To achieve knowledge transfer across modalities, a pretrained…
Several methods of knowledge distillation have been developed for neural network compression. While they all use the KL divergence loss to align the soft outputs of the student model more closely with that of the teacher, the various…
The rapid increase in multimodal data availability has sparked significant interest in cross-modal knowledge distillation (KD) techniques, where richer "teacher" modalities transfer information to weaker "student" modalities during model…
Vision-Language Models (VLMs) have shown remarkable capabilities in joint vision-language understanding, but their large scale poses significant challenges for deployment in resource-constrained scenarios. Knowledge Distillation (KD) offers…
Model compression through knowledge distillation has seen extensive application in classification and segmentation tasks. However, its potential in image-to-image translation, particularly in image restoration, remains underexplored. To…
Knowledge distillation is normally used to compress a big network, or teacher, onto a smaller one, the student, by training it to match its outputs. Recently, some works have shown that robustness against adversarial attacks can also be…
Novel Class Discovery (NCD) aims to discover unknown and novel classes in an unlabeled set by leveraging knowledge already learned about known classes. Existing works focus on instance-level or class-level knowledge representation and build…