Related papers: SCJD: Sparse Correlation and Joint Distillation fo…
Deep learning networks are being developed in every stage of the MRI workflow and have provided state-of-the-art results. However, this has come at the cost of increased computation requirement and storage. Hence, replacing the networks…
Knowledge Distillation (KD) aims to transfer knowledge in a teacher-student framework, by providing the predictions of the teacher network to the student network in the training stage to help the student network generalize better. It can…
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…
Numerous point-cloud understanding techniques focus on whole entities and have succeeded in obtaining satisfactory results and limited sparsity tolerance. However, these methods are generally sensitive to incomplete point clouds that are…
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…
This paper aims to accelerate video stream processing, such as object detection and semantic segmentation, by leveraging the temporal redundancies that exist between video frames. Instead of propagating and warping features using motion…
Link prediction based on knowledge graph embeddings (KGE) aims to predict new triples to automatically construct knowledge graphs (KGs). However, recent KGE models achieve performance improvements by excessively increasing the embedding…
Sound event detection (SED) is essential for recognizing specific sounds and their temporal locations within acoustic signals. This becomes challenging particularly for on-device applications, where computational resources are limited. To…
Diffusion Transformers currently lead the field in high-quality video generation, but their slow iterative denoising process and prohibitive quadratic attention costs for long sequences create significant inference bottlenecks. While both…
Current knowledge distillation approaches in semantic segmentation tend to adopt a holistic approach that treats all spatial locations equally. However, for dense prediction, students' predictions on edge regions are highly uncertain due to…
Recent advancements in text-to-3D generation improve the visual quality of Score Distillation Sampling (SDS) and its variants by directly connecting Consistency Distillation (CD) to score distillation. However, due to the imbalance between…
3D human pose estimation from sketches has broad applications in computer animation and film production. Unlike traditional human pose estimation, this task presents unique challenges due to the abstract and disproportionate nature of…
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…
We demonstrate that in knowledge distillation for diffusion models, the teacher network's highly complex denoising process - stemming from its substantially larger capacity - poses a significant challenge for the student model to faithfully…
Despite the successful application of convolutional neural networks (CNNs) in object detection tasks, their efficiency in detecting faults from freight train images remains inadequate for implementation in real-world engineering scenarios.…
Diffusion-based stylization methods typically denoise from a specific partial noise state for image-to-image and video-to-video tasks. This multi-step diffusion process is computationally expensive and hinders real-world application. A…
Spiking Neural Networks (SNNs), inspired by the human brain, offer significant computational efficiency through discrete spike-based information transfer. Despite their potential to reduce inference energy consumption, a performance gap…
Growing efforts to improve knowledge distillation (KD) in large language models (LLMs) replace dense teacher supervision with selective distillation, which uses a subset of token positions, vocabulary classes, or training samples for…
Transformer-based Super-Resolution (SR) methods have demonstrated superior performance compared to convolutional neural network (CNN)-based SR approaches due to their capability to capture long-range dependencies. However, their high…
In this paper, we propose a novel training procedure for the continual representation learning problem in which a neural network model is sequentially learned to alleviate catastrophic forgetting in visual search tasks. Our method, called…