相关论文: Multi scale Feature Extraction and Fusion for Onli…

We present a novel online depth map fusion approach that learns depth map aggregation in a latent feature space. While previous fusion methods use an explicit scene representation like signed distance functions (SDFs), we propose a learned…

Although face recognition (FR) has achieved great success in recent years, it is still challenging to accurately recognize faces in low-quality images due to the obscured facial details. Nevertheless, it is often feasible to make…

We present a novel information-theoretic approach to introduce dependency among features of a deep convolutional neural network (CNN). The core idea of our proposed method, called MUSE, is to combine MUtual information and SElf-information…

Micro-Expression Recognition has become challenging, as it is extremely difficult to extract the subtle facial changes of micro-expressions. Recently, several approaches proposed several expression-shared features algorithms for…

Data-Free Knowledge Distillation (DFKD) is an advanced technique that enables knowledge transfer from a teacher model to a student model without relying on original training data. While DFKD methods have achieved success on smaller datasets…

Multi-modality image fusion aims to synthesize a single, comprehensive image from multiple source inputs. Traditional approaches, such as CNNs and GANs, offer efficiency but struggle to handle low-quality or complex inputs. Recent advances…

The effectiveness of machine learning algorithms arises from being able to extract useful features from large amounts of data. As model and dataset sizes increase, dataset distillation methods that compress large datasets into significantly…

This paper addresses the challenges of high computational cost and slow inference in deploying large language models. It proposes a distillation strategy guided by multiple teacher models. The method constructs several teacher models and…

Data-free knowledge distillation aims to learn a compact student network from a pre-trained large teacher network without using the original training data of the teacher network. Existing collection-based and generation-based methods train…

In instance-level detection tasks (e.g., object detection), reducing input resolution is an easy option to improve runtime efficiency. However, this option traditionally hurts the detection performance much. This paper focuses on boosting…

With the exponential increase in image data, training an image restoration model is laborious. Dataset distillation is a potential solution to this problem, yet current distillation techniques are a blank canvas in the field of image…

Distillation is an effective knowledge-transfer technique that uses predicted distributions of a powerful teacher model as soft targets to train a less-parameterized student model. A pre-trained high capacity teacher, however, is not always…

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…

The deep layers of modern neural networks extract a rather rich set of features as an input propagates through the network. This paper sets out to harvest these rich intermediate representations for quantization with minimal accuracy loss…

Communication constraints are one of the major challenges preventing the wide-spread adoption of Federated Learning systems. Recently, Federated Distillation (FD), a new algorithmic paradigm for Federated Learning with fundamentally…

Knowledge distillation is one of the most popular and effective techniques for knowledge transfer, model compression and semi-supervised learning. Most existing distillation approaches require the access to original or augmented training…

Dataset distillation aims to create a small and highly representative synthetic dataset that preserves the essential information of a larger real dataset. Beyond reducing storage and computational costs, related approaches offer a promising…

Existing feature distillation methods commonly adopt the One-to-one Representation Matching between any pre-selected teacher-student layer pair. In this paper, we present N-to-One Representation (NORM), a new two-stage knowledge…

With the development of deep convolutional neural networks, medical image segmentation has achieved a series of breakthroughs in recent years. However, the high-performance convolutional neural networks always mean numerous parameters and…

In this paper, we propose an intra-set and inter-set recursive fusion framework with time-frequency calibrated knowledge distillation (I$^2$SRF-TFCKD) for SE. Different from previous distillation strategies for SE, the proposed framework…