Related papers: RCTDistill: Cross-Modal Knowledge Distillation Fra…

The improvement in the performance of efficient and lightweight models (i.e., the student model) is achieved through knowledge distillation (KD), which involves transferring knowledge from more complex models (i.e., the teacher model).…

Millimeter-wave radar plays a vital role in 3D object detection for autonomous driving due to its all-weather and all-lighting-condition capabilities for perception. However, radar point clouds suffer from pronounced sparsity and…

Due to limitations in data quality, some essential visual tasks are difficult to perform independently. Introducing previously unavailable information to transfer informative dark knowledge has been a common way to solve such hard tasks.…

Knowledge distillation is an effective image anomaly detection and localization scheme. However, a major drawback of this scheme is its tendency to overly generalize, primarily due to the similarities between input and supervisory signals.…

Vision Transformers (ViTs) have achieved significant advancement in computer vision tasks due to their powerful modeling capacity. However, their performance notably degrades when trained with insufficient data due to lack of inherent…

Cross-modal knowledge distillation (CMKD) refers to the scenario in which a learning framework must handle training and test data that exhibit a modality mismatch, more precisely, training and test data do not cover the same set of data…

State-of-the-art distillation methods are mainly based on distilling deep features from intermediate layers, while the significance of logit distillation is greatly overlooked. To provide a novel viewpoint to study logit distillation, we…

Knowledge distillation (KD) is an effective technique to transfer knowledge from one neural network (teacher) to another (student), thus improving the performance of the student. To make the student better mimic the behavior of the teacher,…

LiDAR-based 3D scene perception is a fundamental and important task for autonomous driving. Most state-of-the-art methods on LiDAR-based 3D recognition tasks focus on single frame 3D point cloud data, and the temporal information is ignored…

Most knowledge distillation (KD) methodologies predominantly focus on teacher-student pairs with similar architectures, such as both being convolutional neural networks (CNNs). However, the potential and flexibility of KD can be greatly…

Knowledge Distillation (KD) has been used in image classification for model compression. However, rare studies apply this technology on single-stage object detectors. Focal loss shows that the accumulated errors of easily-classified samples…

The human vision and perception system is inherently incremental where new knowledge is continually learned over time whilst existing knowledge is retained. On the other hand, deep learning networks are ill-equipped for incremental…

Aiming at highly accurate object detection for connected and automated vehicles (CAVs), this paper presents a Deep Neural Network based 3D object detection model that leverages a three-stage feature extractor by developing a novel…

3D occupancy prediction is an emerging task that aims to estimate the occupancy states and semantics of 3D scenes using multi-view images. However, image-based scene perception encounters significant challenges in achieving accurate…

Although multi-view 3D object detection based on the Bird's-Eye-View (BEV) paradigm has garnered widespread attention as an economical and deployment-friendly perception solution for autonomous driving, there is still a performance gap…

Knowledge distillation (KD) is a key technique for compressing large-scale language models (LLMs), yet prevailing logit-based methods typically employ static strategies that are misaligned with the dynamic learning process of student…

The amount of medical images for training deep classification models is typically very scarce, making these deep models prone to overfit the training data. Studies showed that knowledge distillation (KD), especially the mean-teacher…

4D millimeter-wave (MMW) radar, which provides both height information and dense point cloud data over 3D MMW radar, has become increasingly popular in 3D object detection. In recent years, radar-vision fusion models have demonstrated…

Vision-Language Models (VLMs) bring powerful understanding and reasoning capabilities to multimodal tasks. Meanwhile, the great need for capable aritificial intelligence on mobile devices also arises, such as the AI assistant software. Some…

Knowledge Distillation (KD) is a strategy for the definition of a set of transferability gangways to improve the efficiency of Convolutional Neural Networks. Feature-based Knowledge Distillation is a subfield of KD that relies on…