Related papers: 4DRaL: Bridging 4D Radar with LiDAR for Place Reco…
We present a heterogeneous localization framework for solving radar global localization and pose tracking on pre-built lidar maps. To bridge the gap of sensing modalities, deep neural networks are constructed to create shared embedding…
Knowledge distillation is considered as a training and compression strategy in which two neural networks, namely a teacher and a student, are coupled together during training. The teacher network is supposed to be a trustworthy predictor…
Deep learning often requires a large amount of data. In real-world applications, e.g., healthcare applications, the data collected by a single organization (e.g., hospital) is often limited, and the majority of massive and diverse data is…
Knowledge distillation (KD) is a new method for transferring knowledge of a structure under training to another one. The typical application of KD is in the form of learning a small model (named as a student) by soft labels produced by a…
Despite rapid developments in visual image-based road detection, robustly identifying road areas in visual images remains challenging due to issues like illumination changes and blurry images. To this end, LiDAR sensor data can be…
We propose LiDAL, a novel active learning method for 3D LiDAR semantic segmentation by exploiting inter-frame uncertainty among LiDAR frames. Our core idea is that a well-trained model should generate robust results irrespective of…
Leveraging LiDAR-based detectors or real LiDAR point data to guide monocular 3D detection has brought significant improvement, e.g., Pseudo-LiDAR methods. However, the existing methods usually apply non-end-to-end training strategies and…
LiDAR point cloud segmentation is one of the most fundamental tasks for autonomous driving scene understanding. However, it is difficult for existing models to achieve both high inference speed and accuracy simultaneously. For example,…
Place recognition is an essential and challenging task in loop closing and global localization for robotics and autonomous driving applications. Benefiting from the recent advances in deep learning techniques, the performance of LiDAR place…
Recent recommender systems have started to employ knowledge distillation, which is a model compression technique distilling knowledge from a cumbersome model (teacher) to a compact model (student), to reduce inference latency while…
Recently, efficient Multimodal Large Language Models (MLLMs) have gained significant attention as a solution to their high computational complexity, making them more practical for real-world applications. In this regard, the knowledge…
Recent studies pointed out that knowledge distillation (KD) suffers from two degradation problems, the teacher-student gap and the incompatibility with strong data augmentations, making it not applicable to training state-of-the-art models,…
Heterogeneous distillation is an effective way to transfer knowledge from cross-architecture teacher models to student models. However, existing heterogeneous distillation methods do not take full advantage of the dark knowledge hidden in…
Deep learning architectures have shown remarkable results in scene understanding problems, however they exhibit a critical drop of performances when they are required to learn incrementally new tasks without forgetting old ones. This…
Knowledge distillation involves transferring the predictive capabilities of large, high-performing AI models (teachers) to smaller models (students) that can operate in environments with limited computing power. In this paper, we address…
3D perception based on the representations learned from multi-camera bird's-eye-view (BEV) is trending as cameras are cost-effective for mass production in autonomous driving industry. However, there exists a distinct performance gap…
It remains very challenging to build a pedestrian detection system for real world applications, which demand for both accuracy and speed. This work presents a novel hierarchical knowledge distillation framework to learn a lightweight…
Lifelong learning aims to preserve knowledge acquired from previous tasks while incorporating knowledge from a sequence of new tasks. However, most prior work explores only streams of homogeneous tasks (\textit{e.g.}, only classification…
We propose a novel way to train ranking models, such as recommender systems, that are both effective and efficient. Knowledge distillation (KD) was shown to be successful in image recognition to achieve both effectiveness and efficiency. We…
In the field of 3D object detection for autonomous driving, the sensor portfolio including multi-modality and single-modality is diverse and complex. Since the multi-modal methods have system complexity while the accuracy of single-modal…