Related papers: Structured Knowledge Distillation Towards Efficien…
Depth estimation and scene segmentation are two important tasks in intelligent transportation systems. A joint modeling of these two tasks will reduce the requirement for both the storage and training efforts. This work explores how the…
3D object detection based on LiDAR point clouds is a crucial module in autonomous driving particularly for long range sensing. Most of the research is focused on achieving higher accuracy and these models are not optimized for deployment on…
Recent progress in 3D reconstruction has enabled realistic 3D models from dense image captures, yet challenges persist with sparse views, often leading to artifacts in unseen areas. Recent works leverage Video Diffusion Models (VDMs) to…
Multimodal 3D object detectors leverage the strengths of both geometry-aware LiDAR point clouds and semantically rich RGB images to enhance detection performance. However, the inherent heterogeneity between these modalities, including…
Bird's-Eye-View (BEV) 3D Object Detection is a crucial multi-view technique for autonomous driving systems. Recently, plenty of works are proposed, following a similar paradigm consisting of three essential components, i.e., camera feature…
Knowledge distillation aims to enhance the performance of a lightweight student model by exploiting the knowledge from a pre-trained cumbersome teacher model. However, in the traditional knowledge distillation, teacher predictions are only…
While diffusion models have demonstrated remarkable progress in 2D image generation and editing, extending these capabilities to 3D editing remains challenging, particularly in maintaining multi-view consistency. Classical approaches…
Dataset distillation aims to distill the knowledge of a large-scale real dataset into small yet informative synthetic data such that a model trained on it performs as well as a model trained on the full dataset. Despite recent progress,…
Device-directed speech detection (DDSD) is a binary classification task that separates the user's queries to a voice assistant (VA) from background speech or side conversations. This is important for achieving naturalistic user experience.…
Previous knowledge distillation (KD) methods mostly focus on compressing network architectures, which is not thorough enough in deployment as some costs like transmission bandwidth and imaging equipment are related to the image size.…
This paper addresses the critical challenges of sparsity and occlusion in LiDAR-based 3D object detection. Current methods often rely on supplementary modules or specific architectural designs, potentially limiting their applicability to…
We present a hybrid-view-based knowledge distillation framework, termed HVDistill, to guide the feature learning of a point cloud neural network with a pre-trained image network in an unsupervised manner. By exploiting the geometric…
Knowledge distillation (KD) is a widely adopted and effective method for compressing models in object detection tasks. Particularly, feature-based distillation methods have shown remarkable performance. Existing approaches often ignore the…
As a promising approach in model compression, knowledge distillation improves the performance of a compact model by transferring the knowledge from a cumbersome one. The kind of knowledge used to guide the training of the student is…
Knowledge distillation has been applied to image classification successfully. However, object detection is much more sophisticated and most knowledge distillation methods have failed on it. In this paper, we point out that in object…
Knowledge distillation (KD) has been widely applied in semantic segmentation to compress large models, but conventional approaches primarily preserve in-domain accuracy while neglecting out-of-domain generalization, which is essential under…
The application of vision-based multi-view environmental perception system has been increasingly recognized in autonomous driving technology, especially the BEV-based models. Current state-of-the-art solutions primarily encode image…
In advanced paradigms of autonomous driving, learning Bird's Eye View (BEV) representation from surrounding views is crucial for multi-task framework. However, existing methods based on depth estimation or camera-driven attention are not…
Point cloud processing has gained significant attention due to its critical role in applications such as autonomous driving and 3D object recognition. However, deploying high-performance models like Point Transformer V3 in…
Pre-trained language-vision models have shown remarkable performance on the visual question answering (VQA) task. However, most pre-trained models are trained by only considering monolingual learning, especially the resource-rich language…