Related papers: ELiTe: Efficient Image-to-LiDAR Knowledge Transfer…
Medical images usually suffer from image degradation in clinical practice, leading to decreased performance of deep learning-based models. To resolve this problem, most previous works have focused on filtering out degradation-causing…
Vision-language models (VLMs) have revolutionized machine learning by leveraging large pre-trained models to tackle various downstream tasks. Although label, training, and data efficiency have improved, many state-of-the-art VLMs still…
Frame-wise semantic segmentation of indoor lidar scans is a fundamental step toward higher-level 3D scene understanding and mapping applications. However, acquiring frame-wise ground truth for training deep learning models is costly and…
One-Shot Federated Learning, where a central server learns a global model in a single communication round, has emerged as a promising paradigm. However, under extremely non-IID settings, existing data-free methods often generate low-quality…
Collecting and labeling the registered 3D point cloud is costly. As a result, 3D resources for training are typically limited in quantity compared to the 2D images counterpart. In this work, we deal with the data scarcity challenge of 3D…
With the proliferation of edge computing, efficient AI inference on edge devices has become essential for intelligent applications such as autonomous vehicles and VR/AR. In this context, we address the problem of efficient remote object…
Metric learning projects samples into an embedded space, where similarities and dissimilarities are quantified based on their learned representations. However, existing methods often rely on label-guided representation learning, where…
Knowledge distillation addresses the problem of transferring knowledge from a teacher model to a student model. In this process, we typically have multiple types of knowledge extracted from the teacher model. The problem is to make full use…
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…
Vision-language models (VLMs) pre-trained on large-scale image-text pairs have demonstrated impressive transferability on various visual tasks. Transferring knowledge from such powerful VLMs is a promising direction for building effective…
Semantic segmentation is the problem of assigning a class label to every pixel in an image, and is an important component of an autonomous vehicle vision stack for facilitating scene understanding and object detection. However, many of the…
LiDAR odometry estimation and 3D semantic segmentation are crucial for autonomous driving, which has achieved remarkable advances recently. However, these tasks are challenging due to the imbalance of points in different semantic categories…
We propose CLIP-Lite, an information efficient method for visual representation learning by feature alignment with textual annotations. Compared to the previously proposed CLIP model, CLIP-Lite requires only one negative image-text sample…
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…
We introduce Elastic Looped Transformers (ELT), a highly parameter-efficient class of visual generative models based on a recurrent transformer architecture. While conventional generative models rely on deep stacks of unique transformer…
LiDAR point cloud semantic segmentation plays a crucial role in autonomous driving. In recent years, semi-supervised methods have gained popularity due to their significant reduction in annotation labor and time costs. Current…
Panoptic segmentation of point clouds is a crucial task that enables autonomous vehicles to comprehend their vicinity using their highly accurate and reliable LiDAR sensors. Existing top-down approaches tackle this problem by either…
Contrastive Language-Image Pre-training (CLIP) has achieved excellent performance over a wide range of tasks. However, the effectiveness of CLIP heavily relies on a substantial corpus of pre-training data, resulting in notable consumption…
Knowledge distillation becomes a de facto standard to improve the performance of small neural networks. Most of the previous works propose to regress the representational features from the teacher to the student in a one-to-one spatial…
Deep neural networks have enabled major progresses in semantic segmentation. However, even the most advanced neural architectures suffer from important limitations. First, they are vulnerable to catastrophic forgetting, i.e. they perform…