Related papers: A Dynamic Feature Interaction Framework for Multi-…

Multitask learning has shown promising performance in many applications and many multitask models have been proposed. In order to identify an effective multitask model for a given multitask problem, we propose a learning framework called…

In recent years, Fully Convolutional Networks (FCN) has been widely used in various semantic segmentation tasks, including multi-modal remote sensing imagery. How to fuse multi-modal data to improve the segmentation performance has always…

Recent advancements in perception for autonomous driving are driven by deep learning. In order to achieve robust and accurate scene understanding, autonomous vehicles are usually equipped with different sensors (e.g. cameras, LiDARs,…

3D multi-object tracking (MOT) and trajectory forecasting are two critical components in modern 3D perception systems. We hypothesize that it is beneficial to unify both tasks under one framework to learn a shared feature representation of…

Deep neural networks have become a standard building block for designing models that can perform multiple dense computer vision tasks such as depth estimation and semantic segmentation thanks to their ability to capture complex correlations…

As the superiority of context information gradually manifests in advanced semantic segmentation, learning to capture the compact context relationship can help to understand the complex scenes. In contrast to some previous works utilizing…

Availability of labelled data is the major obstacle to the deployment of deep learning algorithms for computer vision tasks in new domains. The fact that many frameworks adopted to solve different tasks share the same architecture suggests…

Learning multiple domains/tasks with a single model is important for improving data efficiency and lowering inference cost for numerous vision tasks, especially on resource-constrained mobile devices. However, hand-crafting a…

Multi-task learning aims to improve generalization performance of multiple prediction tasks by appropriately sharing relevant information across them. In the context of deep neural networks, this idea is often realized by hand-designed…

Spatial redundancy widely exists in visual recognition tasks, i.e., discriminative features in an image or video frame usually correspond to only a subset of pixels, while the remaining regions are irrelevant to the task at hand. Therefore,…

Multi-task learning has proven to be effective in improving the performance of correlated tasks. Most of the existing methods use a backbone to extract initial features with independent branches for each task, and the exchange of…

Accurate detection of objects in 3D point clouds is a key problem in autonomous driving systems. Collaborative perception can incorporate information from spatially diverse sensors and provide significant benefits for improving the…

Neural architecture search has been shown to hold great promise towards the automation of deep learning. However in spite of its potential, neural architecture search remains quite costly. To this point, we propose a novel gradient-based…

We present a fast and accurate visual tracking algorithm based on the multi-domain convolutional neural network (MDNet). The proposed approach accelerates feature extraction procedure and learns more discriminative models for instance…

To better detect pedestrians of various scales, deep multi-scale methods usually detect pedestrians of different scales by different in-network layers. However, the semantic levels of features from different layers are usually inconsistent.…

Multi-modality fusion and multi-task learning are becoming trendy in 3D autonomous driving scenario, considering robust prediction and computation budget. However, naively extending the existing framework to the domain of multi-modality…

Despite the recent success of deep neural networks, it remains challenging to effectively model the long-tail class distribution in visual recognition tasks. To address this problem, we first investigate the performance bottleneck of the…

Many techniques have been developed, such as model compression, to make Deep Neural Networks (DNNs) inference more efficiently. Nevertheless, DNNs still lack excellent run-time dynamic inference capability to enable users trade-off accuracy…

We introduce MGNet, a multi-task framework for monocular geometric scene understanding. We define monocular geometric scene understanding as the combination of two known tasks: Panoptic segmentation and self-supervised monocular depth…

We propose a unified cross-domain transfer learning framework that leverages knowledge from multiple heterogeneous medical imaging datasets to improve performance across segmentation, classification, and object detection tasks. Our approach…