Related papers: LidarNAS: Unifying and Searching Neural Architectu…

Binary Neural Networks (BNNs) have gained extensive attention for their superior inferencing efficiency and compression ratio compared to traditional full-precision networks. However, due to the unique characteristics of BNNs, designing a…

Recently, neural architecture search (NAS) has been exploited to design feature pyramid networks (FPNs) and achieved promising results for visual object detection. Encouraged by the success, we propose a novel One-Shot Path Aggregation…

Point cloud stands as the most widely adopted format for representing 3D shapes and scenes due to its simplicity and geometric fidelity. However, its inherent unordered and irregular nature, exacerbated by sensor noise and occlusions,…

We propose a method for joint detection and tracking of multiple objects in 3D point clouds, a task conventionally treated as a two-step process comprising object detection followed by data association. Our method embeds both steps into a…

Neural architecture search has shown its great potential in various areas recently. However, existing methods rely heavily on a black-box controller to search architectures, which suffers from the serious problem of lacking…

Differentiable architecture search has gradually become the mainstream research topic in the field of Neural Architecture Search (NAS) for its high efficiency compared with the early NAS methods. Recent differentiable NAS also aims at…

Current neural architecture search (NAS) algorithms still require expert knowledge and effort to design a search space for network construction. In this paper, we consider automating the search space design to minimize human interference,…

We revisit the one-shot Neural Architecture Search (NAS) paradigm and analyze its advantages over existing NAS approaches. Existing one-shot method, however, is hard to train and not yet effective on large scale datasets like ImageNet. This…

We develop a Neural Architecture Search (NAS) framework for CycleGAN that carries out unpaired image-to-image translation task. Extending previous NAS techniques for Generative Adversarial Networks (GANs) to CycleGAN is not straightforward…

The recent breakthroughs of Neural Architecture Search (NAS) have motivated various applications in medical image segmentation. However, most existing work either simply rely on hyper-parameter tuning or stick to a fixed network backbone,…

In this paper, we investigate a new variant of neural architecture search (NAS) paradigm -- searching with random labels (RLNAS). The task sounds counter-intuitive for most existing NAS algorithms since random label provides few information…

Edge computing aims to enable edge devices, such as IoT devices, to process data locally instead of relying on the cloud. However, deep learning techniques like computer vision and natural language processing can be computationally…

Over the past few years, there has been remarkable progress in research on 3D point clouds and their use in autonomous driving scenarios has become widespread. However, deep learning methods heavily rely on annotated data and often face…

Visual data in autonomous driving perception, such as camera image and LiDAR point cloud, can be interpreted as a mixture of two aspects: semantic feature and geometric structure. Semantics come from the appearance and context of objects to…

As deep neural networks achieve unprecedented performance in various tasks, neural architecture search (NAS), a research field for designing neural network architectures with automated processes, is actively underway. More recently,…

Panoptic segmentation is posed as a new popular test-bed for the state-of-the-art holistic scene understanding methods with the requirement of simultaneously segmenting both foreground things and background stuff. The state-of-the-art…

In class-incremental learning, a model learns continuously from a sequential data stream in which new classes occur. Existing methods often rely on static architectures that are manually crafted. These methods can be prone to capacity…

Unified segmentation of 3D point clouds is crucial for scene understanding, but is hindered by its sparse structure, limited annotations, and the challenge of distinguishing fine-grained object classes in complex environments. Existing…

Neural architecture search (NAS), the study of automating the discovery of optimal deep neural network architectures for tasks in domains such as computer vision and natural language processing, has seen rapid growth in the machine learning…

3D point cloud generation by the deep neural network from a single image has been attracting more and more researchers' attention. However, recently-proposed methods require the objects be captured with relatively clean backgrounds, fixed…