Search
Results
-
SRFlow: Learning the Super-Resolution Space with Normalizing Flow
(2020)Lecture Notes in Computer Science ~ Computer Vision – ECCV 2020 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part VConference Paper -
Weakly Supervised 3D Object Detection from Lidar Point Cloud
(2020)Lecture Notes in Computer Science ~ Computer Vision – ECCV 2020It is laborious to manually label point cloud data for training high-quality 3D object detectors. This work proposes a weakly supervised approach for 3D object detection, only requiring a small set of weakly annotated scenes, associated with a few precisely labeled object instances. This is achieved by a two-stage architecture design. Stage-1 learns to generate cylindrical object proposals under weak supervision, i.e., only the horizontal ...Conference Paper -
Modelling the Distribution of 3D Brain MRI using a 2D Slice VAE
(2020)Lecture Notes in Computer Science ~ Medical Image Computing and Computer Assisted Intervention – MICCAI 2020Probabilistic modelling has been an essential tool in medical image analysis, especially for analyzing brain Magnetic Resonance Images (MRI). Recent deep learning techniques for estimating high-dimensional distributions, in particular Variational Autoencoders (VAEs), opened up new avenues for probabilistic modeling. Modelling of volumetric data has remained a challenge, however, because constraints on available computation and training ...Conference Paper -
Same Same but Different: Augmentation of Tiny Industrial Datasets using Generative Adversarial Networks
(2020)2020 7th Swiss Conference on Data Science (SDS)The evolution of generative adversarial networks has permitted the generation of realistic fake images which, in some cases, are indistinguishable from the real ones. Many recent works in image generation focus on learning internal image statistics via training only on a single natural image. While natural images exhibit a variability in their attributes, industrial images are often acquired in a controlled environment following a specific ...Conference Paper -
Efficient video semantic segmentation with labels propagation and refinement
(2020)2020 IEEE Winter Conference on Applications of Computer Vision (WACV)This paper tackles the problem of real-time semantic segmentation of high definition videos using a hybrid GPU-CPU approach. We propose an Efficient Video Segmentation (EVS) pipeline that combines:(i)On the CPU, a very fast optical flow method, that is used to exploit the temporal aspect of the video and propagate semantic information from one frame to the next. It runs in parallel with the GPU.(ii)On the GPU, two Convolutional Neural ...Conference Paper -
Towards Good Practice for CNN-Based Monocular Depth Estimation
(2020)Monocular depth estimation has gained increasing attention in recent years, and various techniques have been proposed to tackle this problem. In this work, we aim to provide a comprehensive study on the techniques widely used in monocular depth estimation, and examine their individual influence on the performance. More specifically, we provide a study on: 1) network architectures, including different combinations of encoders/decoders. 2) ...Conference Paper -
Action Sequence Predictions of Vehicles in Urban Environments using Map and Social Context
(2020)2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)This work studies the problem of predicting the sequence of future actions for surround vehicles in real-world driving scenarios. To this aim, we make three main contributions. The first contribution is an automatic method to convert the trajectories recorded in real-world driving scenarios to action sequences with the help of HD maps. The method enables automatic dataset creation for this task from large-scale driving data. Our second ...Conference Paper -
Group sparsity: The Hinge Between Filter Pruning and Decomposition for Network Compression
(2020)2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)In this paper, we analyze two popular network compression techniques, i.e. filter pruning and low-rank decomposition, in a unified sense. By simply changing the way the sparsity regularization is enforced, filter pruning and low-rank decomposition can be derived accordingly. This provides another flexible choice for network compression because the techniques complement each other. For example, in popular network architectures with shortcut ...Conference Paper -
Replacing Mobile Camera ISP with a Single Deep Learning Model
(2020)2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)As the popularity of mobile photography is growing constantly, lots of efforts are being invested now into building complex hand-crafted camera ISP solutions. In this work, we demonstrate that even the most sophisticated ISP pipelines can be replaced with a single end-to-end deep learning model trained without any prior knowledge about the sensor and optics used in a particular device. For this, we present PyNET, a novel pyramidal CNN ...Conference Paper -
Neural Architecture Search as Sparse Supernet
(2021)Proceedings of the AAAI Conference on Artificial IntelligenceThis paper aims at enlarging the problem of Neural Architecture Search (NAS) from Single-Path and Multi-Path Search to automated Mixed-Path Search. In particular, we model the NAS problem as a sparse supernet using a new continuous architecture representation with a mixture of sparsity constraints. The sparse supernet enables us to automatically achieve sparsely-mixed paths upon a compact set of nodes. To optimize the proposed sparse ...Conference Paper