| |
Records |
Links |
|
Author |
Sudeep Katakol; Basem Elbarashy; Luis Herranz; Joost Van de Weijer; Antonio Lopez |
|
| |
Title |
Distributed Learning and Inference with Compressed Images |
Type |
Journal Article |
| |
Year  |
2021 |
Publication |
IEEE Transactions on Image Processing |
Abbreviated Journal |
TIP |
|
| |
Volume |
30 |
Issue |
|
Pages |
3069 - 3083 |
|
| |
Keywords |
|
|
| |
Abstract |
Modern computer vision requires processing large amounts of data, both while training the model and/or during inference, once the model is deployed. Scenarios where images are captured and processed in physically separated locations are increasingly common (e.g. autonomous vehicles, cloud computing). In addition, many devices suffer from limited resources to store or transmit data (e.g. storage space, channel capacity). In these scenarios, lossy image compression plays a crucial role to effectively increase the number of images collected under such constraints. However, lossy compression entails some undesired degradation of the data that may harm the performance of the downstream analysis task at hand, since important semantic information may be lost in the process. Moreover, we may only have compressed images at training time but are able to use original images at inference time, or vice versa, and in such a case, the downstream model suffers from covariate shift. In this paper, we analyze this phenomenon, with a special focus on vision-based perception for autonomous driving as a paradigmatic scenario. We see that loss of semantic information and covariate shift do indeed exist, resulting in a drop in performance that depends on the compression rate. In order to address the problem, we propose dataset restoration, based on image restoration with generative adversarial networks (GANs). Our method is agnostic to both the particular image compression method and the downstream task; and has the advantage of not adding additional cost to the deployed models, which is particularly important in resource-limited devices. The presented experiments focus on semantic segmentation as a challenging use case, cover a broad range of compression rates and diverse datasets, and show how our method is able to significantly alleviate the negative effects of compression on the downstream visual task. |
|
| |
Address |
|
|
| |
Corporate Author |
|
Thesis |
|
|
| |
Publisher |
|
Place of Publication |
|
Editor |
|
|
| |
Language |
|
Summary Language |
|
Original Title |
|
|
| |
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
| |
Series Volume |
|
Series Issue |
|
Edition |
|
|
| |
ISSN |
|
ISBN |
|
Medium |
|
|
| |
Area |
|
Expedition |
|
Conference |
|
|
| |
Notes |
LAMP; ADAS; 600.120; 600.118 |
Approved |
no |
|
| |
Call Number |
Admin @ si @ KEH2021 |
Serial |
3543 |
|
| Permanent link to this record |
| |
|
| |
|
Author |
Daniel Hernandez; Antonio Espinosa; David Vazquez; Antonio Lopez; Juan C. Moure |
|
| |
Title |
3D Perception With Slanted Stixels on GPU |
Type |
Journal Article |
| |
Year |
2021 |
Publication |
IEEE Transactions on Parallel and Distributed Systems |
Abbreviated Journal |
TPDS |
|
| |
Volume |
32 |
Issue |
10 |
Pages |
2434-2447 |
|
| |
Keywords |
Daniel Hernandez-Juarez; Antonio Espinosa; David Vazquez; Antonio M. Lopez; Juan C. Moure |
|
| |
Abstract |
This article presents a GPU-accelerated software design of the recently proposed model of Slanted Stixels, which represents the geometric and semantic information of a scene in a compact and accurate way. We reformulate the measurement depth model to reduce the computational complexity of the algorithm, relying on the confidence of the depth estimation and the identification of invalid values to handle outliers. The proposed massively parallel scheme and data layout for the irregular computation pattern that corresponds to a Dynamic Programming paradigm is described and carefully analyzed in performance terms. Performance is shown to scale gracefully on current generation embedded GPUs. We assess the proposed methods in terms of semantic and geometric accuracy as well as run-time performance on three publicly available benchmark datasets. Our approach achieves real-time performance with high accuracy for 2048 × 1024 image sizes and 4 × 4 Stixel resolution on the low-power embedded GPU of an NVIDIA Tegra Xavier. |
|
| |
Address |
|
|
| |
Corporate Author |
|
Thesis |
|
|
| |
Publisher |
|
Place of Publication |
|
Editor |
|
|
| |
Language |
|
Summary Language |
|
Original Title |
|
|
| |
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
| |
Series Volume |
|
Series Issue |
|
Edition |
|
|
| |
ISSN |
|
ISBN |
|
Medium |
|
|
| |
Area |
|
Expedition |
|
Conference |
|
|
| |
Notes |
ADAS; 600.124; 600.118 |
Approved |
no |
|
| |
Call Number |
Admin @ si @ HEV2021 |
Serial |
3561 |
|
| Permanent link to this record |
| |
|
| |
|
Author |
Jose Luis Gomez; Gabriel Villalonga; Antonio Lopez |
|
| |
Title |
Co-Training for Deep Object Detection: Comparing Single-Modal and Multi-Modal Approaches |
Type |
Journal Article |
| |
Year |
2021 |
Publication |
Sensors |
Abbreviated Journal |
SENS |
|
| |
Volume |
21 |
Issue |
9 |
Pages |
3185 |
|
| |
Keywords |
co-training; multi-modality; vision-based object detection; ADAS; self-driving |
|
| |
Abstract |
Top-performing computer vision models are powered by convolutional neural networks (CNNs). Training an accurate CNN highly depends on both the raw sensor data and their associated ground truth (GT). Collecting such GT is usually done through human labeling, which is time-consuming and does not scale as we wish. This data-labeling bottleneck may be intensified due to domain shifts among image sensors, which could force per-sensor data labeling. In this paper, we focus on the use of co-training, a semi-supervised learning (SSL) method, for obtaining self-labeled object bounding boxes (BBs), i.e., the GT to train deep object detectors. In particular, we assess the goodness of multi-modal co-training by relying on two different views of an image, namely, appearance (RGB) and estimated depth (D). Moreover, we compare appearance-based single-modal co-training with multi-modal. Our results suggest that in a standard SSL setting (no domain shift, a few human-labeled data) and under virtual-to-real domain shift (many virtual-world labeled data, no human-labeled data) multi-modal co-training outperforms single-modal. In the latter case, by performing GAN-based domain translation both co-training modalities are on par, at least when using an off-the-shelf depth estimation model not specifically trained on the translated images. |
|
| |
Address |
|
|
| |
Corporate Author |
|
Thesis |
|
|
| |
Publisher |
|
Place of Publication |
|
Editor |
|
|
| |
Language |
|
Summary Language |
|
Original Title |
|
|
| |
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
| |
Series Volume |
|
Series Issue |
|
Edition |
|
|
| |
ISSN |
|
ISBN |
|
Medium |
|
|
| |
Area |
|
Expedition |
|
Conference |
|
|
| |
Notes |
ADAS; 600.118 |
Approved |
no |
|
| |
Call Number |
Admin @ si @ GVL2021 |
Serial |
3562 |
|
| Permanent link to this record |
| |
|
| |
|
Author |
Hannes Mueller; Andre Groeger; Jonathan Hersh; Andrea Matranga; Joan Serrat |
|
| |
Title |
Monitoring war destruction from space using machine learning |
Type |
Journal Article |
| |
Year |
2021 |
Publication |
Proceedings of the National Academy of Sciences of the United States of America |
Abbreviated Journal |
PNAS |
|
| |
Volume |
118 |
Issue |
23 |
Pages |
e2025400118 |
|
| |
Keywords |
|
|
| |
Abstract |
Existing data on building destruction in conflict zones rely on eyewitness reports or manual detection, which makes it generally scarce, incomplete, and potentially biased. This lack of reliable data imposes severe limitations for media reporting, humanitarian relief efforts, human-rights monitoring, reconstruction initiatives, and academic studies of violent conflict. This article introduces an automated method of measuring destruction in high-resolution satellite images using deep-learning techniques combined with label augmentation and spatial and temporal smoothing, which exploit the underlying spatial and temporal structure of destruction. As a proof of concept, we apply this method to the Syrian civil war and reconstruct the evolution of damage in major cities across the country. Our approach allows generating destruction data with unprecedented scope, resolution, and frequency—and makes use of the ever-higher frequency at which satellite imagery becomes available. |
|
| |
Address |
|
|
| |
Corporate Author |
|
Thesis |
|
|
| |
Publisher |
|
Place of Publication |
|
Editor |
|
|
| |
Language |
|
Summary Language |
|
Original Title |
|
|
| |
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
| |
Series Volume |
|
Series Issue |
|
Edition |
|
|
| |
ISSN |
|
ISBN |
|
Medium |
|
|
| |
Area |
|
Expedition |
|
Conference |
|
|
| |
Notes |
ADAS; 600.118 |
Approved |
no |
|
| |
Call Number |
Admin @ si @ MGH2021 |
Serial |
3584 |
|
| Permanent link to this record |
| |
|
| |
|
Author |
Cesar de Souza; Adrien Gaidon; Yohann Cabon; Naila Murray; Antonio Lopez |
|
| |
Title |
Generating Human Action Videos by Coupling 3D Game Engines and Probabilistic Graphical Models |
Type |
Journal Article |
| |
Year |
2020 |
Publication |
International Journal of Computer Vision |
Abbreviated Journal |
IJCV |
|
| |
Volume |
128 |
Issue |
|
Pages |
1505–1536 |
|
| |
Keywords |
Procedural generation; Human action recognition; Synthetic data; Physics |
|
| |
Abstract |
Deep video action recognition models have been highly successful in recent years but require large quantities of manually-annotated data, which are expensive and laborious to obtain. In this work, we investigate the generation of synthetic training data for video action recognition, as synthetic data have been successfully used to supervise models for a variety of other computer vision tasks. We propose an interpretable parametric generative model of human action videos that relies on procedural generation, physics models and other components of modern game engines. With this model we generate a diverse, realistic, and physically plausible dataset of human action videos, called PHAV for “Procedural Human Action Videos”. PHAV contains a total of 39,982 videos, with more than 1000 examples for each of 35 action categories. Our video generation approach is not limited to existing motion capture sequences: 14 of these 35 categories are procedurally-defined synthetic actions. In addition, each video is represented with 6 different data modalities, including RGB, optical flow and pixel-level semantic labels. These modalities are generated almost simultaneously using the Multiple Render Targets feature of modern GPUs. In order to leverage PHAV, we introduce a deep multi-task (i.e. that considers action classes from multiple datasets) representation learning architecture that is able to simultaneously learn from synthetic and real video datasets, even when their action categories differ. Our experiments on the UCF-101 and HMDB-51 benchmarks suggest that combining our large set of synthetic videos with small real-world datasets can boost recognition performance. Our approach also significantly outperforms video representations produced by fine-tuning state-of-the-art unsupervised generative models of videos. |
|
| |
Address |
|
|
| |
Corporate Author |
|
Thesis |
|
|
| |
Publisher |
|
Place of Publication |
|
Editor |
|
|
| |
Language |
|
Summary Language |
|
Original Title |
|
|
| |
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
| |
Series Volume |
|
Series Issue |
|
Edition |
|
|
| |
ISSN |
|
ISBN |
|
Medium |
|
|
| |
Area |
|
Expedition |
|
Conference |
|
|
| |
Notes |
ADAS; 600.124; 600.118 |
Approved |
no |
|
| |
Call Number |
Admin @ si @ SGC2019 |
Serial |
3303 |
|
| Permanent link to this record |
