toggle visibility Search & Display Options
Select All    Deselect All [11–20] << 21 22 >>
List View
 | 
Citations
 | 
Details
  Records Links
Author Yi Xiao; Felipe Codevilla; Christopher Pal; Antonio Lopez edit   pdf
openurl 
  Title Action-Based Representation Learning for Autonomous Driving Type Conference Article
  Year 2020 Publication Conference on Robot Learning Abbreviated Journal  
  Volume Issue Pages  
  Keywords  
  Abstract Human drivers produce a vast amount of data which could, in principle, be used to improve autonomous driving systems. Unfortunately, seemingly straightforward approaches for creating end-to-end driving models that map sensor data directly into driving actions are problematic in terms of interpretability, and typically have significant difficulty dealing with spurious correlations. Alternatively, we propose to use this kind of action-based driving data for learning representations. Our experiments show that an affordance-based driving model pre-trained with this approach can leverage a relatively small amount of weakly annotated imagery and outperform pure end-to-end driving models, while being more interpretable. Further, we demonstrate how this strategy outperforms previous methods based on learning inverse dynamics models as well as other methods based on heavy human supervision (ImageNet).  
  Address virtual; November 2020  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title (down)  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference CORL  
  Notes ADAS; 600.118 Approved no  
  Call Number Admin @ si @ XCP2020 Serial 3487  
Permanent link to this record
 
 
Author Idoia Ruiz; Lorenzo Porzi; Samuel Rota Bulo; Peter Kontschieder; Joan Serrat edit   pdf
openurl 
  Title Weakly Supervised Multi-Object Tracking and Segmentation Type Conference Article
  Year 2021 Publication IEEE Winter Conference on Applications of Computer Vision Workshops Abbreviated Journal  
  Volume Issue Pages 125-133  
  Keywords  
  Abstract We introduce the problem of weakly supervised MultiObject Tracking and Segmentation, i.e. joint weakly supervised instance segmentation and multi-object tracking, in which we do not provide any kind of mask annotation.
To address it, we design a novel synergistic training strategy by taking advantage of multi-task learning, i.e. classification and tracking tasks guide the training of the unsupervised instance segmentation. For that purpose, we extract weak foreground localization information, provided by
Grad-CAM heatmaps, to generate a partial ground truth to learn from. Additionally, RGB image level information is employed to refine the mask prediction at the edges of the
objects. We evaluate our method on KITTI MOTS, the most representative benchmark for this task, reducing the performance gap on the MOTSP metric between the fully supervised and weakly supervised approach to just 12% and 12.7 % for cars and pedestrians, respectively.		  
  Address Virtual; January 2021  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title (down)  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference WACVW  
  Notes ADAS; 600.118; 600.124 Approved no  
  Call Number Admin @ si @ RPR2021 Serial 3548  
Permanent link to this record
 
 
Author Idoia Ruiz; Joan Serrat edit   pdf
url  doi
openurl 
  Title Rank-based ordinal classification Type Conference Article
  Year 2020 Publication 25th International Conference on Pattern Recognition Abbreviated Journal  
  Volume Issue Pages 8069-8076  
  Keywords  
  Abstract Differently from the regular classification task, in ordinal classification there is an order in the classes. As a consequence not all classification errors matter the same: a predicted class close to the groundtruth one is better than predicting a farther away class. To account for this, most previous works employ loss functions based on the absolute difference between the predicted and groundtruth class labels. We argue that there are many cases in ordinal classification where label values are arbitrary (for instance 1. . . C, being C the number of classes) and thus such loss functions may not be the best choice. We instead propose a network architecture that produces not a single class prediction but an ordered vector, or ranking, of all the possible classes from most to least likely. This is thanks to a loss function that compares groundtruth and predicted rankings of these class labels, not the labels themselves. Another advantage of this new formulation is that we can enforce consistency in the predictions, namely, predicted rankings come from some unimodal vector of scores with mode at the groundtruth class. We compare with the state of the art ordinal classification methods, showing
that ours attains equal or better performance, as measured by common ordinal classification metrics, on three benchmark datasets. Furthermore, it is also suitable for a new task on image aesthetics assessment, i.e. most voted score prediction. Finally, we also apply it to building damage assessment from satellite images, providing an analysis of its performance depending on the degree of imbalance of the dataset.		  
  Address Virtual; January 2021  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title (down)  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference ICPR  
  Notes ADAS; 600.118; 600.124 Approved no  
  Call Number Admin @ si @ RuS2020 Serial 3549  
Permanent link to this record
 
 
Author Yi Xiao; Felipe Codevilla; Diego Porres; Antonio Lopez edit  url
openurl 
  Title Scaling Vision-Based End-to-End Autonomous Driving with Multi-View Attention Learning Type Conference Article
  Year 2023 Publication International Conference on Intelligent Robots and Systems Abbreviated Journal  
  Volume Issue Pages  
  Keywords  
  Abstract On end-to-end driving, human driving demonstrations are used to train perception-based driving models by imitation learning. This process is supervised on vehicle signals (e.g., steering angle, acceleration) but does not require extra costly supervision (human labeling of sensor data). As a representative of such vision-based end-to-end driving models, CILRS is commonly used as a baseline to compare with new driving models. So far, some latest models achieve better performance than CILRS by using expensive sensor suites and/or by using large amounts of human-labeled data for training. Given the difference in performance, one may think that it is not worth pursuing vision-based pure end-to-end driving. However, we argue that this approach still has great value and potential considering cost and maintenance. In this paper, we present CIL++, which improves on CILRS by both processing higher-resolution images using a human-inspired HFOV as an inductive bias and incorporating a proper attention mechanism. CIL++ achieves competitive performance compared to models which are more costly to develop. We propose to replace CILRS with CIL++ as a strong vision-based pure end-to-end driving baseline supervised by only vehicle signals and trained by conditional imitation learning.  
  Address Detroit; USA; October 2023  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title (down)  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference IROS  
  Notes ADAS Approved no  
  Call Number Admin @ si @ XCP2023 Serial 3930  
Permanent link to this record
Select All    Deselect All [11–20] << 21 22 >>
List View
 | 
Citations
 | 
Details
toggle visibility
Save Citations:
Export Records: