60 citations · 83 across the 10 of their papers we have counts for
10 papers
Sanity Checks for Saliency Methods Explaining Object Detectors
Deepan Chakravarthi Padmanabhan, Paul G. Plöger, Octavio Arriaga +1
Saliency methods are frequently used to explain Deep Neural Network-based models. Adebayo et al.'s work on evaluating saliency methods for classification models illustrate certain…
DExT: Detector Explanation Toolkit
Deepan Chakravarthi Padmanabhan, Paul G. Plöger, Octavio Arriaga +1
State-of-the-art object detectors are treated as black boxes due to their highly non-linear internal computations. Even with unprecedented advancements in detector performance, the…
The VVAD-LRS3 Dataset for Visual Voice Activity Detection
Adrian Lubitz, Matias Valdenegro-Toro, Frank Kirchner
Robots are becoming everyday devices, increasing their interaction with humans. To make human-machine interaction more natural, cognitive features like Visual Voice Activity Detect…
Are Gradient-based Saliency Maps Useful in Deep Reinforcement Learning?
Matthias Rosynski, Frank Kirchner, Matias Valdenegro-Toro
Deep Reinforcement Learning (DRL) connects the classic Reinforcement Learning algorithms with Deep Neural Networks. A problem in DRL is that CNNs are black-boxes and it is hard to…
Unsupervised Difficulty Estimation with Action Scores
Octavio Arriaga, Matias Valdenegro-Toro
Evaluating difficulty and biases in machine learning models has become of extreme importance as current models are now being applied in real-world situations. In this paper we pres…
Black-Box Optimization of Object Detector Scales
Mohandass Muthuraja, Octavio Arriaga, Paul Plöger +2
Object detectors have improved considerably in the last years by using advanced CNN architectures. However, many detector hyper-parameters are generally manually tuned, or they are…
Perception for Autonomous Systems (PAZ)
Octavio Arriaga, Matias Valdenegro-Toro, Mohandass Muthuraja +2
In this paper we introduce the Perception for Autonomous Systems (PAZ) software library. PAZ is a hierarchical perception library that allow users to manipulate multiple levels of…
Evaluating Uncertainty Estimation Methods on 3D Semantic Segmentation of Point Clouds
Swaroop Bhandary K, Nico Hochgeschwender, Paul Plöger +2
Deep learning models are extensively used in various safety critical applications. Hence these models along with being accurate need to be highly reliable. One way of achieving thi…
Image Captioning and Classification of Dangerous Situations
Octavio Arriaga, Paul Plöger, Matias Valdenegro-Toro
Current robot platforms are being employed to collaborate with humans in a wide range of domestic and industrial tasks. These environments require autonomous systems that are able…
Real-time Convolutional Neural Networks for Emotion and Gender Classification
Octavio Arriaga, Matias Valdenegro-Toro, Paul Plöger
In this paper we propose an implement a general convolutional neural network (CNN) building framework for designing real-time CNNs. We validate our models by creating a real-time v…