Atabak Dehban

Atabak Dehban

Auto-generated profile, based on publicly available information

Atabak Dehban

Institute for Systems and Robotics University of Lisbon Portugal

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
20 June 2016 in International Journal of Computational Intelligence and Applications
Verified
Journal Article
Closed access
DYDanial Yazdani
Danial Yazdani
ASAlireza Sepas-Moghaddam
Alireza Sepas-Moghaddam
ADAtabak Dehban
Atabak Dehban
NHNuno Horta
Nuno Horta

1 November 2019
Verified
Conference Paper
Closed access
ADAtabak Dehban
Atabak Dehban
JBJoao Borrego
Joao Borrego
RFRui Figueiredo
Rui Figueiredo
PMPlinio Moreno
Plinio Moreno
ABAlexandre Bernardino
Alexandre Bernardino
JSJosa Santos-Victor
Josa Santos-Victor
Recent advances in deep learning–based object detection techniques have revolutionized their applicability in several fields. However, since these methods rely on unwieldy and large amounts of data, a common practice is to download models pre-trained on standard datasets and fine-tune them for specific application domains with a small set of domain–relevant images. In this work, we show that using synthetic datasets that are not necessarily photo-realistic can be a better alternative to simply fine-tune pre-trained networks. Specifically, our results show an impressive 25%improvement in the mAP metric over a fine-tuning baseline when only about 200 labelled images are available to train. Finally, an ablation study of our results is presented to delineate the individual contribution of different components in the randomization pipeline.

1 July 2019 in Robotics and Autonomous Systems
Verified
Journal Article
Closed access
RFRui Figueiredo
Rui Figueiredo
ADAtabak Dehban
Atabak Dehban
PMPlinio Moreno
Plinio Moreno
Alexandre BernardinoAlexandre Bernardino
Alexandre Bernardino
JSJosé Santos-Victor
José Santos-Victor
HAHelder Araujo
Helder Araujo

1 May 2016
Verified
Conference Paper
Closed access
ADAtabak Dehban
Atabak Dehban
LJLorenzo Jamone
Lorenzo Jamone
AKAdam R. Kampff
Adam R. Kampff
JSJose Santos-Victor
Jose Santos-Victor
The concept of affordances facilitates the encoding of relations between actions and effects in an environment centered around the agent. Such an interpretation has important impacts on several cognitive capabilities and manifestations of intelligence, such as prediction and planning. In this paper, a new framework based on denoising Auto-encoders (dA) is proposed which allows an agent to explore its environment and actively learn the affordances of objects and tools by observing the consequences of acting on them. The dA serves as a unified framework to fuse multi-modal data and retrieve an entire missing modality or a feature within a modality given information about other modalities. This work has two major contributions. First, since training the dA is done in continuous space, there will be no need to discretize the dataset and higher accuracies in inference can be achieved with respect to approaches in which data discretization is required (e.g. Bayesian networks). Second, by fixing the structure of the dA, knowledge can be added incrementally making the architecture particularly useful in online learning scenarios. Evaluation scores of real and simulated robotic experiments show improvements over previous approaches while the new model can be applied in a wider range of domains.

1 April 2018
Verified
Conference Paper
Closed access
JBJoao Borrego
Joao Borrego
RFRui Figueiredo
Rui Figueiredo
ADAtabak Dehban
Atabak Dehban
Plinio MorenoPlinio Moreno
Plinio Moreno
Alexandre BernardinoAlexandre Bernardino
Alexandre Bernardino
JSJose Santos-Victor
Jose Santos-Victor
The impressive results of applying deep neural networks in tasks such as object recognition, language translation, and solving digital games are largely attributed to the availability of massive amounts of high quality labelled data. However, despite numerous promising steps in incorporating these techniques in robotic tasks, the cost of gathering data with a real robot has halted the proliferation of deep learning in robotics. In this work, a plugin for the Gazebo simulator is presented, which allows rapid generation of synthetic data. By introducing variations in simulator-specific or irrelevant aspects of a task, one can train a model which exhibits some degree of robustness against those aspects, and ultimately narrow the reality gap between simulated and real-world data. To show a use-case of the developed software, we build a new dataset for detection and localisation of three object classes: box, cylinder and sphere. Our results in the object detection and localisation task demonstrate that with small datasets generated only in simulation, one can achieve comparable performance to that achieved when training on real-world images.

1 November 2017
Verified
Conference Paper
Closed access
ADAtabak Dehban
Atabak Dehban
LJLorenzo Jamone
Lorenzo Jamone
AKAdam R. Kampff
Adam R. Kampff
JSJose Santos-Victor
Jose Santos-Victor
The perception of affordances provides an action-centered parametric representation of the environment. By perceiving an object's visual features in terms of what actions they afford, novel behavior opportunities can be inferred about previously unseen objects. In this paper, a flexible deep probabilistic framework is proposed which allows an explorative agent to learn tool-object affordances in continuous space. To this end, we use a deep variational auto-encoder with heterogeneous probabilistic distributions to infer the most probable action that achieves a desired effect or to predict a parametric probability distribution over action consequences i.e. effects. Our experiments show the generalization of the method to unseen objects and tools and we have analyzed the influence of different design choices. Our framework goes beyond other proposals by incorporating various probability distributions tailored for each individual modality and by eliminating the need for any pre-processing of the data.