Artificial Intelligence

---

Factor Graph Attention (1904.05880v1)

Idan Schwartz, Seunghak Yu, Tamir Hazan, Alexander Schwing

2019-04-11

Dialog is an effective way to exchange information, but subtle details and nuances are extremely important. While significant progress has paved a path to address visual dialog with algorithms, details and nuances remain a challenge. Attention mechanisms have demonstrated compelling results to extract details in visual question answering and also provide a convincing framework for visual dialog due to their interpretability and effectiveness. However, the many data utilities that accompany visual dialog challenge existing attention techniques. We address this issue and develop a general attention mechanism for visual dialog which operates on any number of data utilities. To this end, we design a factor graph based attention mechanism which combines any number of utility representations. We illustrate the applicability of the proposed approach on the challenging and recently introduced VisDial datasets, outperforming recent state-of-the-art methods by 1.1% for VisDial0.9 and by 2% for VisDial1.0 on MRR. Our ensemble model improved the MRR score on VisDial1.0 by more than 6%.

Two Body Problem: Collaborative Visual Task Completion (1904.05879v1)

Unnat Jain, Luca Weihs, Eric Kolve, Mohammad Rastegari, Svetlana Lazebnik, Ali Farhadi, Alexander Schwing, Aniruddha Kembhavi

2019-04-11

Collaboration is a necessary skill to perform tasks that are beyond one agent's capabilities. Addressed extensively in both conventional and modern AI, multi-agent collaboration has often been studied in the context of simple grid worlds. We argue that there are inherently visual aspects to collaboration which should be studied in visually rich environments. A key element in collaboration is communication that can be either explicit, through messages, or implicit, through perception of the other agents and the visual world. Learning to collaborate in a visual environment entails learning (1) to perform the task, (2) when and what to communicate, and (3) how to act based on these communications and the perception of the visual world. In this paper we study the problem of learning to collaborate directly from pixels in AI2-THOR and demonstrate the benefits of explicit and implicit modes of communication to perform visual tasks. Refer to our project page for more details: https://prior.allenai.org/projects/two-body-problem

A Simple Baseline for Audio-Visual Scene-Aware Dialog (1904.05876v1)

Idan Schwartz Alexander Schwing, Tamir Hazan and

2019-04-11

The recently proposed audio-visual scene-aware dialog task paves the way to a more data-driven way of learning virtual assistants, smart speakers and car navigation systems. However, very little is known to date about how to effectively extract meaningful information from a plethora of sensors that pound the computational engine of those devices. Therefore, in this paper, we provide and carefully analyze a simple baseline for audio-visual scene-aware dialog which is trained end-to-end. Our method differentiates in a data-driven manner useful signals from distracting ones using an attention mechanism. We evaluate the proposed approach on the recently introduced and challenging audio-visual scene-aware dataset, and demonstrate the key features that permit to outperform the current state-of-the-art by more than 20% on CIDEr.

Three-Dimensional Dose Prediction for Lung IMRT Patients with Deep Neural Networks: Robust Learning from Heterogeneous Beam Configurations (1812.06934v2)

Ana M. Barragan-Montero, Dan Nguyen, Weiguo Lu, Mu-Han Lin, Xavier Geets, Edmond Sterpin, Steve Jiang

2018-12-17

The use of neural networks to directly predict three-dimensional dose distributions for automatic planning is becoming popular. However, the existing methods only use patient anatomy as input and assume consistent beam configuration for all patients in the training database. The purpose of this work is to develop a more general model that, in addition to patient anatomy, also considers variable beam configurations, to achieve a more comprehensive automatic planning with a potentially easier clinical implementation, without the need of training specific models for different beam settings.

Variational Information Distillation for Knowledge Transfer (1904.05835v1)

Sungsoo Ahn, Shell Xu Hu, Andreas Damianou, Neil D. Lawrence, Zhenwen Dai

2019-04-11

Transferring knowledge from a teacher neural network pretrained on the same or a similar task to a student neural network can significantly improve the performance of the student neural network. Existing knowledge transfer approaches match the activations or the corresponding hand-crafted features of the teacher and the student networks. We propose an information-theoretic framework for knowledge transfer which formulates knowledge transfer as maximizing the mutual information between the teacher and the student networks. We compare our method with existing knowledge transfer methods on both knowledge distillation and transfer learning tasks and show that our method consistently outperforms existing methods. We further demonstrate the strength of our method on knowledge transfer across heterogeneous network architectures by transferring knowledge from a convolutional neural network (CNN) to a multi-layer perceptron (MLP) on CIFAR-10. The resulting MLP significantly outperforms the-state-of-the-art methods and it achieves similar performance to the CNN with a single convolutional layer.

Learning Classical Planning Strategies with Policy Gradient (1810.09923v2)

Pawel Gomoluch, Dalal Alrajeh, Alessandra Russo

2018-10-23

A common paradigm in classical planning is heuristic forward search. Forward search planners often rely on simple best-first search which remains fixed throughout the search process. In this paper, we introduce a novel search framework capable of alternating between several forward search approaches while solving a particular planning problem. Selection of the approach is performed using a trainable stochastic policy, mapping the state of the search to a probability distribution over the approaches. This enables using policy gradient to learn search strategies tailored to a specific distributions of planning problems and a selected performance metric, e.g. the IPC score. We instantiate the framework by constructing a policy space consisting of five search approaches and a two-dimensional representation of the planner's state. Then, we train the system on randomly generated problems from five IPC domains using three different performance metrics. Our experimental results show that the learner is able to discover domain-specific search strategies, improving the planner's performance relative to the baselines of plain best-first search and a uniform policy.

Relational Graph Attention Networks (1904.05811v1)

Dan Busbridge, Dane Sherburn, Pietro Cavallo, Nils Y. Hammerla

2019-04-11

We investigate Relational Graph Attention Networks, a class of models that extends non-relational graph attention mechanisms to incorporate relational information, opening up these methods to a wider variety of problems. A thorough evaluation of these models is performed, and comparisons are made against established benchmarks. To provide a meaningful comparison, we retrain Relational Graph Convolutional Networks, the spectral counterpart of Relational Graph Attention Networks, and evaluate them under the same conditions. We find that Relational Graph Attention Networks perform worse than anticipated, although some configurations are marginally beneficial for modelling molecular properties. We provide insights as to why this may be, and suggest both modifications to evaluation strategies, as well as directions to investigate for future work.

YUVMultiNet: Real-time YUV multi-task CNN for autonomous driving (1904.05673v1)

Thomas Boulay, Said El-Hachimi, Mani Kumar Surisetti, Pullarao Maddu, Saranya Kandan

2019-04-11

In this paper, we propose a multi-task convolutional neural network (CNN) architecture optimized for a low power automotive grade SoC. We introduce a network based on a unified architecture where the encoder is shared among the two tasks namely detection and segmentation. The pro-posed network runs at 25FPS for 1280x800 resolution. We briefly discuss the methods used to optimize the network architecture such as using native YUV image directly, optimization of layers & feature maps and applying quantization. We also focus on memory bandwidth in our design as convolutions are data intensives and most SOCs are bandwidth bottlenecked. We then demonstrate the efficiency of our proposed network for a dedicated CNN accelerators presenting the key performance indicators (KPI) for the detection and segmentation tasks obtained from the hardware execution and the corresponding run-time.

Multi-lingual Dialogue Act Recognition with Deep Learning Methods (1904.05606v1)

Jiří Martínek, Pavel Král, Ladislav Lenc, Christophe Cerisara

2019-04-11

This paper deals with multi-lingual dialogue act (DA) recognition. The proposed approaches are based on deep neural networks and use word2vec embeddings for word representation. Two multi-lingual models are proposed for this task. The first approach uses one general model trained on the embeddings from all available languages. The second method trains the model on a single pivot language and a linear transformation method is used to project other languages onto the pivot language. The popular convolutional neural network and LSTM architectures with different set-ups are used as classifiers. To the best of our knowledge this is the first attempt at multi-lingual DA recognition using neural networks. The multi-lingual models are validated experimentally on two languages from the Verbmobil corpus.

Ontologies-based Architecture for Sociocultural Knowledge Co-Construction Systems (1904.05596v1)

Guidedi Kaladzavi, Papa Fary Diallo, Cedric Béré, Olivier Corby, Isabelle Mirbel, Moussa Lo, Dina Taiwe Kolyang

2019-04-11

Considering the evolution of the semantic wiki engine based platforms, two main approaches could be distinguished: Ontologies for Wikis (OfW) and Wikis for Ontologies (WfO). OfW vision requires existing ontologies to be imported. Most of them use the RDF-based (Resource Description Framework) systems in conjunction with the standard SQL (Structured Query Language) database to manage and query semantic data. But, relational database is not an ideal type of storage for semantic data. A more natural data model for SMW (Semantic MediaWiki) is RDF, a data format that organizes information in graphs rather than in fixed database tables. This paper presents an ontology based architecture, which aims to implement this idea. The architecture mainly includes three layered functional architectures: Web User Interface Layer, Semantic Layer and Persistence Layer.

---