Paper Group ANR 683
Q-Search Trees: An Information-Theoretic Approach Towards Hierarchical Abstractions for Agents with Computational Limitations. Generative Continual Concept Learning. Development of a Robotic System for Automatic Wheel Removal and Fitting. Continual Learning of New Sound Classes using Generative Replay. Can Neural Networks Learn Symbolic Rewriting?. …
Q-Search Trees: An Information-Theoretic Approach Towards Hierarchical Abstractions for Agents with Computational Limitations
| Title | Q-Search Trees: An Information-Theoretic Approach Towards Hierarchical Abstractions for Agents with Computational Limitations |
| Authors | Daniel T. Larsson, Dipankar Maity, Panagiotis Tsiotras |
| Abstract | In this paper, we develop a framework to obtain graph abstractions for decision-making by an agent where the abstractions emerge as a function of the agent’s limited computational resources. We discuss the connection of the proposed approach with information-theoretic signal compression, and formulate a novel optimization problem to obtain tree-based abstractions as a function of the agent’s computational resources. The structural properties of the new problem are discussed in detail, and two algorithmic approaches are proposed to obtain solutions to this optimization problem. We discuss the quality of, and prove relationships between, solutions obtained by the two proposed algorithms. The framework is demonstrated to generate a hierarchy of abstractions for a non-trivial environment. |
| Tasks | Decision Making |
| Published | 2019-09-30 |
| URL | https://arxiv.org/abs/1910.00063v1 |
| https://arxiv.org/pdf/1910.00063v1.pdf | |
| PWC | https://paperswithcode.com/paper/q-search-trees-an-information-theoretic |
| Repo | |
| Framework | |
Generative Continual Concept Learning
| Title | Generative Continual Concept Learning |
| Authors | Mohammad Rostami, Soheil Kolouri, James McClelland, Praveen Pilly |
| Abstract | After learning a concept, humans are also able to continually generalize their learned concepts to new domains by observing only a few labeled instances without any interference with the past learned knowledge. In contrast, learning concepts efficiently in a continual learning setting remains an open challenge for current Artificial Intelligence algorithms as persistent model retraining is necessary. Inspired by the Parallel Distributed Processing learning and the Complementary Learning Systems theories, we develop a computational model that is able to expand its previously learned concepts efficiently to new domains using a few labeled samples. We couple the new form of a concept to its past learned forms in an embedding space for effective continual learning. Doing so, a generative distribution is learned such that it is shared across the tasks in the embedding space and models the abstract concepts. This procedure enables the model to generate pseudo-data points to replay the past experience to tackle catastrophic forgetting. |
| Tasks | Continual Learning |
| Published | 2019-06-10 |
| URL | https://arxiv.org/abs/1906.03744v2 |
| https://arxiv.org/pdf/1906.03744v2.pdf | |
| PWC | https://paperswithcode.com/paper/generative-continual-concept-learning |
| Repo | |
| Framework | |
Development of a Robotic System for Automatic Wheel Removal and Fitting
| Title | Development of a Robotic System for Automatic Wheel Removal and Fitting |
| Authors | Gideon Gbenga Oladipupo |
| Abstract | This paper discusses the image processing and computer vision algorithms for real time detection and tracking of a sample wheel of a vehicle. During the manual tyre changing process, spinal and other muscular injuries are common and even more serious injuries have been recorded when occasionally, tyres fail (burst) during this process. It, therefore, follows that the introduction of a robotic system to take over this process would be a welcome development. This work discusses various useful applicable algorithms, Circular Hough Transform (CHT) as well as Continuously adaptive mean shift (Camshift) and provides some of the software solutions which can be deployed with a robotic mechanical arm to make the task of tyre changing faster, safer and more efficient. Image acquisition and software to accurately detect and classify specific objects of interest were implemented successfully, outcomes were discussed and areas for further studies suggested. |
| Tasks | |
| Published | 2019-08-19 |
| URL | https://arxiv.org/abs/1908.09009v1 |
| https://arxiv.org/pdf/1908.09009v1.pdf | |
| PWC | https://paperswithcode.com/paper/development-of-a-robotic-system-for-automatic |
| Repo | |
| Framework | |
Continual Learning of New Sound Classes using Generative Replay
| Title | Continual Learning of New Sound Classes using Generative Replay |
| Authors | Zhepei Wang, Cem Subakan, Efthymios Tzinis, Paris Smaragdis, Laurent Charlin |
| Abstract | Continual learning consists in incrementally training a model on a sequence of datasets and testing on the union of all datasets. In this paper, we examine continual learning for the problem of sound classification, in which we wish to refine already trained models to learn new sound classes. In practice one does not want to maintain all past training data and retrain from scratch, but naively updating a model with new data(sets) results in a degradation of already learned tasks, which is referred to as “catastrophic forgetting.” We develop a generative replay procedure for generating training audio spectrogram data, in place of keeping older training datasets. We show that by incrementally refining a classifier with generative replay a generator that is 4% of the size of all previous training data matches the performance of refining the classifier keeping 20% of all previous training data. We thus conclude that we can extend a trained sound classifier to learn new classes without having to keep previously used datasets. |
| Tasks | Continual Learning |
| Published | 2019-06-03 |
| URL | https://arxiv.org/abs/1906.00654v1 |
| https://arxiv.org/pdf/1906.00654v1.pdf | |
| PWC | https://paperswithcode.com/paper/190600654 |
| Repo | |
| Framework | |
Can Neural Networks Learn Symbolic Rewriting?
| Title | Can Neural Networks Learn Symbolic Rewriting? |
| Authors | Bartosz Piotrowski, Josef Urban, Chad E. Brown, Cezary Kaliszyk |
| Abstract | This work investigates if the current neural architectures are adequate for learning symbolic rewriting. Two kinds of data sets are proposed for this research – one based on automated proofs and the other being a synthetic set of polynomial terms. The experiments with use of the current neural machine translation models are performed and its results are discussed. Ideas for extending this line of research are proposed and its relevance is motivated. |
| Tasks | Machine Translation |
| Published | 2019-11-07 |
| URL | https://arxiv.org/abs/1911.04873v1 |
| https://arxiv.org/pdf/1911.04873v1.pdf | |
| PWC | https://paperswithcode.com/paper/can-neural-networks-learn-symbolic-rewriting |
| Repo | |
| Framework | |
Can Genetic Programming Do Manifold Learning Too?
| Title | Can Genetic Programming Do Manifold Learning Too? |
| Authors | Andrew Lensen, Bing Xue, Mengjie Zhang |
| Abstract | Exploratory data analysis is a fundamental aspect of knowledge discovery that aims to find the main characteristics of a dataset. Dimensionality reduction, such as manifold learning, is often used to reduce the number of features in a dataset to a manageable level for human interpretation. Despite this, most manifold learning techniques do not explain anything about the original features nor the true characteristics of a dataset. In this paper, we propose a genetic programming approach to manifold learning called GP-MaL which evolves functional mappings from a high-dimensional space to a lower dimensional space through the use of interpretable trees. We show that GP-MaL is competitive with existing manifold learning algorithms, while producing models that can be interpreted and re-used on unseen data. A number of promising future directions of research are found in the process. |
| Tasks | Dimensionality Reduction |
| Published | 2019-02-08 |
| URL | http://arxiv.org/abs/1902.02949v1 |
| http://arxiv.org/pdf/1902.02949v1.pdf | |
| PWC | https://paperswithcode.com/paper/can-genetic-programming-do-manifold-learning |
| Repo | |
| Framework | |
Attending to Emotional Narratives
| Title | Attending to Emotional Narratives |
| Authors | Zhengxuan Wu, Xiyu Zhang, Tan Zhi-Xuan, Jamil Zaki, Desmond C. Ong |
| Abstract | Attention mechanisms in deep neural networks have achieved excellent performance on sequence-prediction tasks. Here, we show that these recently-proposed attention-based mechanisms—in particular, the Transformer with its parallelizable self-attention layers, and the Memory Fusion Network with attention across modalities and time—also generalize well to multimodal time-series emotion recognition. Using a recently-introduced dataset of emotional autobiographical narratives, we adapt and apply these two attention mechanisms to predict emotional valence over time. Our models perform extremely well, in some cases reaching a performance comparable with human raters. We end with a discussion of the implications of attention mechanisms to affective computing. |
| Tasks | Emotion Recognition, Time Series |
| Published | 2019-07-08 |
| URL | https://arxiv.org/abs/1907.04197v1 |
| https://arxiv.org/pdf/1907.04197v1.pdf | |
| PWC | https://paperswithcode.com/paper/attending-to-emotional-narratives |
| Repo | |
| Framework | |
L-FGADMM: Layer-Wise Federated Group ADMM for Communication Efficient Decentralized Deep Learning
| Title | L-FGADMM: Layer-Wise Federated Group ADMM for Communication Efficient Decentralized Deep Learning |
| Authors | Anis Elgabli, Jihong Park, Sabbir Ahmed, Mehdi Bennis |
| Abstract | This article proposes a communication-efficient decentralized deep learning algorithm, coined layer-wise federated group ADMM (L-FGADMM). To minimize an empirical risk, every worker in L-FGADMM periodically communicates with two neighbors, in which the periods are separately adjusted for different layers of its deep neural network. A constrained optimization problem for this setting is formulated and solved using the stochastic version of GADMM proposed in our prior work. Numerical evaluations show that by less frequently exchanging the largest layer, L-FGADMM can significantly reduce the communication cost, without compromising the convergence speed. Surprisingly, despite less exchanged information and decentralized operations, intermittently skipping the largest layer consensus in L-FGADMM creates a regularizing effect, thereby achieving the test accuracy as high as federated learning (FL), a baseline method with the entire layer consensus by the aid of a central entity. |
| Tasks | |
| Published | 2019-11-09 |
| URL | https://arxiv.org/abs/1911.03654v1 |
| https://arxiv.org/pdf/1911.03654v1.pdf | |
| PWC | https://paperswithcode.com/paper/l-fgadmm-layer-wise-federated-group-admm-for |
| Repo | |
| Framework | |
Clustering as an Evaluation Protocol for Knowledge Embedding Representation of Categorised Multi-relational Data in the Clinical Domain
| Title | Clustering as an Evaluation Protocol for Knowledge Embedding Representation of Categorised Multi-relational Data in the Clinical Domain |
| Authors | Jianyu Liu, Hegler Tissot |
| Abstract | Learning knowledge representation is an increasingly important technology applicable in many domain-specific machine learning problems. We discuss the effectiveness of traditional Link Prediction or Knowledge Graph Completion evaluation protocol when embedding knowledge representation for categorised multi-relational data in the clinical domain. Link prediction uses to split the data into training and evaluation subsets, leading to loss of information along training and harming the knowledge representation model accuracy. We propose a Clustering Evaluation Protocol as a replacement alternative to the traditionally used evaluation tasks. We used embedding models trained by a knowledge embedding approach which has been evaluated with clinical datasets. Experimental results with Pearson and Spearman correlations show strong evidence that the novel proposed evaluation protocol is pottentially able to replace link prediction. |
| Tasks | Knowledge Graph Completion, Link Prediction |
| Published | 2019-12-29 |
| URL | https://arxiv.org/abs/2002.09473v1 |
| https://arxiv.org/pdf/2002.09473v1.pdf | |
| PWC | https://paperswithcode.com/paper/clustering-as-an-evaluation-protocol-for |
| Repo | |
| Framework | |
WikiCREM: A Large Unsupervised Corpus for Coreference Resolution
| Title | WikiCREM: A Large Unsupervised Corpus for Coreference Resolution |
| Authors | Vid Kocijan, Oana-Maria Camburu, Ana-Maria Cretu, Yordan Yordanov, Phil Blunsom, Thomas Lukasiewicz |
| Abstract | Pronoun resolution is a major area of natural language understanding. However, large-scale training sets are still scarce, since manually labelling data is costly. In this work, we introduce WikiCREM (Wikipedia CoREferences Masked) a large-scale, yet accurate dataset of pronoun disambiguation instances. We use a language-model-based approach for pronoun resolution in combination with our WikiCREM dataset. We compare a series of models on a collection of diverse and challenging coreference resolution problems, where we match or outperform previous state-of-the-art approaches on 6 out of 7 datasets, such as GAP, DPR, WNLI, PDP, WinoBias, and WinoGender. We release our model to be used off-the-shelf for solving pronoun disambiguation. |
| Tasks | Coreference Resolution, Language Modelling |
| Published | 2019-08-21 |
| URL | https://arxiv.org/abs/1908.08025v3 |
| https://arxiv.org/pdf/1908.08025v3.pdf | |
| PWC | https://paperswithcode.com/paper/190808025 |
| Repo | |
| Framework | |
Making an Invisibility Cloak: Real World Adversarial Attacks on Object Detectors
| Title | Making an Invisibility Cloak: Real World Adversarial Attacks on Object Detectors |
| Authors | Zuxuan Wu, Ser-Nam Lim, Larry Davis, Tom Goldstein |
| Abstract | We present a systematic study of adversarial attacks on state-of-the-art object detection frameworks. Using standard detection datasets, we train patterns that suppress the objectness scores produced by a range of commonly used detectors, and ensembles of detectors. Through extensive experiments, we benchmark the effectiveness of adversarially trained patches under both white-box and black-box settings, and quantify transferability of attacks between datasets, object classes, and detector models. Finally, we present a detailed study of physical world attacks using printed posters and wearable clothes, and rigorously quantify the performance of such attacks with different metrics. |
| Tasks | Object Detection |
| Published | 2019-10-31 |
| URL | https://arxiv.org/abs/1910.14667v1 |
| https://arxiv.org/pdf/1910.14667v1.pdf | |
| PWC | https://paperswithcode.com/paper/making-an-invisibility-cloak-real-world |
| Repo | |
| Framework | |
A Survey on Active Learning and Human-in-the-Loop Deep Learning for Medical Image Analysis
| Title | A Survey on Active Learning and Human-in-the-Loop Deep Learning for Medical Image Analysis |
| Authors | Samuel Budd, Emma C Robinson, Bernhard Kainz |
| Abstract | Fully automatic deep learning has become the state-of-the-art technique for many tasks including image acquisition, analysis and interpretation, and for the extraction of clinically useful information for computer-aided detection, diagnosis, treatment planning, intervention and therapy. However, the unique challenges posed by medical image analysis suggest that retaining a human end-user in any deep learning enabled system will be beneficial. In this review we investigate the role that humans might play in the development and deployment of deep learning enabled diagnostic applications and focus on techniques that will retain a significant input from a human end user. Human-in-the-Loop computing is an area that we see as increasingly important in future research due to the safety-critical nature of working in the medical domain. We evaluate four key areas that we consider vital for deep learning in the clinical practice: (1) Active Learning - to choose the best data to annotate for optimal model performance; (2) Interpretation and Refinement - using iterative feedback to steer models to optima for a given prediction and offering meaningful ways to interpret and respond to predictions; (3) Practical considerations - developing full scale applications and the key considerations that need to be made before deployment; (4) Related Areas - research fields that will benefit human-in-the-loop computing as they evolve. We offer our opinions on the most promising directions of research and how various aspects of each area might be unified towards common goals. |
| Tasks | Active Learning |
| Published | 2019-10-07 |
| URL | https://arxiv.org/abs/1910.02923v1 |
| https://arxiv.org/pdf/1910.02923v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-survey-on-active-learning-and-human-in-the |
| Repo | |
| Framework | |
Unsupervised Domain Alignment to Mitigate Low Level Dataset Biases
| Title | Unsupervised Domain Alignment to Mitigate Low Level Dataset Biases |
| Authors | Kirthi Shankar Sivamani |
| Abstract | Dataset bias is a well-known problem in the field of computer vision. The presence of implicit bias in any image collection hinders a model trained and validated on a particular dataset to yield similar accuracies when tested on other datasets. In this paper, we propose a novel debiasing technique to reduce the effects of a biased training dataset. Our goal is to augment the training data using a generative network by learning a non-linear mapping from the source domain (training set) to the target domain (testing set) while retaining training set labels. The cycle consistency loss and adversarial loss for generative adversarial networks are used to learn the mapping. A structured similarity index (SSIM) loss is used to enforce label retention while augmenting the training set. Our methods and hypotheses are supported by quantitative comparisons with prior debiasing techniques. These comparisons showcase the superiority of our method and its potential to mitigate the effects of dataset bias during the inference stage. |
| Tasks | |
| Published | 2019-07-08 |
| URL | https://arxiv.org/abs/1907.03644v2 |
| https://arxiv.org/pdf/1907.03644v2.pdf | |
| PWC | https://paperswithcode.com/paper/unsupervised-domain-alignment-to-mitigate-low |
| Repo | |
| Framework | |
NADS-Net: A Nimble Architecture for Driver and Seat Belt Detection via Convolutional Neural Networks
| Title | NADS-Net: A Nimble Architecture for Driver and Seat Belt Detection via Convolutional Neural Networks |
| Authors | Sehyun Chun, Nima Hamidi Ghalehjegh, Joseph B. Choi, Chris W. Schwarz, John G. Gaspar, Daniel V. McGehee, Stephen S. Baek |
| Abstract | A new convolutional neural network (CNN) architecture for 2D driver/passenger pose estimation and seat belt detection is proposed in this paper. The new architecture is more nimble and thus more suitable for in-vehicle monitoring tasks compared to other generic pose estimation algorithms. The new architecture, named NADS-Net, utilizes the feature pyramid network (FPN) backbone with multiple detection heads to achieve the optimal performance for driver/passenger state detection tasks. The new architecture is validated on a new data set containing video clips of 100 drivers in 50 driving sessions that are collected for this study. The detection performance is analyzed under different demographic, appearance, and illumination conditions. The results presented in this paper may provide meaningful insights for the autonomous driving research community and automotive industry for future algorithm development and data collection. |
| Tasks | Autonomous Driving, Pose Estimation |
| Published | 2019-10-08 |
| URL | https://arxiv.org/abs/1910.03695v1 |
| https://arxiv.org/pdf/1910.03695v1.pdf | |
| PWC | https://paperswithcode.com/paper/nads-net-a-nimble-architecture-for-driver-and |
| Repo | |
| Framework | |
SoildNet: Soiling Degradation Detection in Autonomous Driving
| Title | SoildNet: Soiling Degradation Detection in Autonomous Driving |
| Authors | Arindam Das |
| Abstract | In the field of autonomous driving, camera sensors are extremely prone to soiling because they are located outside of the car and interact with environmental sources of soiling such as rain drops, snow, dust, sand, mud and so on. This can lead to either partial or complete vision degradation. Hence detecting such decay in vision is very important for safety and overall to preserve the functionality of the “autonomous” components in autonomous driving. The contribution of this work involves: 1) Designing a Deep Convolutional Neural Network (DCNN) based baseline network, 2) Exploiting several network remodelling techniques such as employing static and dynamic group convolution, channel reordering to compress the baseline architecture and make it suitable for low power embedded systems with nearly 1 TOPS, 3) Comparing various result metrics of all interim networks dedicated for soiling degradation detection at tile level of size 64 x 64 on input resolution 1280 x 768. The compressed network, is called SoildNet (Sand, snOw, raIn/dIrt, oiL, Dust/muD) that uses only 9.72% trainable parameters of the base network and reduces the model size by more than 7 times with no loss in accuracy |
| Tasks | Autonomous Driving |
| Published | 2019-11-04 |
| URL | https://arxiv.org/abs/1911.01054v2 |
| https://arxiv.org/pdf/1911.01054v2.pdf | |
| PWC | https://paperswithcode.com/paper/soildnet-soiling-degradation-detection-in |
| Repo | |
| Framework | |
