Paper Group ANR 1240
Transport Triggered Array Processor for Vision Applications. Efficient Regularized Piecewise-Linear Regression Trees. Improving Object Detection with Inverted Attention. Illumination-Adaptive Person Re-identification. Towards Task-Oriented Dialogue in Mixed Domains. Designing dialogue systems: A mean, grumpy, sarcastic chatbot in the browser. Domai …
Transport Triggered Array Processor for Vision Applications
| Title | Transport Triggered Array Processor for Vision Applications |
| Authors | Mehdi Safarpour, Ilkka Hautala, Miguel Bordallo Lopez, Olli Silven |
| Abstract | Low-level sensory data processing in many Internet-of-Things (IoT) devices pursue energy efficiency by utilizing sleep modes or slowing the clocking to the minimum. To curb the share of stand-by power dissipation in those designs, near-threshold/sub-threshold operational points or ultra-low-leakage processes in fabrication are employed. Those limit the clocking rates significantly, reducing the computing throughputs of individual processing cores. In this contribution we explore compensating for the performance loss of operating in near-threshold region (Vdd =0.6V) through massive parallelization. Benefits of near-threshold operation and massive parallelism are optimum energy consumption per instruction operation and minimized memory roundtrips, respectively. The Processing Elements (PE) of the design are based on Transport Triggered Architecture. The fine grained programmable parallel solution allows for fast and efficient computation of learnable low-level features (e.g. local binary descriptors and convolutions). Other operations, including Max-pooling have also been implemented. The programmable design achieves excellent energy efficiency for Local Binary Patterns computations. |
| Tasks | |
| Published | 2019-06-10 |
| URL | https://arxiv.org/abs/1906.04258v1 |
| https://arxiv.org/pdf/1906.04258v1.pdf | |
| PWC | https://paperswithcode.com/paper/transport-triggered-array-processor-for |
| Repo | |
| Framework | |
Efficient Regularized Piecewise-Linear Regression Trees
| Title | Efficient Regularized Piecewise-Linear Regression Trees |
| Authors | Leonidas Lefakis, Oleksandr Zadorozhnyi, Gilles Blanchard |
| Abstract | We present a detailed analysis of the class of regression decision tree algorithms which employ a regulized piecewise-linear node-splitting criterion and have regularized linear models at the leaves. From a theoretic standpoint, based on Rademacher complexity framework, we present new high-probability upper bounds for the generalization error for the proposed classes of regularized regression decision tree algorithms, including LASSO-type, and $\ell_{2}$ regularization for linear models at the leaves. Theoretical result are further extended by considering a general type of variable selection procedure. Furthermore, in our work we demonstrate that the class of piecewise-linear regression trees is not only numerically stable but can be made tractable via an algorithmic implementation, presented herein, as well as with the help of modern GPU technology. Empirically, we present results on multiple datasets which highlight the strengths and potential pitfalls, of the proposed tree algorithms compared to baselines which grow trees based on piecewise constant models. |
| Tasks | |
| Published | 2019-06-29 |
| URL | https://arxiv.org/abs/1907.00275v1 |
| https://arxiv.org/pdf/1907.00275v1.pdf | |
| PWC | https://paperswithcode.com/paper/efficient-regularized-piecewise-linear |
| Repo | |
| Framework | |
Improving Object Detection with Inverted Attention
| Title | Improving Object Detection with Inverted Attention |
| Authors | Zeyi Huang, Wei Ke, Dong Huang |
| Abstract | Improving object detectors against occlusion, blur and noise is a critical step to deploy detectors in real applications. Since it is not possible to exhaust all image defects through data collection, many researchers seek to generate hard samples in training. The generated hard samples are either images or feature maps with coarse patches dropped out in the spatial dimensions. Significant overheads are required in training the extra hard samples and/or estimating drop-out patches using extra network branches. In this paper, we improve object detectors using a highly efficient and fine-grain mechanism called Inverted Attention (IA). Different from the original detector network that only focuses on the dominant part of objects, the detector network with IA iteratively inverts attention on feature maps and puts more attention on complementary object parts, feature channels and even context. Our approach (1) operates along both the spatial and channels dimensions of the feature maps; (2) requires no extra training on hard samples, no extra network parameters for attention estimation, and no testing overheads. Experiments show that our approach consistently improved both two-stage and single-stage detectors on benchmark databases. |
| Tasks | Object Detection |
| Published | 2019-03-28 |
| URL | http://arxiv.org/abs/1903.12255v1 |
| http://arxiv.org/pdf/1903.12255v1.pdf | |
| PWC | https://paperswithcode.com/paper/improving-object-detection-with-inverted |
| Repo | |
| Framework | |
Illumination-Adaptive Person Re-identification
| Title | Illumination-Adaptive Person Re-identification |
| Authors | Zelong Zeng, Zhixiang Wang, Zheng Wang, Yung-Yu Chuang, Shin’ichi Satoh |
| Abstract | Most person re-identification (ReID) approaches assume that person images are captured under relatively similar illumination conditions. In reality, long-term person retrieval is common and person images are captured under different illumination conditions at different times across a day. In this situation, the performances of existing ReID models often degrade dramatically. This paper addresses the ReID problem with illumination variations and names it as {\em Illumination-Adaptive Person Re-identification (IA-ReID)}. We propose an Illumination-Identity Disentanglement (IID) network to separate different scales of illuminations apart, while preserving individuals’ identity information. To demonstrate the illumination issue and to evaluate our network, we construct two large-scale simulated datasets with a wide range of illumination variations. Experimental results on the simulated datasets and real-world images demonstrate the effectiveness of the proposed framework. |
| Tasks | Person Re-Identification, Person Retrieval |
| Published | 2019-05-11 |
| URL | https://arxiv.org/abs/1905.04525v1 |
| https://arxiv.org/pdf/1905.04525v1.pdf | |
| PWC | https://paperswithcode.com/paper/illumination-adaptive-person-re |
| Repo | |
| Framework | |
Towards Task-Oriented Dialogue in Mixed Domains
| Title | Towards Task-Oriented Dialogue in Mixed Domains |
| Authors | Tho Luong Chi, Phuong Le-Hong |
| Abstract | This work investigates the task-oriented dialogue problem in mixed-domain settings. We study the effect of alternating between different domains in sequences of dialogue turns using two related state-of-the-art dialogue systems. We first show that a specialized state tracking component in multiple domains plays an important role and gives better results than an end-to-end task-oriented dialogue system. We then propose a hybrid system which is able to improve the belief tracking accuracy of about 28% of average absolute point on a standard multi-domain dialogue dataset. These experimental results give some useful insights for improving our commercial chatbot platform FPT.AI, which is currently deployed for many practical chatbot applications. |
| Tasks | Chatbot |
| Published | 2019-09-05 |
| URL | https://arxiv.org/abs/1909.02265v1 |
| https://arxiv.org/pdf/1909.02265v1.pdf | |
| PWC | https://paperswithcode.com/paper/towards-task-oriented-dialogue-in-mixed |
| Repo | |
| Framework | |
Designing dialogue systems: A mean, grumpy, sarcastic chatbot in the browser
| Title | Designing dialogue systems: A mean, grumpy, sarcastic chatbot in the browser |
| Authors | Suzana Ilić, Reiichiro Nakano, Ivo Hajnal |
| Abstract | In this work we explore a deep learning-based dialogue system that generates sarcastic and humorous responses from a conversation design perspective. We trained a seq2seq model on a carefully curated dataset of 3000 question-answering pairs, the core of our mean, grumpy, sarcastic chatbot. We show that end-to-end systems learn patterns very quickly from small datasets and thus, are able to transfer simple linguistic structures representing abstract concepts to unseen settings. We also deploy our LSTM-based encoder-decoder model in the browser, where users can directly interact with the chatbot. Human raters evaluated linguistic quality, creativity and human-like traits, revealing the system’s strengths, limitations and potential for future research. |
| Tasks | Chatbot, Question Answering |
| Published | 2019-09-20 |
| URL | https://arxiv.org/abs/1909.09531v1 |
| https://arxiv.org/pdf/1909.09531v1.pdf | |
| PWC | https://paperswithcode.com/paper/designing-dialogue-systems-a-mean-grumpy |
| Repo | |
| Framework | |
Domain Compression and its Application to Randomness-Optimal Distributed Goodness-of-Fit
| Title | Domain Compression and its Application to Randomness-Optimal Distributed Goodness-of-Fit |
| Authors | Jayadev Acharya, Clément L. Canonne, Yanjun Han, Ziteng Sun, Himanshu Tyagi |
| Abstract | We study goodness-of-fit of discrete distributions in the distributed setting, where samples are divided between multiple users who can only release a limited amount of information about their samples due to various information constraints. Recently, a subset of the authors showed that having access to a common random seed (i.e., shared randomness) leads to a significant reduction in the sample complexity of this problem. In this work, we provide a complete understanding of the interplay between the amount of shared randomness available, the stringency of information constraints, and the sample complexity of the testing problem by characterizing a tight trade-off between these three parameters. We provide a general distributed goodness-of-fit protocol that as a function of the amount of shared randomness interpolates smoothly between the private- and public-coin sample complexities. We complement our upper bound with a general framework to prove lower bounds on the sample complexity of this testing problems under limited shared randomness. Finally, we instantiate our bounds for the two archetypal information constraints of communication and local privacy, and show that our sample complexity bounds are optimal as a function of all the parameters of the problem, including the amount of shared randomness. A key component of our upper bounds is a new primitive of domain compression, a tool that allows us to map distributions to a much smaller domain size while preserving their pairwise distances, using a limited amount of randomness. |
| Tasks | |
| Published | 2019-07-20 |
| URL | https://arxiv.org/abs/1907.08743v1 |
| https://arxiv.org/pdf/1907.08743v1.pdf | |
| PWC | https://paperswithcode.com/paper/domain-compression-and-its-application-to |
| Repo | |
| Framework | |
Retrieving Multi-Entity Associations: An Evaluation of Combination Modes for Word Embeddings
| Title | Retrieving Multi-Entity Associations: An Evaluation of Combination Modes for Word Embeddings |
| Authors | Gloria Feher, Andreas Spitz, Michael Gertz |
| Abstract | Word embeddings have gained significant attention as learnable representations of semantic relations between words, and have been shown to improve upon the results of traditional word representations. However, little effort has been devoted to using embeddings for the retrieval of entity associations beyond pairwise relations. In this paper, we use popular embedding methods to train vector representations of an entity-annotated news corpus, and evaluate their performance for the task of predicting entity participation in news events versus a traditional word cooccurrence network as a baseline. To support queries for events with multiple participating entities, we test a number of combination modes for the embedding vectors. While we find that even the best combination modes for word embeddings do not quite reach the performance of the full cooccurrence network, especially for rare entities, we observe that different embedding methods model different types of relations, thereby indicating the potential for ensemble methods. |
| Tasks | Word Embeddings |
| Published | 2019-05-22 |
| URL | https://arxiv.org/abs/1905.09052v1 |
| https://arxiv.org/pdf/1905.09052v1.pdf | |
| PWC | https://paperswithcode.com/paper/retrieving-multi-entity-associations-an |
| Repo | |
| Framework | |
AI-enabled Blockchain: An Outlier-aware Consensus Protocol for Blockchain-based IoT Networks
| Title | AI-enabled Blockchain: An Outlier-aware Consensus Protocol for Blockchain-based IoT Networks |
| Authors | Mehrdad Salimitari, Mohsen Joneidi, Mainak Chatterjee |
| Abstract | A new framework for a secure and robust consensus in blockchain-based IoT networks is proposed using machine learning. Hyperledger fabric, which is a blockchain platform developed as part of the Hyperledger project, though looks very apt for IoT applications, has comparatively low tolerance for malicious activities in an untrustworthy environment. To that end, we propose AI-enabled blockchain (AIBC) with a 2-step consensus protocol that uses an outlier detection algorithm for consensus in an IoT network implemented on hyperledger fabric platform. The outlier-aware consensus protocol exploits a supervised machine learning algorithm which detects anomaly activities via a learned detector in the first step. Then, the data goes through the inherent Practical Byzantine Fault Tolerance (PBFT) consensus protocol in the hyperledger fabric for ledger update. We measure and report the performance of our framework with respect to the various delay components. Results reveal that our implemented AIBC network (2-step consensus protocol) improves hyperledger fabric performance in terms of fault tolerance by marginally compromising the delay performance. |
| Tasks | Outlier Detection |
| Published | 2019-06-17 |
| URL | https://arxiv.org/abs/1906.08177v2 |
| https://arxiv.org/pdf/1906.08177v2.pdf | |
| PWC | https://paperswithcode.com/paper/an-outlier-aware-consensus-protocol-for |
| Repo | |
| Framework | |
Deep Learning Training on the Edge with Low-Precision Posits
| Title | Deep Learning Training on the Edge with Low-Precision Posits |
| Authors | Hamed F. Langroudi, Zachariah Carmichael, Dhireesha Kudithipudi |
| Abstract | Recently, the posit numerical format has shown promise for DNN data representation and compute with ultra-low precision ([5..8]-bit). However, majority of studies focus only on DNN inference. In this work, we propose DNN training using posits and compare with the floating point training. We evaluate on both MNIST and Fashion MNIST corpuses, where 16-bit posits outperform 16-bit floating point for end-to-end DNN training. |
| Tasks | |
| Published | 2019-07-30 |
| URL | https://arxiv.org/abs/1907.13216v1 |
| https://arxiv.org/pdf/1907.13216v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-learning-training-on-the-edge-with-low |
| Repo | |
| Framework | |
FairyTED: A Fair Rating Predictor for TED Talk Data
| Title | FairyTED: A Fair Rating Predictor for TED Talk Data |
| Authors | Rupam Acharyya, Shouman Das, Ankani Chattoraj, Md. Iftekhar Tanveer |
| Abstract | With the recent trend of applying machine learning in every aspect of human life, it is important to incorporate fairness into the core of the predictive algorithms. We address the problem of predicting the quality of public speeches while being fair with respect to sensitive attributes of the speakers, e.g. gender and race. We use the TED talks as an input repository of public speeches because it consists of speakers from a diverse community and has a wide outreach. Utilizing the theories of Causal Models, Counterfactual Fairness and state-of-the-art neural language models, we propose a mathematical framework for fair prediction of the public speaking quality. We employ grounded assumptions to construct a causal model capturing how different attributes affect public speaking quality. This causal model contributes in generating counterfactual data to train a fair predictive model. Our framework is general enough to utilize any assumption within the causal model. Experimental results show that while prediction accuracy is comparable to recent work on this dataset, our predictions are counterfactually fair with respect to a novel metric when compared to true data labels. The FairyTED setup not only allows organizers to make informed and diverse selection of speakers from the unobserved counterfactual possibilities but it also ensures that viewers and new users are not influenced by unfair and unbalanced ratings from arbitrary visitors to the www.ted.com website when deciding to view a talk. |
| Tasks | |
| Published | 2019-11-25 |
| URL | https://arxiv.org/abs/1911.11558v1 |
| https://arxiv.org/pdf/1911.11558v1.pdf | |
| PWC | https://paperswithcode.com/paper/fairyted-a-fair-rating-predictor-for-ted-talk |
| Repo | |
| Framework | |
Machine Learning Based Prediction and Classification of Computational Jobs in Cloud Computing Centers
| Title | Machine Learning Based Prediction and Classification of Computational Jobs in Cloud Computing Centers |
| Authors | Zheqi Zhu, Pingyi Fan |
| Abstract | With the rapid growth of the data volume and the fast increasing of the computational model complexity in the scenario of cloud computing, it becomes an important topic that how to handle users’ requests by scheduling computational jobs and assigning the resources in data center. In order to have a better perception of the computing jobs and their requests of resources, we analyze its characteristics and focus on the prediction and classification of the computing jobs with some machine learning approaches. Specifically, we apply LSTM neural network to predict the arrival of the jobs and the aggregated requests for computing resources. Then we evaluate it on Google Cluster dataset and it shows that the accuracy has been improved compared to the current existing methods. Additionally, to have a better understanding of the computing jobs, we use an unsupervised hierarchical clustering algorithm, BIRCH, to make classification and get some interpretability of our results in the computing centers. |
| Tasks | |
| Published | 2019-03-09 |
| URL | http://arxiv.org/abs/1903.03759v1 |
| http://arxiv.org/pdf/1903.03759v1.pdf | |
| PWC | https://paperswithcode.com/paper/machine-learning-based-prediction-and |
| Repo | |
| Framework | |
End-to-End Discriminative Deep Network for Liver Lesion Classification
| Title | End-to-End Discriminative Deep Network for Liver Lesion Classification |
| Authors | Francisco Perdigon Romero, Andre Diler, Gabriel Bisson-Gregoire, Simon Turcotte, Real Lapointe, Franck Vandenbroucke-Menu, An Tang, Samuel Kadoury |
| Abstract | Colorectal liver metastasis is one of most aggressive liver malignancies. While the definition of lesion type based on CT images determines the diagnosis and therapeutic strategy, the discrimination between cancerous and non-cancerous lesions are critical and requires highly skilled expertise, experience and time. In the present work we introduce an end-to-end deep learning approach to assist in the discrimination between liver metastases from colorectal cancer and benign cysts in abdominal CT images of the liver. Our approach incorporates the efficient feature extraction of InceptionV3 combined with residual connections and pre-trained weights from ImageNet. The architecture also includes fully connected classification layers to generate a probabilistic output of lesion type. We use an in-house clinical biobank with 230 liver lesions originating from 63 patients. With an accuracy of 0.96 and a F1-score of 0.92, the results obtained with the proposed approach surpasses state of the art methods. Our work provides the basis for incorporating machine learning tools in specialized radiology software to assist physicians in the early detection and treatment of liver lesions. |
| Tasks | |
| Published | 2019-01-28 |
| URL | http://arxiv.org/abs/1901.09483v1 |
| http://arxiv.org/pdf/1901.09483v1.pdf | |
| PWC | https://paperswithcode.com/paper/end-to-end-discriminative-deep-network-for |
| Repo | |
| Framework | |
Q8BERT: Quantized 8Bit BERT
| Title | Q8BERT: Quantized 8Bit BERT |
| Authors | Ofir Zafrir, Guy Boudoukh, Peter Izsak, Moshe Wasserblat |
| Abstract | Recently, pre-trained Transformer based language models such as BERT and GPT, have shown great improvement in many Natural Language Processing (NLP) tasks. However, these models contain a large amount of parameters. The emergence of even larger and more accurate models such as GPT2 and Megatron, suggest a trend of large pre-trained Transformer models. However, using these large models in production environments is a complex task requiring a large amount of compute, memory and power resources. In this work we show how to perform quantization-aware training during the fine-tuning phase of BERT in order to compress BERT by $4\times$ with minimal accuracy loss. Furthermore, the produced quantized model can accelerate inference speed if it is optimized for 8bit Integer supporting hardware. |
| Tasks | Quantization |
| Published | 2019-10-14 |
| URL | https://arxiv.org/abs/1910.06188v2 |
| https://arxiv.org/pdf/1910.06188v2.pdf | |
| PWC | https://paperswithcode.com/paper/q8bert-quantized-8bit-bert |
| Repo | |
| Framework | |
Guided Weak Supervision for Action Recognition with Scarce Data to Assess Skills of Children with Autism
| Title | Guided Weak Supervision for Action Recognition with Scarce Data to Assess Skills of Children with Autism |
| Authors | Prashant Pandey, Prathosh AP, Manu Kohli, Josh Pritchard |
| Abstract | Diagnostic and intervention methodologies for skill assessment of autism typically requires a clinician repetitively initiating several stimuli and recording the child’s response. In this paper, we propose to automate the response measurement through video recording of the scene following the use of Deep Neural models for human action recognition from videos. However, supervised learning of neural networks demand large amounts of annotated data that are hard to come by. This issue is addressed by leveraging the `similarities’ between the action categories in publicly available large-scale video action (source) datasets and the dataset of interest. A technique called guided weak supervision is proposed, where every class in the target data is matched to a class in the source data using the principle of posterior likelihood maximization. Subsequently, classifier on the target data is re-trained by augmenting samples from the matched source classes, along with a new loss encouraging inter-class separability. The proposed method is evaluated on two skill assessment autism datasets, SSBD and a real world Autism dataset comprising 37 children of different ages and ethnicity who are diagnosed with autism. Our proposed method is found to improve the performance of the state-of-the-art multi-class human action recognition models in-spite of supervision with scarce data. | |
| Tasks | Temporal Action Localization |
| Published | 2019-11-11 |
| URL | https://arxiv.org/abs/1911.04140v3 |
| https://arxiv.org/pdf/1911.04140v3.pdf | |
| PWC | https://paperswithcode.com/paper/guided-weak-supervision-for-action |
| Repo | |
| Framework | |
