Linguistic resources such as part-of-speech (POS) tags have been extensively used in statistical machine translation (SMT) frameworks and have yielded better performances. However, usage of such linguistic annotations in neural machine translation (NMT) systems has been left under-explored. In this work, we show that multi-task learning is a successful and a easy approach to introduce an additional knowledge into an end-to-end neural attentional model. By jointly training several natural language processing (NLP) tasks in one system, we are able to leverage common information and improve the performance of the individual task. We analyze the impact of three design decisions in multi-task learning: the tasks used in training, the training schedule, and the degree of parameter sharing across the tasks, which is defined by the network architecture. The experiments are conducted for an German to English translation task. As additional linguistic resources, we exploit POS information and named-entities (NE). Experiments show that the translation quality can be improved by up to 1.5 BLEU points under the low-resource condition. The performance of the POS tagger is also improved using the multi-task learning scheme.
The growing explosion in the use of surveillance cameras in public security highlights the importance of vehicle search from large-scale image databases. Precise vehicle search, aiming at finding out all instances for a given query vehicle image, is a challenging task as different vehicles will look very similar to each other if they share same visual attributes. To address this problem, we propose the Repression Network (RepNet), a novel multi-task learning framework, to learn discriminative features for each vehicle image from both coarse-grained and detailed level simultaneously. Besides, benefited from the satisfactory accuracy of attribute classification, a bucket search method is proposed to reduce the retrieval time while still maintaining competitive performance. We conduct extensive experiments on the revised VehcileID dataset. Experimental results show that our RepNet achieves the state-of-the-art performance and the bucket search method can reduce the retrieval time by about 24 times.
Transferring knowledge from a source domain to another domain is useful, especially when gathering new data is very expensive and time-consuming. Deep networks have been well-studied for question answering tasks in recent years; however, no prominent research for transfer learning through deep neural networks exists in the question answering field. In this paper, two main methods (INIT and MULT) in this field are examined. Then, a new method named Intelligent sample selection (ISS-MULT) is proposed to improve the MULT method for question answering tasks. Different datasets, specificay SQuAD, SelQA, WikiQA, NewWikiQA and InforBoxQA, are used for evaluation. Moreover, two different tasks of question answering - answer selection and answer triggering - are evaluated to examine the effectiveness of transfer learning. The results show that using transfer learning generally improves the performance if the corpora are related and are based on the same policy. In addition, using ISS-MULT could finely improve the MULT method for question answering tasks, and these improvements prove more significant in the answer triggering task.
We observe standard transfer learning can improve prediction accuracies of target tasks at the cost of lowering their prediction fairness -- a phenomenon we named discriminatory transfer. We examine prediction fairness of a standard hypothesis transfer algorithm and a standard multi-task learning algorithm, and show they both suffer discriminatory transfer on the real-world Communities and Crime data set. The presented case study introduces an interaction between fairness and transfer learning, as an extension of existing fairness studies that focus on single task learning.
Previous research on automatic pain estimation from facial expressions has focused primarily on "one-size-fits-all" metrics (such as PSPI). In this work, we focus on directly estimating each individual's self-reported visual-analog scale (VAS) pain metric, as this is considered the gold standard for pain measurement. The VAS pain score is highly subjective and context-dependent, and its range can vary significantly among different persons. To tackle these issues, we propose a novel two-stage personalized model, named DeepFaceLIFT, for automatic estimation of VAS. This model is based on (1) Neural Network and (2) Gaussian process regression models, and is used to personalize the estimation of self-reported pain via a set of hand-crafted personal features and multi-task learning. We show on the benchmark dataset for pain analysis (The UNBC-McMaster Shoulder Pain Expression Archive) that the proposed personalized model largely outperforms the traditional, unpersonalized models: the intra-class correlation improves from a baseline performance of 19\% to a personalized performance of 35\% while also providing confidence in the model\textquotesingle s estimates -- in contrast to existing models for the target task. Additionally, DeepFaceLIFT automatically discovers the pain-relevant facial regions for each person, allowing for an easy interpretation of the pain-related facial cues.
Video captioning, the task of describing the content of a video, has seen some promising improvements in recent years with sequence-to-sequence models, but accurately learning the temporal and logical dynamics involved in the task still remains a challenge, especially given the lack of sufficient annotated data. We improve video captioning by sharing knowledge with two related directed-generation tasks: a temporally-directed unsupervised video prediction task to learn richer context-aware video encoder representations, and a logically-directed language entailment generation task to learn better video-entailed caption decoder representations. For this, we present a many-to-many multi-task learning model that shares parameters across the encoders and decoders of the three tasks. We achieve significant improvements and the new state-of-the-art on several standard video captioning datasets using diverse automatic and human evaluations. We also show mutual multi-task improvements on the entailment generation task.
Past work in relation extraction has focused on binary relations in single sentences. Recent NLP inroads in high-value domains have sparked interest in the more general setting of extracting n-ary relations that span multiple sentences. In this paper, we explore a general relation extraction framework based on graph long short-term memory networks (graph LSTMs) that can be easily extended to cross-sentence n-ary relation extraction. The graph formulation provides a unified way of exploring different LSTM approaches and incorporating various intra-sentential and inter-sentential dependencies, such as sequential, syntactic, and discourse relations. A robust contextual representation is learned for the entities, which serves as input to the relation classifier. This simplifies handling of relations with arbitrary arity, and enables multi-task learning with related relations. We evaluate this framework in two important precision medicine settings, demonstrating its effectiveness with both conventional supervised learning and distant supervision. Cross-sentence extraction produced larger knowledge bases. and multi-task learning significantly improved extraction accuracy. A thorough analysis of various LSTM approaches yielded useful insight the impact of linguistic analysis on extraction accuracy.
One of the challenges in Speech Emotion Recognition (SER) "in the wild" is the large mismatch between training and test data (e.g. speakers and tasks). In order to improve the generalisation capabilities of the emotion models, we propose to use Multi-Task Learning (MTL) and use gender and naturalness as auxiliary tasks in deep neural networks. This method was evaluated in within-corpus and various cross-corpus classification experiments that simulate conditions "in the wild". In comparison to Single-Task Learning (STL) based state of the art methods, we found that our MTL method proposed improved performance significantly. Particularly, models using both gender and naturalness achieved more gains than those using either gender or naturalness separately. This benefit was also found in the high-level representations of the feature space, obtained from our method proposed, where discriminative emotional clusters could be observed.
Learning visual representations with self-supervised learning has become popular in computer vision. The idea is to design auxiliary tasks where labels are free to obtain. Most of these tasks end up providing data to learn specific kinds of invariance useful for recognition. In this paper, we propose to exploit different self-supervised approaches to learn representations invariant to (i) inter-instance variations (two objects in the same class should have similar features) and (ii) intra-instance variations (viewpoint, pose, deformations, illumination, etc). Instead of combining two approaches with multi-task learning, we argue to organize and reason the data with multiple variations. Specifically, we propose to generate a graph with millions of objects mined from hundreds of thousands of videos. The objects are connected by two types of edges which correspond to two types of invariance: "different instances but a similar viewpoint and category" and "different viewpoints of the same instance". By applying simple transitivity on the graph with these edges, we can obtain pairs of images exhibiting richer visual invariance. We use this data to train a Triplet-Siamese network with VGG16 as the base architecture and apply the learned representations to different recognition tasks. For object detection, we achieve 63.2% mAP on PASCAL VOC 2007 using Fast R-CNN (compare to 67.3% with ImageNet pre-training). For the challenging COCO dataset, our method is surprisingly close (23.5%) to the ImageNet-supervised counterpart (24.4%) using the Faster R-CNN framework. We also show that our network can perform significantly better than the ImageNet network in the surface normal estimation task.
Many popular knowledge graphs such as Freebase, YAGO or DBPedia maintain a list of non-discrete attributes for each entity. Intuitively, these attributes such as height, price or population count are able to richly characterize entities in knowledge graphs. This additional source of information may help to alleviate the inherent sparsity and incompleteness problem that are prevalent in knowledge graphs. Unfortunately, many state-of-the-art relational learning models ignore this information due to the challenging nature of dealing with non-discrete data types in the inherently binary-natured knowledge graphs. In this paper, we propose a novel multi-task neural network approach for both encoding and prediction of non-discrete attribute information in a relational setting. Specifically, we train a neural network for triplet prediction along with a separate network for attribute value regression. Via multi-task learning, we are able to learn representations of entities, relations and attributes that encode information about both tasks. Moreover, such attributes are not only central to many predictive tasks as an information source but also as a prediction target. Therefore, models that are able to encode, incorporate and predict such information in a relational learning context are highly attractive as well. We show that our approach outperforms many state-of-the-art methods for the tasks of relational triplet classification and attribute value prediction.
Estimating crowd count in densely crowded scenes is an extremely challenging task due to non-uniform scale variations. In this paper, we propose a novel end-to-end cascaded network of CNNs to jointly learn crowd count classification and density map estimation. Classifying crowd count into various groups is tantamount to coarsely estimating the total count in the image thereby incorporating a high-level prior into the density estimation network. This enables the layers in the network to learn globally relevant discriminative features which aid in estimating highly refined density maps with lower count error. The joint training is performed in an end-to-end fashion. Extensive experiments on highly challenging publicly available datasets show that the proposed method achieves lower count error and better quality density maps as compared to the recent state-of-the-art methods.
We propose a general framework for reduced-rank modeling of matrix-valued data. By applying a generalized nuclear norm penalty we can directly model low-dimensional latent variables associated with rows and columns. Our framework flexibly incorporates row and column features, smoothing kernels, and other sources of side information by penalizing deviations from the row and column models. Moreover, a large class of these models can be estimated scalably using convex optimization. The computational bottleneck in each case is one singular value decomposition per iteration of a large but easy-to-apply matrix. Our framework generalizes traditional convex matrix completion and multi-task learning methods as well as maximum a posteriori estimation under a large class of popular hierarchical Bayesian models.
Visual attributes, from simple objects (e.g., backpacks, hats) to soft-biometrics (e.g., gender, height, clothing) have proven to be a powerful representational approach for many applications such as image description and human identification. In this paper, we introduce a novel method to combine the advantages of both multi-task and curriculum learning in a visual attribute classification framework. Individual tasks are grouped based on their correlation so that two groups of strongly and weakly correlated tasks are formed. The two groups of tasks are learned in a curriculum learning setup by transferring the acquired knowledge from the strongly to the weakly correlated. The learning process within each group though, is performed in a multi-task classification setup. The proposed method learns better and converges faster than learning all the tasks in a typical multi-task learning paradigm. We demonstrate the effectiveness of our approach on the publicly available, SoBiR, VIPeR and PETA datasets and report state-of-the-art results across the board.
The topic diversity of open-domain videos leads to various vocabularies and linguistic expressions in describing video contents, and therefore, makes the video captioning task even more challenging. In this paper, we propose an unified caption framework, M&M TGM, which mines multimodal topics in unsupervised fashion from data and guides the caption decoder with these topics. Compared to pre-defined topics, the mined multimodal topics are more semantically and visually coherent and can reflect the topic distribution of videos better. We formulate the topic-aware caption generation as a multi-task learning problem, in which we add a parallel task, topic prediction, in addition to the caption task. For the topic prediction task, we use the mined topics as the teacher to train a student topic prediction model, which learns to predict the latent topics from multimodal contents of videos. The topic prediction provides intermediate supervision to the learning process. As for the caption task, we propose a novel topic-aware decoder to generate more accurate and detailed video descriptions with the guidance from latent topics. The entire learning procedure is end-to-end and it optimizes both tasks simultaneously. The results from extensive experiments conducted on the MSR-VTT and Youtube2Text datasets demonstrate the effectiveness of our proposed model. M&M TGM not only outperforms prior state-of-the-art methods on multiple evaluation metrics and on both benchmark datasets, but also achieves better generalization ability.
Pain is a complex and subjective experience that poses a number of measurement challenges. While self-report by the patient is viewed as the gold standard of pain assessment, this approach fails when patients cannot verbally communicate pain intensity or lack normal mental abilities. Here, we present a pain intensity measurement method based on physiological signals. Specifically, we implement a multi-task learning approach based on neural networks that accounts for individual differences in pain responses while still leveraging data from across the population. We test our method in a dataset containing multi-modal physiological responses to nociceptive pain.
In this work, we propose a technique that utilizes a fully convolutional network (FCN) to localize image splicing attacks. We first evaluated a single-task FCN (SFCN) trained only on the surface label. Although the SFCN is shown to provide superior performance over existing methods, it still provides a coarse localization output in certain cases. Therefore, we propose the use of a multi-task FCN (MFCN) that utilizes two output branches for multi-task learning. One branch is used to learn the surface label, while the other branch is used to learn the edge or boundary of the spliced region. We trained the networks using the CASIA v2.0 dataset, and tested the trained models on the CASIA v1.0, Columbia Uncompressed, Carvalho, and the DARPA/NIST Nimble Challenge 2016 SCI datasets. Experiments show that the SFCN and MFCN outperform existing splicing localization algorithms, and that the MFCN can achieve finer localization than the SFCN.
Speech enhancement (SE) aims to reduce noise in speech signals. Most SE techniques focus only on addressing audio information. In this work, inspired by multimodal learning, which utilizes data from different modalities, and the recent success of convolutional neural networks (CNNs) in SE, we propose an audio-visual deep CNNs (AVDCNN) SE model, which incorporates audio and visual streams into a unified network model. We also propose a multi-task learning framework for reconstructing audio and visual signals at the output layer. Precisely speaking, the proposed AVDCNN model is structured as an audio-visual encoder-decoder network, in which audio and visual data are first processed using individual CNNs, and then fused into a joint network to generate enhanced speech (the primary task) and reconstructed images (the secondary task) at the output layer. The model is trained in an end-to-end manner, and parameters are jointly learned through back-propagation. We evaluate enhanced speech using five instrumental criteria. Results show that the AVDCNN model yields a notably superior performance compared with an audio-only CNN-based SE model and two conventional SE approaches, confirming the effectiveness of integrating visual information into the SE process. In addition, the AVDCNN model also outperforms an existing audio-visual SE model, confirming its capability of effectively combining audio and visual information in SE.
For the two-stream style methods in action recognition, fusing the two streams' predictions is always by the weighted averaging scheme. This fusion method with fixed weights lacks of pertinence to different action videos and always needs trial and error on the validation set. In order to enhance the adaptability of two-stream ConvNets and improve its performance, an end-to-end trainable gated fusion method, namely gating ConvNet, for the two-stream ConvNets is proposed in this paper based on the MoE (Mixture of Experts) theory. The gating ConvNet takes the combination of feature maps from the same layer of the spatial and the temporal nets as input and adopts ReLU (Rectified Linear Unit) as the gating output activation function. To reduce the over-fitting of gating ConvNet caused by the redundancy of parameters, a new multi-task learning method is designed, which jointly learns the gating fusion weights for the two streams and learns the gating ConvNet for action classification. With our gated fusion method and multi-task learning approach, a high accuracy of 94.5% is achieved on the dataset UCF101.
Hierarchical attention networks have recently achieved remarkable performance for document classification in a given language. However, when multilingual document collections are considered, training such models separately for each language entails linear parameter growth and lack of cross-language transfer. Learning a single multilingual model with fewer parameters is therefore a challenging but potentially beneficial objective. To this end, we propose multilingual hierarchical attention networks for learning document structures, with shared encoders and/or shared attention mechanisms across languages, using multi-task learning and an aligned semantic space as input. We evaluate the proposed models on multilingual document classification with disjoint label sets, on a large dataset which we provide, with 600k news documents in 8 languages, and 5k labels. The multilingual models outperform monolingual ones in low-resource as well as full-resource settings, and use fewer parameters, thus confirming their computational efficiency and the utility of cross-language transfer.
The increased availability of high resolution satellite imagery allows to sense very detailed structures on the surface of our planet. Access to such information opens up new directions in the analysis of remote sensing imagery. However, at the same time this raises a set of new challenges for existing pixel-based prediction methods, such as semantic segmentation approaches. While deep neural networks have achieved significant advances in the semantic segmentation of high resolution images in the past, most of the existing approaches tend to produce predictions with poor boundaries. In this paper, we address the problem of preserving semantic segmentation boundaries in high resolution satellite imagery by introducing a new cascaded multi-task loss. We evaluate our approach on Inria Aerial Image Labeling Dataset which contains large-scale and high resolution images. Our results show that we are able to outperform state-of-the-art methods by 8.3\% without any additional post-processing step.