Current supervised methods for facial landmark detection require a large amount of training data and may suffer from overfitting to specific datasets due to the massive number of parameters. We introduce a semi-supervised method in which the crucial idea is to first generate implicit face knowledge from the large amounts of unlabeled images of faces available today. In a first, completely unsupervised stage, we train an adversarial autoencoder to reconstruct faces via a low-dimensional face embedding. In a second, supervised stage, we interleave the decoder with transfer layers to retask the generation of color images to the prediction of landmark heatmaps. Our framework (3FabRec) achieves state-of-the-art performance on several common benchmarks and, most importantly, is able to maintain impressive accuracy on extremely small training sets down to as few as 10 images. As the interleaved layers only add a low amount of parameters to the decoder, inference runs at several hundred FPS on a GPU.
Sentences produced by abstractive summarization systems can be ungrammatical and fail to preserve the original meanings, despite being locally fluent. In this paper we propose to remedy this problem by jointly generating a sentence and its syntactic dependency parse while performing abstraction. If generating a word can introduce an erroneous relation to the summary, the behavior must be discouraged. The proposed method thus holds promise for producing grammatical sentences and encouraging the summary to stay true-to-original. Our contributions of this work are twofold. First, we present a novel neural architecture for abstractive summarization that combines a sequential decoder with a tree-based decoder in a synchronized manner to generate a summary sentence and its syntactic parse. Secondly, we describe a novel human evaluation protocol to assess if, and to what extent, a summary remains true to its original meanings. We evaluate our method on a number of summarization datasets and demonstrate competitive results against strong baselines.
In this paper, we study the problem of enabling neural machine translation (NMT) to reuse previous translations from similar examples in target prediction. Distinguishing reusable translations from noisy segments and learning to reuse them in NMT are non-trivial. To solve these challenges, we propose an Example-Guided NMT (EGNMT) framework with two models: (1) a noise-masked encoder model that masks out noisy words according to word alignments and encodes the noise-masked sentences with an additional example encoder and (2) an auxiliary decoder model that predicts reusable words via an auxiliary decoder sharing parameters with the primary decoder. We define and implement the two models with the state-of-the-art Transformer. Experiments show that the noise-masked encoder model allows NMT to learn useful information from examples with low fuzzy match scores (FMS) while the auxiliary decoder model is good for high-FMS examples. More experiments on Chinese-English, English-German and English-Spanish translation demonstrate that the combination of the two EGNMT models can achieve improvements of up to +9 BLEU points over the baseline system and +7 BLEU points over a two-encoder Transformer.
Important information that relates to a specific topic in a document is often organized in tabular format to assist readers with information retrieval and comparison, which may be difficult to provide in natural language. However, tabular data in unstructured digital documents, e.g., Portable Document Format (PDF) and images, are difficult to parse into structured machine-readable format, due to complexity and diversity in their structure and style. To facilitate image-based table recognition with deep learning, we develop the largest publicly available table recognition dataset PubTabNet (https://github.com/ibm-aur-nlp/PubTabNet), containing 568k table images with corresponding structured HTML representation. PubTabNet is automatically generated by matching the XML and PDF representations of the scientific articles in PubMed Central Open Access Subset (PMCOA). We also propose a novel attention-based encoder-dual-decoder (EDD) architecture that converts images of tables into HTML code. The model has a structure decoder which reconstructs the table structure and helps the cell decoder to recognize cell content. In addition, we propose a new Tree-Edit-Distance-based Similarity (TEDS) metric for table recognition, which more appropriately captures multi-hop cell misalignment and OCR errors than the pre-established metric. The experiments demonstrate that the EDD model can accurately recognize complex tables solely relying on the image representation, outperforming the state-of-the-art by 9.7% absolute TEDS score.
We introduce PQ-NET, a deep neural network which represents and generates 3D shapes via sequential part assembly. The input to our network is a 3D shape segmented into parts, where each part is first encoded into a feature representation using a part autoencoder. The core component of PQ-NET is a sequence-to-sequence or Seq2Seq autoencoder which encodes a sequence of part features into a latent vector of fixed size, and the decoder reconstructs the 3D shape, one part at a time, resulting in a sequential assembly. The latent space formed by the Seq2Seq encoder encodes both part structure and fine part geometry. The decoder can be adapted to perform several generative tasks including shape autoencoding, interpolation, novel shape generation, and single-view 3D reconstruction, where the generated shapes are all composed of meaningful parts.
Texts like news, encyclopedias, and some social media strive for objectivity. Yet bias in the form of inappropriate subjectivity - introducing attitudes via framing, presupposing truth, and casting doubt - remains ubiquitous. This kind of bias erodes our collective trust and fuels social conflict. To address this issue, we introduce a novel testbed for natural language generation: automatically bringing inappropriately subjective text into a neutral point of view ("neutralizing" biased text). We also offer the first parallel corpus of biased language. The corpus contains 180,000 sentence pairs and originates from Wikipedia edits that removed various framings, presuppositions, and attitudes from biased sentences. Last, we propose two strong encoder-decoder baselines for the task. A straightforward yet opaque CONCURRENT system uses a BERT encoder to identify subjective words as part of the generation process. An interpretable and controllable MODULAR algorithm separates these steps, using (1) a BERT-based classifier to identify problematic words and (2) a novel join embedding through which the classifier can edit the hidden states of the encoder. Large-scale human evaluation across four domains (encyclopedias, news headlines, books, and political speeches) suggests that these algorithms are a first step towards the automatic identification and reduction of bias.
In this work, we introduce Panoptic-DeepLab, a simple, strong, and fast system for panoptic segmentation, aiming to establish a solid baseline for bottom-up methods that can achieve comparable performance of two-stage methods while yielding fast inference speed. In particular, Panoptic-DeepLab adopts the dual-ASPP and dual-decoder structures specific to semantic, and instance segmentation, respectively. The semantic segmentation branch is the same as the typical design of any semantic segmentation model (e.g., DeepLab), while the instance segmentation branch is class-agnostic, involving a simple instance center regression. As a result, our single Panoptic-DeepLab simultaneously ranks first at all three Cityscapes benchmarks, setting the new state-of-art of 84.2% mIoU, 39.0% AP, and 65.5% PQ on test set. Additionally, equipped with MobileNetV3, Panoptic-DeepLab runs nearly in real-time with a single 1025x2049 image (15.8 frames per second), while achieving a competitive performance on Cityscapes (54.1 PQ% on test set). On Mapillary Vistas test set, our ensemble of six models attains 42.7% PQ, outperforming the challenge winner in 2018 by a healthy margin of 1.5%. Finally, our Panoptic-DeepLab also performs on par with several top-down approaches on the challenging COCO dataset. For the first time, we demonstrate a bottom-up approach could deliver state-of-the-art results on panoptic segmentation.
Recurrent neural networks (RNN) are popular for many computer vision tasks, including multi-label classification. Since RNNs produce sequential outputs, labels need to be ordered for the multi-label classification task. Current approaches sort labels according to their frequency, typically ordering them in either rare-first or frequent-first. These imposed orderings do not take into account that the natural order to generate the labels can change for each image, e.g.\ first the dominant object before summing up the smaller objects in the image. Therefore, in this paper, we propose ways to dynamically order the ground truth labels with the predicted label sequence. This allows for the faster training of more optimal LSTM models for multi-label classification. Analysis evidences that our method does not suffer from duplicate generation, something which is common for other models. Furthermore, it outperforms other CNN-RNN models, and we show that a standard architecture of an image encoder and language decoder trained with our proposed loss obtains the state-of-the-art results on the challenging MS-COCO, WIDER Attribute and PA-100K and competitive results on NUS-WIDE.
The task of video captioning, that is, the automatic generation of sentences describing a sequence of actions in a video, has attracted an increasing attention recently. The complex and high-dimensional representation of video data makes it difficult for a typical encoder-decoder architectures to recognize relevant features and encode them in a proper format. Video data contains different modalities that can be recognized using a mix image, scene, action and audio features. In this paper, we characterize the different features affecting video descriptions and explore the interactions among these features and how they affect the final quality of a video representation. Building on existing encoder-decoder models that utilize limited range of video information, our comparisons show how the inclusion of multi-modal video features can make a significant effect on improving the quality of generated statements. The work is of special interest to scientists and practitioners who are using sequence-to-sequence models to generate video captions.
The key challenge of multi-domain translation lies in simultaneously encoding both the general knowledge shared across domains and the particular knowledge distinctive to each domain in a unified model. Previous work shows that the standard neural machine translation (NMT) model, trained on mixed-domain data, generally captures the general knowledge, but misses the domain-specific knowledge. In response to this problem, we augment NMT model with additional domain transformation networks to transform the general representations to domain-specific representations, which are subsequently fed to the NMT decoder. To guarantee the knowledge transformation, we also propose two complementary supervision signals by leveraging the power of knowledge distillation and adversarial learning. Experimental results on several language pairs, covering both balanced and unbalanced multi-domain translation, demonstrate the effectiveness and universality of the proposed approach. Encouragingly, the proposed unified model achieves comparable results with the fine-tuning approach that requires multiple models to preserve the particular knowledge. Further analyses reveal that the domain transformation networks successfully capture the domain-specific knowledge as expected.
A relation tuple consists of two entities and the relation between them, and often such tuples are found in unstructured text. There may be multiple relation tuples present in a text and they may share one or both entities among them. Extracting such relation tuples from a sentence is a difficult task and sharing of entities or overlapping entities among the tuples makes it more challenging. Most prior work adopted a pipeline approach where entities were identified first followed by finding the relations among them, thus missing the interaction among the relation tuples in a sentence. In this paper, we propose two approaches to use encoder-decoder architecture for jointly extracting entities and relations. In the first approach, we propose a representation scheme for relation tuples which enables the decoder to generate one word at a time like machine translation models and still finds all the tuples present in a sentence with full entity names of different length and with overlapping entities. Next, we propose a pointer network-based decoding approach where an entire tuple is generated at every time step. Experiments on the publicly available New York Times corpus show that our proposed approaches outperform previous work and achieve significantly higher F1 scores.
Neural conversation models such as encoder-decoder models are easy to generate bland and generic responses. Some researchers propose to use the conditional variational autoencoder(CVAE) which maximizes the lower bound on the conditional log-likelihood on a continuous latent variable. With different sampled la-tent variables, the model is expected to generate diverse responses. Although the CVAE-based models have shown tremendous potential, their improvement of generating high-quality responses is still unsatisfactory. In this paper, we introduce a discrete latent variable with an explicit semantic meaning to improve the CVAE on short-text conversation. A major advantage of our model is that we can exploit the semantic distance between the latent variables to maintain good diversity between the sampled latent variables. Accordingly, we pro-pose a two-stage sampling approach to enable efficient diverse variable selection from a large latent space assumed in the short-text conversation task. Experimental results indicate that our model outperforms various kinds of generation models under both automatic and human evaluations and generates more diverse and in-formative responses.
The encoder-decoder networks are commonly used in medical image segmentation due to their remarkable performance in hierarchical feature fusion. However, the expanding path for feature decoding and spatial recovery does not consider the long-term dependency when fusing feature maps from different layers, and the universal encoder-decoder network does not make full use of the multi-modality information to improve the network robustness especially for segmenting medical MRI. In this paper, we propose a novel feature fusion unit called Recurrent Decoding Cell (RDC) which leverages convolutional RNNs to memorize the long-term context information from the previous layers in the decoding phase. An encoder-decoder network, named Convolutional Recurrent Decoding Network (CRDN), is also proposed based on RDC for segmenting multi-modality medical MRI. CRDN adopts CNN backbone to encode image features and decode them hierarchically through a chain of RDCs to obtain the final high-resolution score map. The evaluation experiments on BrainWeb, MRBrainS and HVSMR datasets demonstrate that the introduction of RDC effectively improves the segmentation accuracy as well as reduces the model size, and the proposed CRDN owns its robustness to image noise and intensity non-uniformity in medical MRI.
Contemporary deep learning based video captioning follows encoder-decoder framework. In encoder, visual features are extracted with 2D/3D Convolutional Neural Networks (CNNs) and a transformed version of those features is passed to the decoder. The decoder uses word embeddings and a language model to map visual features to natural language captions. Due to its composite nature, the encoder-decoder pipeline provides the freedom of multiple choices for each of its components, e.g the choices of CNNs models, feature transformations, word embeddings, and language models etc. Component selection can have drastic effects on the overall video captioning performance. However, current literature is void of any systematic investigation in this regard. This article fills this gap by providing the first thorough empirical analysis of the role that each major component plays in a contemporary video captioning pipeline. We perform extensive experiments by varying the constituent components of the video captioning framework, and quantify the performance gains that are possible by mere component selection. We use the popular MSVD dataset as the test-bed, and demonstrate that substantial performance gains are possible by careful selection of the constituent components without major changes to the pipeline itself. These results are expected to provide guiding principles for future research in the fast growing direction of video captioning.
Transformer model has been widely used on machine translation tasks and obtained state-of-the-art results. In this paper, we report an interesting phenomenon in its encoder-decoder multi-head attention: different attention heads of the final decoder layer align to different word translation candidates. We empirically verify this discovery and propose a method to generate diverse translations by manipulating heads. Furthermore, we make use of these diverse translations with the back-translation technique for better data augmentation. Experiment results show that our method generates diverse translations without severe drop in translation quality. Experiments also show that back-translation with these diverse translations could bring significant improvement on performance on translation tasks. An auxiliary experiment of conversation response generation task proves the effect of diversity as well.
Heart is one of the vital organs of human body. A minor dysfunction of heart even for a short time interval can be fatal, therefore, efficient monitoring of its physiological state is essential for the patients with cardiovascular diseases. In the recent past, various computer assisted medical imaging systems have been proposed for the segmentation of the organ of interest. However, for the segmentation of heart using MRI, only few methods have been proposed each with its own merits and demerits. For further advancement in this area of research, we analyze automated heart segmentation methods for magnetic resonance images. The analysis are based on deep learning methods that processes a full MR scan in a slice by slice fashion to predict desired mask for heart region. We design two encoder decoder type fully convolutional neural network models
Designing a lightweight and robust portrait segmentation algorithm is an important task for a wide range of face applications. However, the problem has been considered as a subset of the object segmentation problem and less handled in the semantic segmentation field. Obviously, portrait segmentation has its unique requirements. First, because the portrait segmentation is performed in the middle of a whole process of many real-world applications, it requires extremely lightweight models. Second, there has not been any public datasets in this domain that contain a sufficient number of images with unbiased statistics. To solve the first problem, we introduce the new extremely lightweight portrait segmentation model SINet, containing an information blocking decoder and spatial squeeze modules. The information blocking decoder uses confidence estimates to recover local spatial information without spoiling global consistency. The spatial squeeze module uses multiple receptive fields to cope with various sizes of consistency in the image. To tackle the second problem, we propose a simple method to create additional portrait segmentation data which can improve accuracy on the EG1800 dataset. In our qualitative and quantitative analysis on the EG1800 dataset, we show that our method outperforms various existing lightweight segmentation models. Our method reduces the number of parameters from 2.1M to 86.9K (around 95.9% reduction), while maintaining the accuracy under an 1% margin from the state-of-the-art portrait segmentation method. We also show our model is successfully executed on a real mobile device with 100.6 FPS. In addition, we demonstrate that our method can be used for general semantic segmentation on the Cityscapes dataset. The code and dataset are available in https://github.com/HYOJINPARK/ExtPortraitSeg .
In reading comprehension, generating sentence-level distractors is a significant task, which requires a deep understanding of the article and question. The traditional entity-centered methods can only generate word-level or phrase-level distractors. Although recently proposed neural-based methods like sequence-to-sequence (Seq2Seq) model show great potential in generating creative text, the previous neural methods for distractor generation ignore two important aspects. First, they didn't model the interactions between the article and question, making the generated distractors tend to be too general or not relevant to question context. Second, they didn't emphasize the relationship between the distractor and article, making the generated distractors not semantically relevant to the article and thus fail to form a set of meaningful options. To solve the first problem, we propose a co-attention enhanced hierarchical architecture to better capture the interactions between the article and question, thus guide the decoder to generate more coherent distractors. To alleviate the second problem, we add an additional semantic similarity loss to push the generated distractors more relevant to the article. Experimental results show that our model outperforms several strong baselines on automatic metrics, achieving state-of-the-art performance. Further human evaluation indicates that our generated distractors are more coherent and more educative compared with those distractors generated by baselines.
Generative seq2seq dialogue systems are trained to predict the next word in dialogues that have already occurred. They can learn from large unlabeled conversation datasets, build a deeper understanding of conversational context, and generate a wide variety of responses. This flexibility comes at the cost of control, a concerning tradeoff in doctor/patient interactions. Inaccuracies, typos, or undesirable content in the training data will be reproduced by the model at inference time. We trade a small amount of labeling effort and some loss of response variety in exchange for quality control. More specifically, a pretrained language model encodes the conversational context, and we finetune a classification head to map an encoded conversational context to a response class, where each class is a noisily labeled group of interchangeable responses. Experts can update these exemplar responses over time as best practices change without retraining the classifier or invalidating old training data. Expert evaluation of 775 unseen doctor/patient conversations shows that only 12% of the discriminative model's responses are worse than the what the doctor ended up writing, compared to 18% for the generative model.
This paper considers the problem of resource allocation in stream processing, where continuous data flows must be processed in real time in a large distributed system. To maximize system throughput, the resource allocation strategy that partitions the computation tasks of a stream processing graph onto computing devices must simultaneously balance workload distribution and minimize communication. Since this problem of graph partitioning is known to be NP-complete yet crucial to practical streaming systems, many heuristic-based algorithms have been developed to find reasonably good solutions. In this paper, we present a graph-aware encoder-decoder framework to learn a generalizable resource allocation strategy that can properly distribute computation tasks of stream processing graphs unobserved from training data. We, for the first time, propose to leverage graph embedding to learn the structural information of the stream processing graphs. Jointly trained with the graph-aware decoder using deep reinforcement learning, our approach can effectively find optimized solutions for unseen graphs. Our experiments show that the proposed model outperforms both METIS, a state-of-the-art graph partitioning algorithm, and an LSTM-based encoder-decoder model, in about 70% of the test cases.