Leveraging the advances of natural language processing, most recent scene text recognizers adopt an encoder-decoder architecture where text images are first converted to representative features and then a sequence of characters via `sequential decoding'. However, scene text images suffer from rich noises of different sources such as complex background and geometric distortions which often confuse the decoder and lead to incorrect alignment of visual features at noisy decoding time steps. This paper presents I2C2W, a novel scene text recognition technique that is tolerant to geometric and photometric degradation by decomposing scene text recognition into two inter-connected tasks. The first task focuses on image-to-character (I2C) mapping which detects a set of character candidates from images based on different alignments of visual features in an non-sequential way. The second task tackles character-to-word (C2W) mapping which recognizes scene text by decoding words from the detected character candidates. The direct learning from character semantics (instead of noisy image features) corrects falsely detected character candidates effectively which improves the final text recognition accuracy greatly. Extensive experiments over nine public datasets show that the proposed I2C2W outperforms the state-of-the-art by large margins for challenging scene text datasets with various curvature and perspective distortions. It also achieves very competitive recognition performance over multiple normal scene text datasets.
Recent years have witnessed great progress on building emotional chatbots. Tremendous methods have been proposed for chatbots to generate responses with given emotions. However, the emotion changes of the user during the conversation has not been fully explored. In this work, we study the problem of positive emotion elicitation, which aims to generate responses that can elicit positive emotion of the user, in human-machine conversation. We propose a weakly supervised Emotion Eliciting Machine (EEM) to address this problem. Specifically, we first collect weak labels of user emotion status changes in a conversion based on a pre-trained emotion classifier. Then we propose a dual encoder-decoder structure to model the generation of responses in both positive and negative side based on the changes of the user's emotion status in the conversation. An emotion eliciting factor is introduced on top of the dual structure to balance the positive and negative emotional impacts on the generated response during emotion elicitation. The factor also provides a fine-grained controlling manner for emotion elicitation. Experimental results on a large real-world dataset show that EEM outperforms the existing models in generating responses with positive emotion elicitation.
We present CoTexT, a pre-trained, transformer-based encoder-decoder model that learns the representative context between natural language (NL) and programming language (PL). Using self-supervision, CoTexT is pre-trained on large programming language corpora to learn a general understanding of language and code. CoTexT supports downstream NL-PL tasks such as code summarizing/documentation, code generation, defect detection, and code debugging. We train CoTexT on different combinations of available PL corpus including both "bimodal" and "unimodal" data. Here, bimodal data is the combination of text and corresponding code snippets, whereas unimodal data is merely code snippets. We first evaluate CoTexT with multi-task learning: we perform Code Summarization on 6 different programming languages and Code Refinement on both small and medium size featured in the CodeXGLUE dataset. We further conduct extensive experiments to investigate CoTexT on other tasks within the CodeXGlue dataset, including Code Generation and Defect Detection. We consistently achieve SOTA results in these tasks, demonstrating the versatility of our models.
In text-to-SQL task, seq-to-seq models often lead to sub-optimal performance due to limitations in their architecture. In this paper, we present a simple yet effective approach that adapts transformer-based seq-to-seq model to robust text-to-SQL generation. Instead of inducing constraint to decoder or reformat the task as slot-filling, we propose to train seq-to-seq model with Schema aware Denoising (SeaD), which consists of two denoising objectives that train model to either recover input or predict output from two novel erosion and shuffle noises. These denoising objectives acts as the auxiliary tasks for better modeling the structural data in S2S generation. In addition, we improve and propose a clause-sensitive execution guided (EG) decoding strategy to overcome the limitation of EG decoding for generative model. The experiments show that the proposed method improves the performance of seq-to-seq model in both schema linking and grammar correctness and establishes new state-of-the-art on WikiSQL benchmark. The results indicate that the capacity of vanilla seq-to-seq architecture for text-to-SQL may have been under-estimated.
AtomAI is an open-source software package bridging instrument-specific Python libraries, deep learning, and simulation tools into a single ecosystem. AtomAI allows direct applications of the deep convolutional neural networks for atomic and mesoscopic image segmentation converting image and spectroscopy data into class-based local descriptors for downstream tasks such as statistical and graph analysis. For atomically-resolved imaging data, the output is types and positions of atomic species, with an option for subsequent refinement. AtomAI further allows the implementation of a broad range of image and spectrum analysis functions, including invariant variational autoencoders (VAEs). The latter consists of VAEs with rotational and (optionally) translational invariance for unsupervised and class-conditioned disentanglement of categorical and continuous data representations. In addition, AtomAI provides utilities for mapping structure-property relationships via im2spec and spec2im type of encoder-decoder models. Finally, AtomAI allows seamless connection to the first principles modeling with a Python interface, including molecular dynamics and density functional theory calculations on the inferred atomic position. While the majority of applications to date were based on atomically resolved electron microscopy, the flexibility of AtomAI allows straightforward extension towards the analysis of mesoscopic imaging data once the labels and feature identification workflows are established/available. The source code and example notebooks are available at https://github.com/pycroscopy/atomai.
Being low-level radiation exposure and less harmful to health, low-dose computed tomography (LDCT) has been widely adopted in the early screening of lung cancer and COVID-19. LDCT images inevitably suffer from the degradation problem caused by complex noises. It was reported that deep learning (DL)-based LDCT denoising methods using convolutional neural network (CNN) achieved impressive denoising performance. Although most existing DL-based methods (e.g., encoder-decoder framework) can implicitly utilize non-local and contextual information via downsampling operator and 3D CNN, the explicit multi-information (i.e., local, non-local, and contextual) integration may not be explored enough. To address this issue, we propose a novel graph convolutional network-based LDCT denoising model, namely GCN-MIF, to explicitly perform multi-information fusion for denoising purpose. Concretely, by constructing intra- and inter-slice graph, the graph convolutional network is introduced to leverage the non-local and contextual relationships among pixels. The traditional CNN is adopted for the extraction of local information. Finally, the proposed GCN-MIF model fuses all the extracted local, non-local, and contextual information. Extensive experiments show the effectiveness of our proposed GCN-MIF model by quantitative and visualized results. Furthermore, a double-blind reader study on a public clinical dataset is also performed to validate the usability of denoising results in terms of the structural fidelity, the noise suppression, and the overall score. Models and code are available at https://github.com/tonyckc/GCN-MIF_demo.
The rapid increment of morbidity of brain stroke in the last few years have been a driving force towards fast and accurate segmentation of stroke lesions from brain MRI images. With the recent development of deep-learning, computer-aided and segmentation methods of ischemic stroke lesions have been useful for clinicians in early diagnosis and treatment planning. However, most of these methods suffer from inaccurate and unreliable segmentation results because of their inability to capture sufficient contextual features from the MRI volumes. To meet these requirements, 3D convolutional neural networks have been proposed, which, however, suffer from huge computational requirements. To mitigate these problems, we propose a novel Dimension Fusion Edge-guided network (DFENet) that can meet both of these requirements by fusing the features of 2D and 3D CNNs. Unlike other methods, our proposed network uses a parallel partial decoder (PPD) module for aggregating and upsampling selected features, rich in important contextual information. Additionally, we use an edge-guidance and enhanced mixing loss for constantly supervising and improvising the learning process of the network. The proposed method is evaluated on publicly available Anatomical Tracings of Lesions After Stroke (ATLAS) dataset, resulting in mean DSC, IoU, Precision and Recall values of 0.5457, 0.4015, 0.6371, and 0.4969 respectively. The results, when compared to other state-of-the-art methods, outperforms them by a significant margin. Therefore, the proposed model is robust, accurate, superior to the existing methods, and can be relied upon for biomedical applications.
In this paper, we propose a solution to the task of generating dynamic 3D facial expressions from a neutral 3D face and an expression label. This involves solving two sub-problems: (i)modeling the temporal dynamics of expressions, and (ii) deforming the neutral mesh to obtain the expressive counterpart. We represent the temporal evolution of expressions using the motion of a sparse set of 3D landmarks that we learn to generate by training a manifold-valued GAN (Motion3DGAN). To better encode the expression-induced deformation and disentangle it from the identity information, the generated motion is represented as per-frame displacement from a neutral configuration. To generate the expressive meshes, we train a Sparse2Dense mesh Decoder (S2D-Dec) that maps the landmark displacements to a dense, per-vertex displacement. This allows us to learn how the motion of a sparse set of landmarks influences the deformation of the overall face surface, independently from the identity. Experimental results on the CoMA and D3DFACS datasets show that our solution brings significant improvements with respect to previous solutions in terms of both dynamic expression generation and mesh reconstruction, while retaining good generalization to unseen data. The code and the pretrained model will be made publicly available.
It is a long-standing question to discover causal relations among a set of variables in many empirical sciences. Recently, Reinforcement Learning (RL) has achieved promising results in causal discovery from observational data. However, searching the space of directed graphs and enforcing acyclicity by implicit penalties tend to be inefficient and restrict the existing RL-based method to small scale problems. In this work, we propose a novel RL-based approach for causal discovery, by incorporating RL into the ordering-based paradigm. Specifically, we formulate the ordering search problem as a multi-step Markov decision process, implement the ordering generating process with an encoder-decoder architecture, and finally use RL to optimize the proposed model based on the reward mechanisms designed for~each ordering. A generated ordering would then be processed using variable selection to obtain the final causal graph. We analyze the consistency and computational complexity of the proposed method, and empirically show that a pretrained model can be exploited to accelerate training. Experimental results on both synthetic and real data sets shows that the proposed method achieves a much improved performance over existing RL-based method.
Language-queried video actor segmentation aims to predict the pixel-level mask of the actor which performs the actions described by a natural language query in the target frames. Existing methods adopt 3D CNNs over the video clip as a general encoder to extract a mixed spatio-temporal feature for the target frame. Though 3D convolutions are amenable to recognizing which actor is performing the queried actions, it also inevitably introduces misaligned spatial information from adjacent frames, which confuses features of the target frame and yields inaccurate segmentation. Therefore, we propose a collaborative spatial-temporal encoder-decoder framework which contains a 3D temporal encoder over the video clip to recognize the queried actions, and a 2D spatial encoder over the target frame to accurately segment the queried actors. In the decoder, a Language-Guided Feature Selection (LGFS) module is proposed to flexibly integrate spatial and temporal features from the two encoders. We also propose a Cross-Modal Adaptive Modulation (CMAM) module to dynamically recombine spatial- and temporal-relevant linguistic features for multimodal feature interaction in each stage of the two encoders. Our method achieves new state-of-the-art performance on two popular benchmarks with less computational overhead than previous approaches.
In educational applications, Knowledge Tracing (KT), the problem of accurately predicting students' responses to future questions by summarizing their knowledge states, has been widely studied for decades as it is considered a fundamental task towards adaptive online learning. Among all the proposed KT methods, Deep Knowledge Tracing (DKT) and its variants are by far the most effective ones due to the high flexibility of the neural network. However, DKT often ignores the inherent differences between students (e.g. memory skills, reasoning skills, ...), averaging the performances of all students, leading to the lack of personalization, and therefore was considered insufficient for adaptive learning. To alleviate this problem, in this paper, we proposed Leveled Attentive KNowledge TrAcing (LANA), which firstly uses a novel student-related features extractor (SRFE) to distill students' unique inherent properties from their respective interactive sequences. Secondly, the pivot module was utilized to dynamically reconstruct the decoder of the neural network on attention of the extracted features, successfully distinguishing the performance between students over time. Moreover, inspired by Item Response Theory (IRT), the interpretable Rasch model was used to cluster students by their ability levels, and thereby utilizing leveled learning to assign different encoders to different groups of students. With pivot module reconstructed the decoder for individual students and leveled learning specialized encoders for groups, personalized DKT was achieved. Extensive experiments conducted on two real-world large-scale datasets demonstrated that our proposed LANA improves the AUC score by at least 1.00% (i.e. EdNet 1.46% and RAIEd2020 1.00%), substantially surpassing the other State-Of-The-Art KT methods.
Clustering using deep neural network models have been extensively studied in recent years. Among the most popular frameworks are the VAE and GAN frameworks, which learns latent feature representations of data through encoder / decoder neural net structures. This is a suitable base for clustering tasks, as the latent space often seems to effectively capture the inherent essence of data, simplifying its manifold and reducing noise. In this article, the VAE framework is used to investigate how probability function gradient ascent over data points can be used to process data in order to achieve better clustering. Improvements in classification is observed comparing with unprocessed data, although state of the art results are not obtained. Processing data with gradient descent however results in more distinct cluster separation, making it simpler to investigate suitable hyper parameter settings such as the number of clusters. We propose a simple yet effective method for investigating suitable number of clusters for data, based on the DBSCAN clustering algorithm, and demonstrate that cluster number determination is facilitated with gradient processing. As an additional curiosity, we find that our baseline model used for comparison; a GMM on a t-SNE latent space for a VAE structure with weight one on reconstruction during training (autoencoder), yield state of the art results on the MNIST data, to our knowledge not beaten by any other existing model.
Generating audio captions is a new research area that combines audio and natural language processing to create meaningful textual descriptions for audio clips. To address this problem, previous studies mostly use the encoder-decoder based models without considering semantic information. To fill this gap, we present a novel encoder-decoder architecture using bi-directional Gated Recurrent Units (BiGRU) with audio and semantic embeddings. We extract semantic embedding by obtaining subjects and verbs from the audio clip captions and combine these embedding with audio embedding to feed the BiGRU-based encoder-decoder model. To enable semantic embeddings for the test audios, we introduce a Multilayer Perceptron classifier to predict the semantic embeddings of those clips. We also present exhaustive experiments to show the efficiency of different features and datasets for our proposed model the audio captioning task. To extract audio features, we use the log Mel energy features, VGGish embeddings, and a pretrained audio neural network (PANN) embeddings. Extensive experiments on two audio captioning datasets Clotho and AudioCaps show that our proposed model outperforms state-of-the-art audio captioning models across different evaluation metrics and using the semantic information improves the captioning performance. Keywords: Audio captioning; PANNs; VGGish; GRU; BiGRU.
Recently, denoising diffusion probabilistic models and generative score matching have shown high potential in modelling complex data distributions while stochastic calculus has provided a unified point of view on these techniques allowing for flexible inference schemes. In this paper we introduce Grad-TTS, a novel text-to-speech model with score-based decoder producing mel-spectrograms by gradually transforming noise predicted by encoder and aligned with text input by means of Monotonic Alignment Search. The framework of stochastic differential equations helps us to generalize conventional diffusion probabilistic models to the case of reconstructing data from noise with different parameters and allows to make this reconstruction flexible by explicitly controlling trade-off between sound quality and inference speed. Subjective human evaluation shows that Grad-TTS is competitive with state-of-the-art text-to-speech approaches in terms of Mean Opinion Score. We will make the code publicly available shortly.
Blind face restoration (BFR) from severely degraded face images in the wild is a very challenging problem. Due to the high illness of the problem and the complex unknown degradation, directly training a deep neural network (DNN) usually cannot lead to acceptable results. Existing generative adversarial network (GAN) based methods can produce better results but tend to generate over-smoothed restorations. In this work, we propose a new method by first learning a GAN for high-quality face image generation and embedding it into a U-shaped DNN as a prior decoder, then fine-tuning the GAN prior embedded DNN with a set of synthesized low-quality face images. The GAN blocks are designed to ensure that the latent code and noise input to the GAN can be respectively generated from the deep and shallow features of the DNN, controlling the global face structure, local face details and background of the reconstructed image. The proposed GAN prior embedded network (GPEN) is easy-to-implement, and it can generate visually photo-realistic results. Our experiments demonstrated that the proposed GPEN achieves significantly superior results to state-of-the-art BFR methods both quantitatively and qualitatively, especially for the restoration of severely degraded face images in the wild. The source code and models can be found at https://github.com/yangxy/GPEN.
This paper describes an automatic drum transcription (ADT) method that directly estimates a tatum-level drum score from a music signal, in contrast to most conventional ADT methods that estimate the frame-level onset probabilities of drums. To estimate a tatum-level score, we propose a deep transcription model that consists of a frame-level encoder for extracting the latent features from a music signal and a tatum-level decoder for estimating a drum score from the latent features pooled at the tatum level. To capture the global repetitive structure of drum scores, which is difficult to learn with a recurrent neural network (RNN), we introduce a self-attention mechanism with tatum-synchronous positional encoding into the decoder. To mitigate the difficulty of training the self-attention-based model from an insufficient amount of paired data and improve the musical naturalness of the estimated scores, we propose a regularized training method that uses a global structure-aware masked language (score) model with a self-attention mechanism pretrained from an extensive collection of drum scores. Experimental results showed that the proposed regularized model outperformed the conventional RNN-based model in terms of the tatum-level error rate and the frame-level F-measure, even when only a limited amount of paired data was available so that the non-regularized model underperformed the RNN-based model.
Neural decoders were introduced as a generalization of the classic Belief Propagation (BP) decoding algorithms, where the Trellis graph in the BP algorithm is viewed as a neural network, and the weights in the Trellis graph are optimized by training the neural network. In this work, we propose a novel neural decoder for cyclic codes by exploiting their cyclically invariant property. More precisely, we impose a shift invariant structure on the weights of our neural decoder so that any cyclic shift of inputs results in the same cyclic shift of outputs. Extensive simulations with BCH codes and punctured Reed-Muller (RM) codes show that our new decoder consistently outperforms previous neural decoders when decoding cyclic codes. Finally, we propose a list decoding procedure that can significantly reduce the decoding error probability for BCH codes and punctured RM codes. For certain high-rate codes, the gap between our list decoder and the Maximum Likelihood decoder is less than $0.1$dB. Code available at https://github.com/cyclicallyneuraldecoder/CyclicallyEquivariantNeuralDecoders
In the past few years, convolutional neural networks (CNNs) have achieved milestones in medical image analysis. Especially, the deep neural networks based on U-shaped architecture and skip-connections have been widely applied in a variety of medical image tasks. However, although CNN has achieved excellent performance, it cannot learn global and long-range semantic information interaction well due to the locality of the convolution operation. In this paper, we propose Swin-Unet, which is an Unet-like pure Transformer for medical image segmentation. The tokenized image patches are fed into the Transformer-based U-shaped Encoder-Decoder architecture with skip-connections for local-global semantic feature learning. Specifically, we use hierarchical Swin Transformer with shifted windows as the encoder to extract context features. And a symmetric Swin Transformer-based decoder with patch expanding layer is designed to perform the up-sampling operation to restore the spatial resolution of the feature maps. Under the direct down-sampling and up-sampling of the inputs and outputs by 4x, experiments on multi-organ and cardiac segmentation tasks demonstrate that the pure Transformer-based U-shaped Encoder-Decoder network outperforms those methods with full-convolution or the combination of transformer and convolution. The codes and trained models will be publicly available at https://github.com/HuCaoFighting/Swin-Unet.
Image segmentation is often ambiguous at the level of individual image patches and requires contextual information to reach label consensus. In this paper we introduce Segmenter, a transformer model for semantic segmentation. In contrast to convolution-based methods, our approach allows to model global context already at the first layer and throughout the network. We build on the recent Vision Transformer (ViT) and extend it to semantic segmentation. To do so, we rely on the output embeddings corresponding to image patches and obtain class labels from these embeddings with a point-wise linear decoder or a mask transformer decoder. We leverage models pre-trained for image classification and show that we can fine-tune them on moderate sized datasets available for semantic segmentation. The linear decoder allows to obtain excellent results already, but the performance can be further improved by a mask transformer generating class masks. We conduct an extensive ablation study to show the impact of the different parameters, in particular the performance is better for large models and small patch sizes. Segmenter attains excellent results for semantic segmentation. It outperforms the state of the art on both ADE20K and Pascal Context datasets and is competitive on Cityscapes.
We propose a novel framework for modeling the interaction between graphical structures and the natural language text associated with their nodes and edges. Existing approaches typically fall into two categories. On group ignores the relational structure by converting them into linear sequences and then utilize the highly successful Seq2Seq models. The other side ignores the sequential nature of the text by representing them as fixed-dimensional vectors and apply graph neural networks. Both simplifications lead to information loss. Our proposed method utilizes both the graphical structure as well as the sequential nature of the texts. The input to our model is a set of text segments associated with the nodes and edges of the graph, which are then processed with a transformer encoder-decoder model, equipped with a self-attention mechanism that is aware of the graphical relations between the nodes containing the segments. This also allows us to use BERT-like models that are already trained on large amounts of text. While the proposed model has wide applications, we demonstrate its capabilities on data-to-text generation tasks. Our approach compares favorably against state-of-the-art methods in four tasks without tailoring the model architecture. We also provide an early demonstration in a novel practical application -- generating clinical notes from the medical entities mentioned during clinical visits.