Time series forecasting is a significant problem in many applications, e.g., financial predictions and business optimization. Modern datasets can have multiple correlated time series, which are often generated with global (shared) regularities and local (specific) dynamics. In this paper, we seek to tackle such forecasting problems with DeepDGL, a deep forecasting model that disentangles dynamics into global and local temporal patterns. DeepDGL employs an encoder-decoder architecture, consisting of two encoders to learn global and local temporal patterns, respectively, and a decoder to make multi-step forecasting. Specifically, to model complicated global patterns, the vector quantization (VQ) module is introduced, allowing the global feature encoder to learn a shared codebook among all time series. To model diversified and heterogenous local patterns, an adaptive parameter generation module enhanced by the contrastive multi-horizon coding (CMC) is proposed to generate the parameters of the local feature encoder for each individual time series, which maximizes the mutual information between the series-specific context variable and the long/short-term representations of the corresponding time series. Our experiments on several real-world datasets show that DeepDGL outperforms existing state-of-the-art models.
Large-scale Transformer models have significantly promoted the recent development of natural language processing applications. However, little effort has been made to unify the effective models. In this paper, driven by providing a new set of baseline models in the future, we adopt various novel transformer architectures and launch a model set with the help of recent mainstream technologies. We focus the discussions on optimizing the depth of the networks based on the existing powerful encode-decoder structures. We show that by properly avoiding training defects such as non-convergence and degradation, scaling up off-the-shelf transformer architectures consistently delivers better performance. To stimulate future research on large-scale language model pretraining, we present extensive results and detailed discussions on network performance improvements with respect to the network depth and confirm the existence of the optimal number of layers under specific tasks. To the best of our knowledge, we provide the largest Chinese generative model and the largest Chinese encoding model. The BERT language models we trained on English datasets deliver a 14.45% higher F1 score than the Turing-NLR.
The existing methods to calculate the Eigenvector Centrality(EC) tend to not be robust enough for determination of EC in low time complexity or not well-scalable for large networks, hence rendering them practically unreliable/ computationally expensive. So, it is of the essence to develop a method that is scalable in low computational time. Hence, we propose a deep learning model for the identification of nodes with high Eigenvector Centrality. There have been a few previous works in identifying the high ranked nodes with supervised learning methods, but in real-world cases, the graphs are not labelled and hence deployment of supervised learning methods becomes a hazard and its usage becomes impractical. So, we devise CUL(Centrality with Unsupervised Learning) method to learn the relative EC scores in a network in an unsupervised manner. To achieve this, we develop an Encoder-Decoder based framework that maps the nodes to their respective estimated EC scores. Extensive experiments were conducted on different synthetic and real-world networks. We compared CUL against a baseline supervised method for EC estimation similar to some of the past works. It was observed that even with training on a minuscule number of training datasets, CUL delivers a relatively better accuracy score when identifying the higher ranked nodes than its supervised counterpart. We also show that CUL is much faster and has a smaller runtime than the conventional baseline method for EC computation. The code is available at https://github.com/codexhammer/CUL.
In this study, we present a pragmatic lightweight pose estimation model. Our model can achieve real-time predictions using low-power embedded devices. This system was found to be very accurate and achieved a 94.5% accuracy of SOTA HRNet 256x192 using a computational cost of only 3.8% on COCO test dataset. Our model adopts an encoder-decoder architecture and is carefully downsized to improve its efficiency. We especially focused on optimizing the deconvolution layers and observed that the channel reduction of the deconvolution layers contributes significantly to reducing computational resource consumption without degrading the accuracy of this system. We also incorporated recent model agnostic techniques such as DarkPose and distillation training to maximize the efficiency of our model. Furthermore, we applied model quantization to exploit multi/mixed precision features. Our FP16'ed model (COCO AP 70.0) operates at ~60-fps on NVIDIA Jetson AGX Xavier and ~200 fps on NVIDIA Quadro RTX6000.
Recognition of Arabic-like scripts such as Persian and Urdu is more challenging than Latin-based scripts. This is due to the presence of a two-dimensional structure, context-dependent character shapes, spaces and overlaps, and placement of diacritics. Not much research exists for offline handwritten Urdu script which is the 10th most spoken language in the world. We present an attention based encoder-decoder model that learns to read Urdu in context. A novel localization penalty is introduced to encourage the model to attend only one location at a time when recognizing the next character. In addition, we comprehensively refine the only complete and publicly available handwritten Urdu dataset in terms of ground-truth annotations. We evaluate the model on both Urdu and Arabic datasets and show that contextual attention localization outperforms both simple attention and multi-directional LSTM models.
Segmentation of head and neck (H\&N) tumours and prediction of patient outcome are crucial for patient's disease diagnosis and treatment monitoring. Current developments of robust deep learning models are hindered by the lack of large multi-centre, multi-modal data with quality annotations. The MICCAI 2021 HEad and neCK TumOR (HECKTOR) segmentation and outcome prediction challenge creates a platform for comparing segmentation methods of the primary gross target volume on fluoro-deoxyglucose (FDG)-PET and Computed Tomography images and prediction of progression-free survival in H\&N oropharyngeal cancer.For the segmentation task, we proposed a new network based on an encoder-decoder architecture with full inter- and intra-skip connections to take advantage of low-level and high-level semantics at full scales. Additionally, we used Conditional Random Fields as a post-processing step to refine the predicted segmentation maps. We trained multiple neural networks for tumor volume segmentation, and these segmentations were ensembled achieving an average Dice Similarity Coefficient of 0.75 in cross-validation, and 0.76 on the challenge testing data set. For prediction of patient progression free survival task, we propose a Cox proportional hazard regression combining clinical, radiomic, and deep learning features. Our survival prediction model achieved a concordance index of 0.82 in cross-validation, and 0.62 on the challenge testing data set.
Machine learning (ML) has established itself as a cornerstone for various critical applications ranging from autonomous driving to authentication systems. However, with this increasing adoption rate of machine learning models, multiple attacks have emerged. One class of such attacks is training time attack, whereby an adversary executes their attack before or during the machine learning model training. In this work, we propose a new training time attack against computer vision based machine learning models, namely model hijacking attack. The adversary aims to hijack a target model to execute a different task than its original one without the model owner noticing. Model hijacking can cause accountability and security risks since a hijacked model owner can be framed for having their model offering illegal or unethical services. Model hijacking attacks are launched in the same way as existing data poisoning attacks. However, one requirement of the model hijacking attack is to be stealthy, i.e., the data samples used to hijack the target model should look similar to the model's original training dataset. To this end, we propose two different model hijacking attacks, namely Chameleon and Adverse Chameleon, based on a novel encoder-decoder style ML model, namely the Camouflager. Our evaluation shows that both of our model hijacking attacks achieve a high attack success rate, with a negligible drop in model utility.
Medical report generation, which aims to automatically generate a long and coherent report of a given medical image, has been receiving growing research interests. Existing approaches mainly adopt a supervised manner and heavily rely on coupled image-report pairs. However, in the medical domain, building a large-scale image-report paired dataset is both time-consuming and expensive. To relax the dependency on paired data, we propose an unsupervised model Knowledge Graph Auto-Encoder (KGAE) which accepts independent sets of images and reports in training. KGAE consists of a pre-constructed knowledge graph, a knowledge-driven encoder and a knowledge-driven decoder. The knowledge graph works as the shared latent space to bridge the visual and textual domains; The knowledge-driven encoder projects medical images and reports to the corresponding coordinates in this latent space and the knowledge-driven decoder generates a medical report given a coordinate in this space. Since the knowledge-driven encoder and decoder can be trained with independent sets of images and reports, KGAE is unsupervised. The experiments show that the unsupervised KGAE generates desirable medical reports without using any image-report training pairs. Moreover, KGAE can also work in both semi-supervised and supervised settings, and accept paired images and reports in training. By further fine-tuning with image-report pairs, KGAE consistently outperforms the current state-of-the-art models on two datasets.
An AI chatbot provides an impressive response after learning from the trained dataset. In this decade, most of the research work demonstrates that deep neural models superior to any other model. RNN model regularly used for determining the sequence-related problem like a question and it answers. This approach acquainted with everyone as seq2seq learning. In a seq2seq model mechanism, it has encoder and decoder. The encoder embedded any input sequence, and the decoder embedded output sequence. For reinforcing the seq2seq model performance, attention mechanism added into the encoder and decoder. After that, the transformer model has introduced itself as a high-performance model with multiple attention mechanism for solving the sequence-related dilemma. This model reduces training time compared with RNN based model and also achieved state-of-the-art performance for sequence transduction. In this research, we applied the transformer model for Bengali general knowledge chatbot based on the Bengali general knowledge Question Answer (QA) dataset. It scores 85.0 BLEU on the applied QA data. To check the comparison of the transformer model performance, we trained the seq2seq model with attention on our dataset that scores 23.5 BLEU.
Single image deraining is typically addressed as residual learning to predict the rain layer from an input rainy image. For this purpose, an encoder-decoder network draws wide attention, where the encoder is required to encode a high-quality rain embedding which determines the performance of the subsequent decoding stage to reconstruct the rain layer. However, most of existing studies ignore the significance of rain embedding quality, thus leading to limited performance with over/under-deraining. In this paper, with our observation of the high rain layer reconstruction performance by an rain-to-rain autoencoder, we introduce the idea of "Rain Embedding Consistency" by regarding the encoded embedding by the autoencoder as an ideal rain embedding and aim at enhancing the deraining performance by improving the consistency between the ideal rain embedding and the rain embedding derived by the encoder of the deraining network. To achieve this, a Rain Embedding Loss is applied to directly supervise the encoding process, with a Rectified Local Contrast Normalization (RLCN) as the guide that effectively extracts the candidate rain pixels. We also propose Layered LSTM for recurrent deraining and fine-grained encoder feature refinement considering different scales. Qualitative and quantitative experiments demonstrate that our proposed method outperforms previous state-of-the-art methods particularly on a real-world dataset. Our source code is available at http://www.ok.sc.e.titech.ac.jp/res/SIR/.
Recent works in image inpainting have shown that structural information plays an important role in recovering visually pleasing results. In this paper, we propose an end-to-end architecture composed of two parallel UNet-based streams: a main stream (MS) and a structure stream (SS). With the assistance of SS, MS can produce plausible results with reasonable structures and realistic details. Specifically, MS reconstructs detailed images by inferring missing structures and textures simultaneously, and SS restores only missing structures by processing the hierarchical information from the encoder of MS. By interacting with SS in the training process, MS can be implicitly encouraged to exploit structural cues. In order to help SS focus on structures and prevent textures in MS from being affected, a gated unit is proposed to depress structure-irrelevant activations in the information flow between MS and SS. Furthermore, the multi-scale structure feature maps in SS are utilized to explicitly guide the structure-reasonable image reconstruction in the decoder of MS through the fusion block. Extensive experiments on CelebA, Paris StreetView and Places2 datasets demonstrate that our proposed method outperforms state-of-the-art methods.
Salient object detection plays an important role in many downstream tasks. However, complex real-world scenes with varying scales and numbers of salient objects still pose a challenge. In this paper, we directly address the problem of detecting multiple salient objects across complex scenes. We propose a network architecture incorporating non-local feature information in both the spatial and channel spaces, capturing the long-range dependencies between separate objects. Traditional bottom-up and non-local features are combined with edge features within a feature fusion gate that progressively refines the salient object prediction in the decoder. We show that our approach accurately locates multiple salient regions even in complex scenarios. To demonstrate the efficacy of our approach to the multiple salient objects problem, we curate a new dataset containing only multiple salient objects. Our experiments demonstrate the proposed method presents state-of-the-art results on five widely used datasets without any pre-processing and post-processing. We obtain a further performance improvement against competing techniques on our multi-objects dataset. The dataset and source code are avaliable at: https://github.com/EricDengbowen/DSLRDNet.
In spite of widely discussed, drawing order recovery (DOR) from static images is still a great challenge task. Based on the idea that drawing trajectories are able to be recovered by connecting their trajectory components in correct orders, this work proposes a novel DOR method from static images. The method contains two steps: firstly, we adopt a convolution neural network (CNN) to predict the next possible drawing components, which is able to covert the components in images to their reasonable sequences. We denote this architecture as Im2Seq-CNN; secondly, considering possible errors exist in the reasonable sequences generated by the first step, we construct a sequence to order structure (Seq2Order) to adjust the sequences to the correct orders. The main contributions include: (1) the Img2Seq-CNN step considers DOR from components instead of traditional pixels one by one along trajectories, which contributes to static images to component sequences; (2) the Seq2Order step adopts image position codes instead of traditional points’ coordinates in its encoder-decoder gated recurrent neural network (GRU-RNN). The proposed method is experienced on two well-known open handwriting databases, and yields robust and competitive results on handwriting DOR tasks compared to the state-of-arts.
Empirically observed time series in physics, biology, or medicine, are commonly generated by some underlying dynamical system (DS) which is the target of scientific interest. There is an increasing interest to harvest machine learning methods to reconstruct this latent DS in a data-driven, unsupervised way. In many areas of science it is common to sample time series observations from many data modalities simultaneously, e.g. electrophysiological and behavioral time series in a typical neuroscience experiment. However, current machine learning tools for reconstructing DSs usually focus on just one data modality. Here we propose a general framework for multi-modal data integration for the purpose of nonlinear DS reconstruction and the analysis of cross-modal relations. This framework is based on dynamically interpretable recurrent neural networks as general approximators of nonlinear DSs, coupled to sets of modality-specific decoder models from the class of generalized linear models. Both an expectation-maximization and a variational inference algorithm for model training are advanced and compared. We show on nonlinear DS benchmarks that our algorithms can efficiently compensate for too noisy or missing information in one data channel by exploiting other channels, and demonstrate on experimental neuroscience data how the algorithm learns to link different data domains to the underlying dynamics.
Deep learning has been widely used for inferring robust grasps. Although human-labeled RGB-D datasets were initially used to learn grasp configurations, preparation of this kind of large dataset is expensive. To address this problem, images were generated by a physical simulator, and a physically inspired model (e.g., a contact model between a suction vacuum cup and object) was used as a grasp quality evaluation metric to annotate the synthesized images. However, this kind of contact model is complicated and requires parameter identification by experiments to ensure real world performance. In addition, previous studies have not considered manipulator reachability such as when a grasp configuration with high grasp quality is unable to reach the target due to collisions or the physical limitations of the robot. In this study, we propose an intuitive geometric analytic-based grasp quality evaluation metric. We further incorporate a reachability evaluation metric. We annotate the pixel-wise grasp quality and reachability by the proposed evaluation metric on synthesized images in a simulator to train an auto-encoder--decoder called suction graspability U-Net++ (SG-U-Net++). Experiment results show that our intuitive grasp quality evaluation metric is competitive with a physically-inspired metric. Learning the reachability helps to reduce motion planning computation time by removing obviously unreachable candidates. The system achieves an overall picking speed of 560 PPH (pieces per hour).
Detection of illegal and threatening items in baggage is one of the utmost security concern nowadays. Even for experienced security personnel, manual detection is a time-consuming and stressful task. Many academics have created automated frameworks for detecting suspicious and contraband data from X-ray scans of luggage. However, to our knowledge, no framework exists that utilizes temporal baggage X-ray imagery to effectively screen highly concealed and occluded objects which are barely visible even to the naked eye. To address this, we present a novel temporal fusion driven multi-scale residual fashioned encoder-decoder that takes series of consecutive scans as input and fuses them to generate distinct feature representations of the suspicious and non-suspicious baggage content, leading towards a more accurate extraction of the contraband data. The proposed methodology has been thoroughly tested using the publicly accessible GDXray dataset, which is the only dataset containing temporally linked grayscale X-ray scans showcasing extremely concealed contraband data. The proposed framework outperforms its competitors on the GDXray dataset on various metrics.
This report describes Microsoft's machine translation systems for the WMT21 shared task on large-scale multilingual machine translation. We participated in all three evaluation tracks including Large Track and two Small Tracks where the former one is unconstrained and the latter two are fully constrained. Our model submissions to the shared task were initialized with DeltaLM\footnote{\url{https://aka.ms/deltalm}}, a generic pre-trained multilingual encoder-decoder model, and fine-tuned correspondingly with the vast collected parallel data and allowed data sources according to track settings, together with applying progressive learning and iterative back-translation approaches to further improve the performance. Our final submissions ranked first on three tracks in terms of the automatic evaluation metric.
Keyphrase provides accurate information of document content that is highly compact, concise, full of meanings, and widely used for discourse comprehension, organization, and text retrieval. Though previous studies have made substantial efforts for automated keyphrase extraction and generation, surprisingly, few studies have been made for \textit{keyphrase completion} (KPC). KPC aims to generate more keyphrases for document (e.g. scientific publication) taking advantage of document content along with a very limited number of known keyphrases, which can be applied to improve text indexing system, etc. In this paper, we propose a novel KPC method with an encoder-decoder framework. We name it \textit{deep keyphrase completion} (DKPC) since it attempts to capture the deep semantic meaning of the document content together with known keyphrases via a deep learning framework. Specifically, the encoder and the decoder in DKPC play different roles to make full use of the known keyphrases. The former considers the keyphrase-guiding factors, which aggregates information of known keyphrases into context. On the contrary, the latter considers the keyphrase-inhibited factor to inhibit semantically repeated keyphrase generation. Extensive experiments on benchmark datasets demonstrate the efficacy of our proposed model.
Vision-and-language (VL) pre-training has proven to be highly effective on various VL downstream tasks. While recent work has shown that fully transformer-based VL models can be more efficient than previous region-feature-based methods, their performance on downstream tasks often degrades significantly. In this paper, we present METER, a Multimodal End-to-end TransformER framework, through which we investigate how to design and pre-train a fully transformer-based VL model in an end-to-end manner. Specifically, we dissect the model designs along multiple dimensions: vision encoders (e.g., CLIP-ViT, Swin transformer), text encoders (e.g., RoBERTa, DeBERTa), multimodal fusion module (e.g., merged attention vs. co-attention), architectural design (e.g., encoder-only vs. encoder-decoder), and pre-training objectives (e.g., masked image modeling). We conduct comprehensive experiments and provide insights on how to train a performant VL transformer. METER achieves an accuracy of 77.64% on the VQAv2 test-std set using only 4M images for pre-training, surpassing the state-of-the-art region-feature-based model by 1.04%, and outperforming the previous best fully transformer-based model by 1.6%. Notably, when further scaled up, our best VQA model achieves an accuracy of 80.54%. Code and pre-trained models are released at https://github.com/zdou0830/METER.
Using a deep autoencoder (DAE) for end-to-end communication in multiple-input multiple-output (MIMO) systems is a novel concept with significant potential. DAE-aided MIMO has been shown to outperform singular-value decomposition (SVD)-based precoded MIMO in terms of bit error rate (BER). This paper proposes embedding left- and right-singular vectors of the channel matrix into DAE encoder and decoder to further improve the performance of the MIMO DAE. SVDembedded DAE largely outperforms theoretic linear precoding in terms of BER. This is remarkable since it demonstrates that DAEs have significant potential to exceed the limits of current system design by treating the communication system as a single, end-to-end optimization block. Based on the simulation results, at SNR=10dB, the proposed SVD-embedded design can achieve a BER of about $10^{-5}$ and reduce the BER at least 10 times compared with existing DAE without SVD, and up to 18 times compared with theoretical linear precoding. We attribute this to the fact that the proposed DAE can match the input and output as an adaptive modulation structure with finite alphabet input. We also observe that adding residual connections to the DAE further improves the performance.