We propose an approach to generate images of people given a desired appearance and pose. Disentangled representations of pose and appearance are necessary to handle the compound variability in the resulting generated images. Hence, we develop an approach based on intermediate representations of poses and appearance: our pose-guided appearance rendering network firstly encodes the targets' poses using an encoder-decoder neural network. Then the targets' appearances are encoded by learning adaptive appearance filters using a fully convolutional network. Finally, these filters are placed in the encoder-decoder neural networks to complete the rendering. We demonstrate that our model can generate images and videos that are superior to state-of-the-art methods, and can handle pose guided appearance rendering in both image and video generation.
Recently, large-scale transformer-based models have been proven to be effective over various tasks across many domains. Nevertheless, applying them in industrial production requires tedious and heavy works to reduce inference costs. To fill such a gap, we introduce a scalable inference solution: Easy and Efficient Transformer (EET), including a series of transformer inference optimization at the algorithm and implementation levels. First, we design highly optimized kernels for long inputs and large hidden sizes. Second, we propose a flexible CUDA memory manager to reduce the memory footprint when deploying a large model. Compared with the state-of-the-art transformer inference library (Faster Transformer v4.0), EET can achieve an average of 1.40-4.20x speedup on the transformer decoder layer with an A100 GPU
Despite the significant progress made by deep learning in natural image matting, there has been so far no representative work on deep learning for video matting due to the inherent technical challenges in reasoning temporal domain and lack of large-scale video matting datasets. In this paper, we propose a deep learning-based video matting framework which employs a novel and effective spatio-temporal feature aggregation module (ST-FAM). As optical flow estimation can be very unreliable within matting regions, ST-FAM is designed to effectively align and aggregate information across different spatial scales and temporal frames within the network decoder. To eliminate frame-by-frame trimap annotations, a lightweight interactive trimap propagation network is also introduced. The other contribution consists of a large-scale video matting dataset with groundtruth alpha mattes for quantitative evaluation and real-world high-resolution videos with trimaps for qualitative evaluation. Quantitative and qualitative experimental results show that our framework significantly outperforms conventional video matting and deep image matting methods applied to video in presence of multi-frame temporal information.
Predicting future behavior of the surrounding vehicles is crucial for self-driving platforms to safely navigate through other traffic. This is critical when making decisions like crossing an unsignalized intersection. We address the problem of vehicle motion prediction in a challenging roundabout environment by learning from human driver data. We extend existing recurrent encoder-decoder models to be advantageously combined with anchor trajectories to predict vehicle behaviors on a roundabout. Drivers' intentions are encoded by a set of maneuvers that correspond to semantic driving concepts. Accordingly, our model employs a set of maneuver-specific anchor trajectories that cover the space of possible outcomes at the roundabout. The proposed model can output a multi-modal distribution over the predicted future trajectories based on the maneuver-specific anchors. We evaluate our model using the public RounD dataset and the experiment results show the effectiveness of the proposed maneuver-based anchor regression in improving prediction accuracy, reducing the average RMSE to 28% less than the best baseline. Our code is available at https://github.com/m-hasan-n/roundabout.
Differentiable simulations of optical systems can be combined with deep learning-based reconstruction networks to enable high performance computational imaging via end-to-end (E2E) optimization of both the optical encoder and the deep decoder. This has enabled imaging applications such as 3D localization microscopy, depth estimation, and lensless photography via the optimization of local optical encoders. More challenging computational imaging applications, such as 3D snapshot microscopy which compresses 3D volumes into single 2D images, require a highly non-local optical encoder. We show that existing deep network decoders have a locality bias which prevents the optimization of such highly non-local optical encoders. We address this with a decoder based on a shallow neural network architecture using global kernel Fourier convolutional neural networks (FourierNets). We show that FourierNets surpass existing deep network based decoders at reconstructing photographs captured by the highly non-local DiffuserCam optical encoder. Further, we show that FourierNets enable E2E optimization of highly non-local optical encoders for 3D snapshot microscopy. By combining FourierNets with a large-scale multi-GPU differentiable optical simulation, we are able to optimize non-local optical encoders 170$\times$ to 7372$\times$ larger than prior state of the art, and demonstrate the potential for ROI-type specific optical encoding with a programmable microscope.
Abstractive conversation summarization has received much attention recently. However, these generated summaries often suffer from insufficient, redundant, or incorrect content, largely due to the unstructured and complex characteristics of human-human interactions. To this end, we propose to explicitly model the rich structures in conversations for more precise and accurate conversation summarization, by first incorporating discourse relations between utterances and action triples ("who-doing-what") in utterances through structured graphs to better encode conversations, and then designing a multi-granularity decoder to generate summaries by combining all levels of information. Experiments show that our proposed models outperform state-of-the-art methods and generalize well in other domains in terms of both automatic evaluations and human judgments. We have publicly released our code at https://github.com/GT-SALT/Structure-Aware-BART.
Previous work mainly focuses on improving cross-lingual transfer for NLU tasks with a multilingual pretrained encoder (MPE), or improving the performance on supervised machine translation with BERT. However, it is under-explored that whether the MPE can help to facilitate the cross-lingual transferability of NMT model. In this paper, we focus on a zero-shot cross-lingual transfer task in NMT. In this task, the NMT model is trained with parallel dataset of only one language pair and an off-the-shelf MPE, then it is directly tested on zero-shot language pairs. We propose SixT, a simple yet effective model for this task. SixT leverages the MPE with a two-stage training schedule and gets further improvement with a position disentangled encoder and a capacity-enhanced decoder. Using this method, SixT significantly outperforms mBART, a pretrained multilingual encoder-decoder model explicitly designed for NMT, with an average improvement of 7.1 BLEU on zero-shot any-to-English test sets across 14 source languages. Furthermore, with much less training computation cost and training data, our model achieves better performance on 15 any-to-English test sets than CRISS and m2m-100, two strong multilingual NMT baselines.
The advance of image editing techniques allows users to create artistic works, but the manipulated regions may be incompatible with the background. Localizing the inharmonious region is an appealing yet challenging task. Realizing that this task requires effective aggregation of multi-scale contextual information and suppression of redundant information, we design novel Bi-directional Feature Integration (BFI) block and Global-context Guided Decoder (GGD) block to fuse multi-scale features in the encoder and decoder respectively. We also employ Mask-guided Dual Attention (MDA) block between the encoder and decoder to suppress the redundant information. Experiments on the image harmonization dataset demonstrate that our method achieves competitive performance for inharmonious region localization. The source code is available at https://github.com/bcmi/DIRL.
Image light source transfer (LLST), as the most challenging task in the domain of image relighting, has attracted extensive attention in recent years. In the latest research, LLST is decomposed three sub-tasks: scene reconversion, shadow estimation, and image re-rendering, which provides a new paradigm for image relighting. However, many problems for scene reconversion and shadow estimation tasks, including uncalibrated feature information and poor semantic information, are still unresolved, thereby resulting in insufficient feature representation. In this paper, we propose novel down-sampling feature self-calibrated block (DFSB) and up-sampling feature self-calibrated block (UFSB) as the basic blocks of feature encoder and decoder to calibrate feature representation iteratively because the LLST is similar to the recalibration of image light source. In addition, we fuse the multi-scale features of the decoder in scene reconversion task to further explore and exploit more semantic information, thereby providing more accurate primary scene structure for image re-rendering. Experimental results in the VIDIT dataset show that the proposed approach significantly improves the performance for LLST.
Few researches have been proposed specifically for real-time semantic segmentation in rainy environments. However, the demand in this area is huge and it is challenging for lightweight networks. Therefore, this paper proposes a lightweight network which is specially designed for the foreground segmentation in rainy environments, named De-raining Semantic Segmentation Network (DRSNet). By analyzing the characteristics of raindrops, the MultiScaleSE Block is targetedly designed to encode the input image, it uses multi-scale dilated convolutions to increase the receptive field, and SE attention mechanism to learn the weights of each channels. In order to combine semantic information between different encoder and decoder layers, it is proposed to use Asymmetric Skip, that is, the higher semantic layer of encoder employs bilinear interpolation and the output passes through pointwise convolution, then added element-wise to the lower semantic layer of decoder. According to the control experiments, the performances of MultiScaleSE Block and Asymmetric Skip compared with SEResNet18 and Symmetric Skip respectively are improved to a certain degree on the Foreground Accuracy index. The parameters and the floating point of operations (FLOPs) of DRSNet is only 0.54M and 0.20GFLOPs separately. The state-of-the-art results and real-time performances are achieved on both the UESTC all-day Scenery add rain (UAS-add-rain) and the Baidu People Segmentation add rain (BPS-add-rain) benchmarks with the input sizes of 192*128, 384*256 and 768*512. The speed of DRSNet exceeds all the networks within 1GFLOPs, and Foreground Accuracy index is also the best among the similar magnitude networks on both benchmarks.
Recent work in cross-lingual semantic parsing has successfully applied machine translation to localize parsers to new languages. However, these advances assume access to high-quality machine translation systems and word alignment tools. We remove these assumptions and study cross-lingual semantic parsing as a zero-shot problem, without parallel data (i.e., utterance-logical form pairs) for new languages. We propose a multi-task encoder-decoder model to transfer parsing knowledge to additional languages using only English-logical form paired data and in-domain natural language corpora in each new language. Our model encourages language-agnostic encodings by jointly optimizing for logical-form generation with auxiliary objectives designed for cross-lingual latent representation alignment. Our parser performs significantly above translation-based baselines and, in some cases, competes with the supervised upper-bound.
Existing pre-trained language models (PLMs) have demonstrated the effectiveness of self-supervised learning for a broad range of natural language processing (NLP) tasks. However, most of them are not explicitly aware of domain-specific knowledge, which is essential for downstream tasks in many domains, such as tasks in e-commerce scenarios. In this paper, we propose K-PLUG, a knowledge-injected pre-trained language model based on the encoder-decoder transformer that can be transferred to both natural language understanding and generation tasks. We verify our method in a diverse range of e-commerce scenarios that require domain-specific knowledge. Specifically, we propose five knowledge-aware self-supervised pre-training objectives to formulate the learning of domain-specific knowledge, including e-commerce domain-specific knowledge-bases, aspects of product entities, categories of product entities, and unique selling propositions of product entities. K-PLUG achieves new state-of-the-art results on a suite of domain-specific NLP tasks, including product knowledge base completion, abstractive product summarization, and multi-turn dialogue, significantly outperforms baselines across the board, which demonstrates that the proposed method effectively learns a diverse set of domain-specific knowledge for both language understanding and generation tasks.
Recently, it has been argued that encoder-decoder models can be made more interpretable by replacing the softmax function in the attention with its sparse variants. In this work, we introduce a novel, simple method for achieving sparsity in attention: we replace the softmax activation with a ReLU, and show that sparsity naturally emerges from such a formulation. Training stability is achieved with layer normalization with either a specialized initialization or an additional gating function. Our model, which we call Rectified Linear Attention (ReLA), is easy to implement and more efficient than previously proposed sparse attention mechanisms. We apply ReLA to the Transformer and conduct experiments on five machine translation tasks. ReLA achieves translation performance comparable to several strong baselines, with training and decoding speed similar to that of the vanilla attention. Our analysis shows that ReLA delivers high sparsity rate and head diversity, and the induced cross attention achieves better accuracy with respect to source-target word alignment than recent sparsified softmax-based models. Intriguingly, ReLA heads also learn to attend to nothing (i.e. 'switch off') for some queries, which is not possible with sparsified softmax alternatives.
In this paper, we present a regression-based pose recognition method using cascade Transformers. One way to categorize the existing approaches in this domain is to separate them into 1). heatmap-based and 2). regression-based. In general, heatmap-based methods achieve higher accuracy but are subject to various heuristic designs (not end-to-end mostly), whereas regression-based approaches attain relatively lower accuracy but they have less intermediate non-differentiable steps. Here we utilize the encoder-decoder structure in Transformers to perform regression-based person and keypoint detection that is general-purpose and requires less heuristic design compared with the existing approaches. We demonstrate the keypoint hypothesis (query) refinement process across different self-attention layers to reveal the recursive self-attention mechanism in Transformers. In the experiments, we report competitive results for pose recognition when compared with the competing regression-based methods.
We introduce DatasetGAN: an automatic procedure to generate massive datasets of high-quality semantically segmented images requiring minimal human effort. Current deep networks are extremely data-hungry, benefiting from training on large-scale datasets, which are time consuming to annotate. Our method relies on the power of recent GANs to generate realistic images. We show how the GAN latent code can be decoded to produce a semantic segmentation of the image. Training the decoder only needs a few labeled examples to generalize to the rest of the latent space, resulting in an infinite annotated dataset generator! These generated datasets can then be used for training any computer vision architecture just as real datasets are. As only a few images need to be manually segmented, it becomes possible to annotate images in extreme detail and generate datasets with rich object and part segmentations. To showcase the power of our approach, we generated datasets for 7 image segmentation tasks which include pixel-level labels for 34 human face parts, and 32 car parts. Our approach outperforms all semi-supervised baselines significantly and is on par with fully supervised methods, which in some cases require as much as 100x more annotated data as our method.
We consider the problem of learning to simplify medical texts. This is important because most reliable, up-to-date information in biomedicine is dense with jargon and thus practically inaccessible to the lay audience. Furthermore, manual simplification does not scale to the rapidly growing body of biomedical literature, motivating the need for automated approaches. Unfortunately, there are no large-scale resources available for this task. In this work we introduce a new corpus of parallel texts in English comprising technical and lay summaries of all published evidence pertaining to different clinical topics. We then propose a new metric based on likelihood scores from a masked language model pretrained on scientific texts. We show that this automated measure better differentiates between technical and lay summaries than existing heuristics. We introduce and evaluate baseline encoder-decoder Transformer models for simplification and propose a novel augmentation to these in which we explicitly penalize the decoder for producing "jargon" terms; we find that this yields improvements over baselines in terms of readability.
Deep generative models can synthesize photorealistic images of human faces with novel identities. However, a key challenge to the wide applicability of such techniques is to provide independent control over semantically meaningful parameters: appearance, head pose, face shape, and facial expressions. In this paper, we propose VariTex - to the best of our knowledge the first method that learns a variational latent feature space of neural face textures, which allows sampling of novel identities. We combine this generative model with a parametric face model and gain explicit control over head pose and facial expressions. To generate complete images of human heads, we propose an additive decoder that adds plausible details such as hair. A novel training scheme enforces a pose-independent latent space and in consequence, allows learning a one-to-many mapping between latent codes and pose-conditioned exterior regions. The resulting method can generate geometrically consistent images of novel identities under fine-grained control over head pose, face shape, and facial expressions. This facilitates a broad range of downstream tasks, like sampling novel identities, changing the head pose, expression transfer, and more. Code and models are available for research on https://mcbuehler.github.io/VariTex.
In this paper, we propose SC-GlowTTS: an efficient zero-shot multi-speaker text-to-speech model that improves similarity for speakers unseen during training. We propose a speaker-conditional architecture that explores a flow-based decoder that works in a zero-shot scenario. As text encoders, we explore a dilated residual convolutional-based encoder, gated convolutional-based encoder, and transformer-based encoder. Additionally, we have shown that adjusting a GAN-based vocoder for the spectrograms predicted by the TTS model on the training dataset can significantly improve the similarity and speech quality for new speakers. Our model converges using only 11 speakers, reaching state-of-the-art results for similarity with new speakers, as well as high speech quality.
The reading of arbitrarily-shaped text has received increasing research attention. However, existing text spotters are mostly built on two-stage frameworks or character-based methods, which suffer from either Non-Maximum Suppression (NMS), Region-of-Interest (RoI) operations, or character-level annotations. In this paper, to address the above problems, we propose a novel fully convolutional Point Gathering Network (PGNet) for reading arbitrarily-shaped text in real-time. The PGNet is a single-shot text spotter, where the pixel-level character classification map is learned with proposed PG-CTC loss avoiding the usage of character-level annotations. With a PG-CTC decoder, we gather high-level character classification vectors from two-dimensional space and decode them into text symbols without NMS and RoI operations involved, which guarantees high efficiency. Additionally, reasoning the relations between each character and its neighbors, a graph refinement module (GRM) is proposed to optimize the coarse recognition and improve the end-to-end performance. Experiments prove that the proposed method achieves competitive accuracy, meanwhile significantly improving the running speed. In particular, in Total-Text, it runs at 46.7 FPS, surpassing the previous spotters with a large margin.
The explosion of user-generated content (UGC)--e.g. social media posts, comments, and reviews--has motivated the development of NLP applications tailored to these types of informal texts. Prevalent among these applications have been sentiment analysis and machine translation (MT). Grounded in the observation that UGC features highly idiomatic, sentiment-charged language, we propose a decoder-side approach that incorporates automatic sentiment scoring into the MT candidate selection process. We train separate English and Spanish sentiment classifiers, then, using n-best candidates generated by a baseline MT model with beam search, select the candidate that minimizes the absolute difference between the sentiment score of the source sentence and that of the translation, and perform a human evaluation to assess the produced translations. Unlike previous work, we select this minimally divergent translation by considering the sentiment scores of the source sentence and translation on a continuous interval, rather than using e.g. binary classification, allowing for more fine-grained selection of translation candidates. The results of human evaluations show that, in comparison to the open-source MT baseline model on top of which our sentiment-based pipeline is built, our pipeline produces more accurate translations of colloquial, sentiment-heavy source texts.