Recently, substantial progress has been made in text ranking based on pretrained language models such as BERT. However, there are limited studies on how to leverage more powerful sequence-to-sequence models such as T5. Existing attempts usually formulate text ranking as classification and rely on postprocessing to obtain a ranked list. In this paper, we propose RankT5 and study two T5-based ranking model structures, an encoder-decoder and an encoder-only one, so that they not only can directly output ranking scores for each query-document pair, but also can be fine-tuned with "pairwise" or "listwise" ranking losses to optimize ranking performances. Our experiments show that the proposed models with ranking losses can achieve substantial ranking performance gains on different public text ranking data sets. Moreover, when fine-tuned with listwise ranking losses, the ranking model appears to have better zero-shot ranking performance on out-of-domain data sets compared to the model fine-tuned with classification losses.
Large-scale pre-trained language models (PLMs) have advanced Graph-to-Text (G2T) generation by processing the linearised version of a graph. However, the linearisation is known to ignore the structural information. Additionally, PLMs are typically pre-trained on free text which introduces domain mismatch between pre-training and downstream G2T generation tasks. To address these shortcomings, we propose graph masking pre-training strategies that neither require supervision signals nor adjust the architecture of the underlying pre-trained encoder-decoder model. When used with a pre-trained T5, our approach achieves new state-of-the-art results on WebNLG+2020 and EventNarrative G2T generation datasets. Our method also shows to be very effective in the low-resource setting.
In this work, we empirically confirm that non-autoregressive translation with an iterative refinement mechanism (IR-NAT) suffers from poor acceleration robustness because it is more sensitive to decoding batch size and computing device setting than autoregressive translation (AT). Inspired by it, we attempt to investigate how to combine the strengths of autoregressive and non-autoregressive translation paradigms better. To this end, we demonstrate through synthetic experiments that prompting a small number of AT's predictions can promote one-shot non-autoregressive translation to achieve the equivalent performance of IR-NAT. Following this line, we propose a new two-stage translation prototype called hybrid-regressive translation (HRT). Specifically, HRT first generates discontinuous sequences via autoregression (e.g., make a prediction every k tokens, k>1) and then fills in all previously skipped tokens at once in a non-autoregressive manner. We also propose a bag of techniques to effectively and efficiently train HRT without adding any model parameters. HRT achieves the state-of-the-art BLEU score of 28.49 on the WMT En-De task and is at least 1.5x faster than AT, regardless of batch size and device. In addition, another bonus of HRT is that it successfully inherits the good characteristics of AT in the deep-encoder-shallow-decoder architecture. Concretely, compared to the vanilla HRT with a 6-layer encoder and 6-layer decoder, the inference speed of HRT with a 12-layer encoder and 1-layer decoder is further doubled on both GPU and CPU without BLEU loss.
In this work, we present a new single-stage method for subject agnostic face swapping and identity transfer, named FaceDancer. We have two major contributions: Adaptive Feature Fusion Attention (AFFA) and Interpreted Feature Similarity Regularization (IFSR). The AFFA module is embedded in the decoder and adaptively learns to fuse attribute features and features conditioned on identity information without requiring any additional facial segmentation process. In IFSR, we leverage the intermediate features in an identity encoder to preserve important attributes such as head pose, facial expression, lighting, and occlusion in the target face, while still transferring the identity of the source face with high fidelity. We conduct extensive quantitative and qualitative experiments on various datasets and show that the proposed FaceDancer outperforms other state-of-the-art networks in terms of identityn transfer, while having significantly better pose preservation than most of the previous methods.
This paper proposes an efficient iris localization method without using iris segmentation and circle fitting. Conventional iris localization methods first extract iris regions by using semantic segmentation methods such as U-Net. Afterward, the inner and outer iris circles are localized using the traditional circle fitting algorithm. However, this approach requires high-resolution encoder-decoder networks for iris segmentation, so it causes computational costs to be high. In addition, traditional circle fitting tends to be sensitive to noise in input images and fitting parameters, causing the iris recognition performance to be poor. To solve these problems, we propose an iris localization network (ILN), that can directly localize pupil and iris circles with eyelid points from a low-resolution iris image. We also introduce a pupil refinement network (PRN) to improve the accuracy of pupil localization. Experimental results show that the combination of ILN and PRN works in 34.5 ms for one iris image on a CPU, and its localization performance outperforms conventional iris segmentation methods. In addition, generalized evaluation results show that the proposed method has higher robustness for datasets in different domain than other segmentation methods. Furthermore, we also confirm that the proposed ILN and PRN improve the iris recognition accuracy.
End-to-end speech recognition models trained using joint Connectionist Temporal Classification (CTC)-Attention loss have gained popularity recently. In these models, a non-autoregressive CTC decoder is often used at inference time due to its speed and simplicity. However, such models are hard to personalize because of their conditional independence assumption that prevents output tokens from previous time steps to influence future predictions. To tackle this, we propose a novel two-way approach that first biases the encoder with attention over a predefined list of rare long-tail and out-of-vocabulary (OOV) words and then uses dynamic boosting and phone alignment network during decoding to further bias the subword predictions. We evaluate our approach on open-source VoxPopuli and in-house medical datasets to showcase a 60% improvement in F1 score on domain-specific rare words over a strong CTC baseline.
The fusion of images taken by heterogeneous sensors helps to enrich the information and improve the quality of imaging. In this article, we present a hybrid model consisting of a convolutional encoder and a Transformer-based decoder to fuse multimodal images. In the encoder, a non-local cross-modal attention block is proposed to capture both local and global dependencies of multiple source images. A branch fusion module is designed to adaptively fuse the features of the two branches. We embed a Transformer module with linear complexity in the decoder to enhance the reconstruction capability of the proposed network. Qualitative and quantitative experiments demonstrate the effectiveness of the proposed method by comparing it with existing state-of-the-art fusion models. The source code of our work is available at https://github.com/pandayuanyu/HCFusion.
Relation extraction typically aims to extract semantic relationships between entities from the unstructured text. One of the most essential data sources for relation extraction is the spoken language, such as interviews and dialogues. However, the error propagation introduced in automatic speech recognition (ASR) has been ignored in relation extraction, and the end-to-end speech-based relation extraction method has been rarely explored. In this paper, we propose a new listening information extraction task, i.e., speech relation extraction. We construct the training dataset for speech relation extraction via text-to-speech systems, and we construct the testing dataset via crowd-sourcing with native English speakers. We explore speech relation extraction via two approaches: the pipeline approach conducting text-based extraction with a pretrained ASR module, and the end2end approach via a new proposed encoder-decoder model, or what we called SpeechRE. We conduct comprehensive experiments to distinguish the challenges in speech relation extraction, which may shed light on future explorations. We share the code and data on https://github.com/wutong8023/SpeechRE.
Existing automatic story evaluation methods place a premium on story lexical level coherence, deviating from human preference. We go beyond this limitation by considering a novel \textbf{Story} \textbf{E}valuation method that mimics human preference when judging a story, namely \textbf{StoryER}, which consists of three sub-tasks: \textbf{R}anking, \textbf{R}ating and \textbf{R}easoning. Given either a machine-generated or a human-written story, StoryER requires the machine to output 1) a preference score that corresponds to human preference, 2) specific ratings and their corresponding confidences and 3) comments for various aspects (e.g., opening, character-shaping). To support these tasks, we introduce a well-annotated dataset comprising (i) 100k ranked story pairs; and (ii) a set of 46k ratings and comments on various aspects of the story. We finetune Longformer-Encoder-Decoder (LED) on the collected dataset, with the encoder responsible for preference score and aspect prediction and the decoder for comment generation. Our comprehensive experiments result in a competitive benchmark for each task, showing the high correlation to human preference. In addition, we have witnessed the joint learning of the preference scores, the aspect ratings, and the comments brings gain in each single task. Our dataset and benchmarks are publicly available to advance the research of story evaluation tasks.\footnote{Dataset and pre-trained model demo are available at anonymous website \url{http://storytelling-lab.com/eval} and \url{https://github.com/sairin1202/StoryER}}
Encoder-only transformer models have been successfully applied to different table understanding tasks, as in TAPAS (Herzig et al., 2020). A major limitation of these architectures is that they are constrained to classification-like tasks such as cell selection or entailment detection. We present TABT5, an encoder-decoder model that generates natural language text based on tables and textual inputs. TABT5 overcomes the encoder-only limitation by incorporating a decoder component and leverages the input structure with table specific embeddings and pre-training. TABT5 achieves new state-of-the-art results on several domains, including spreadsheet formula prediction with a 15% increase in sequence accuracy, QA with a 2.5% increase in sequence accuracy and data-to-text generation with a 2.5% increase in BLEU.
Proteins are macromolecules that perform essential functions in all living organisms. Designing novel proteins with specific structures and desired functions has been a long-standing challenge in the field of bioengineering. Existing approaches generate both protein sequence and structure using either autoregressive models or diffusion models, both of which suffer from high inference costs. In this paper, we propose a new approach capable of protein sequence and structure co-design, which iteratively translates both protein sequence and structure into the desired state from random initialization, based on context features given a priori. Our model consists of a trigonometry-aware encoder that reasons geometrical constraints and interactions from context features, and a roto-translation equivariant decoder that translates protein sequence and structure interdependently. Notably, all protein amino acids are updated in one shot in each translation step, which significantly accelerates the inference process. Experimental results across multiple tasks show that our model outperforms previous state-of-the-art baselines by a large margin, and is able to design proteins of high fidelity as regards both sequence and structure, with running time orders of magnitude less than sampling-based methods.
We propose using a coordinate network decoder for the task of super-resolution in MRI. The continuous signal representation of coordinate networks enables this approach to be scale-agnostic, i.e. one can train over a continuous range of scales and subsequently query at arbitrary resolutions. Due to the difficulty of performing super-resolution on inherently noisy data, we analyze network behavior under multiple denoising strategies. Lastly we compare this method to a standard convolutional decoder using both quantitative metrics and a radiologist study implemented in Voxel, our newly developed tool for web-based evaluation of medical images.
Currently, a significant amount of research has been done in field of Remote Sensing with the use of deep learning techniques. The introduction of Marine Debris Archive (MARIDA), an open-source dataset with benchmark results, for marine debris detection opened new pathways to use deep learning techniques for the task of debris detection and segmentation. This paper introduces a novel attention based segmentation technique that outperforms the existing state-of-the-art results introduced with MARIDA. The paper presents a novel spatial aware encoder and decoder architecture to maintain the contextual information and structure of sparse ground truth patches present in the images. The attained results are expected to pave the path for further research involving deep learning using remote sensing images. The code is available at https://github.com/sheikhazhanmohammed/SADMA.git
Zero-shot Chinese character recognition has attracted rising attention in recent years. Existing methods for this problem are mainly based on either certain low-level stroke-based decomposition or medium-level radical-based decomposition. Considering that the stroke- and radical-level decompositions can provide different levels of information, we propose an effective zero-shot Chinese character recognition method by combining them. The proposed method consists of a training stage and an inference stage. In the training stage, we adopt two similar encoder-decoder models to yield the estimates of stroke and radical encodings, which together with the true encodings are then used to formalize the associated stroke and radical losses for training. A similarity loss is introduced to regularize stroke and radical encoders to yield features of the same characters with high correlation. In the inference stage, two key modules, i.e., the stroke screening module (SSM) and feature matching module (FMM) are introduced to tackle the deterministic and confusing cases respectively. In particular, we introduce an effective stroke rectification scheme in FMM to enlarge the candidate set of characters for final inference. Numerous experiments over three benchmark datasets covering the handwritten, printed artistic and street view scenarios are conducted to demonstrate the effectiveness of the proposed method. Numerical results show that the proposed method outperforms the state-of-the-art methods in both character and radical zero-shot settings, and maintains competitive performance in the traditional seen character setting.
The interpretability of neural networks has recently received extensive attention. Previous prototype-based explainable networks involved prototype activation in both reasoning and interpretation processes, requiring specific explainable structures for the prototype, thus making the network less accurate as it gains interpretability. Therefore, the decoupling prototypical network (DProtoNet) was proposed to avoid this problem. This new model contains encoder, inference, and interpretation modules. As regards the encoder module, unrestricted feature masks were presented to generate expressive features and prototypes. Regarding the inference module, a multi-image prototype learning method was introduced to update prototypes so that the network can learn generalized prototypes. Finally, concerning the interpretation module, a multiple dynamic masks (MDM) decoder was suggested to explain the neural network, which generates heatmaps using the consistent activation of the original image and mask image at the detection nodes of the network. It decouples the inference and interpretation modules of a prototype-based network by avoiding the use of prototype activation to explain the network's decisions in order to simultaneously improve the accuracy and interpretability of the neural network. The multiple public general and medical datasets were tested, and the results confirmed that our method could achieve a 5% improvement in accuracy and state-of-the-art interpretability compared with previous methods.
Non-parametric mesh reconstruction has recently shown significant progress in 3D hand and body applications. In these methods, mesh vertices and edges are visible to neural networks, enabling the possibility to establish a direct mapping between 2D image pixels and 3D mesh vertices. In this paper, we seek to establish and exploit this mapping with a simple and compact architecture. The network is designed with these considerations: 1) aggregating both local 2D image features from the encoder and 3D geometric features captured in the mesh decoder; 2) decoding coarse-to-fine meshes along the decoding layers to make the best use of the hierarchical multi-scale information. Specifically, we propose an end-to-end pipeline for hand mesh recovery tasks which consists of three phases: a 2D feature extractor constructing multi-scale feature maps, a feature mapping module transforming local 2D image features to 3D vertex features via 3D-to-2D projection, and a mesh decoder combining the graph convolution and self-attention to reconstruct mesh. The decoder aggregate both local image features in pixels and geometric features in vertices. It also regresses the mesh vertices in a coarse-to-fine manner, which can leverage multi-scale information. By exploiting the local connection and designing the mesh decoder, Our approach achieves state-of-the-art for hand mesh reconstruction on the public FreiHAND dataset.
Monocular Depth Estimation (MDE) aims to predict pixel-wise depth given a single RGB image. For both, the convolutional as well as the recent attention-based models, encoder-decoder-based architectures have been found to be useful due to the simultaneous requirement of global context and pixel-level resolution. Typically, a skip connection module is used to fuse the encoder and decoder features, which comprises of feature map concatenation followed by a convolution operation. Inspired by the demonstrated benefits of attention in a multitude of computer vision problems, we propose an attention-based fusion of encoder and decoder features. We pose MDE as a pixel query refinement problem, where coarsest-level encoder features are used to initialize pixel-level queries, which are then refined to higher resolutions by the proposed Skip Attention Module (SAM). We formulate the prediction problem as ordinal regression over the bin centers that discretize the continuous depth range and introduce a Bin Center Predictor (BCP) module that predicts bins at the coarsest level using pixel queries. Apart from the benefit of image adaptive depth binning, the proposed design helps learn improved depth embedding in initial pixel queries via direct supervision from the ground truth. Extensive experiments on the two canonical datasets, NYUV2 and KITTI, show that our architecture outperforms the state-of-the-art by 5.3% and 3.9%, respectively, along with an improved generalization performance by 9.4% on the SUNRGBD dataset. Code is available at https://github.com/ashutosh1807/PixelFormer.git.
Accurate passenger flow prediction of urban rail transit is essential for improving the performance of intelligent transportation systems, especially during the epidemic. How to dynamically model the complex spatiotemporal dependencies of passenger flow is the main issue in achieving accurate passenger flow prediction during the epidemic. To solve this issue, this paper proposes a brand-new transformer-based architecture called STformer under the encoder-decoder framework specifically for COVID-19. Concretely, we develop a modified self-attention mechanism named Causal-Convolution ProbSparse Self-Attention (CPSA) to model the multiple temporal dependencies of passenger flow with low computational costs. To capture the complex and dynamic spatial dependencies, we introduce a novel Adaptive Multi-Graph Convolution Network (AMGCN) by leveraging multiple graphs in a self-adaptive manner. Additionally, the Multi-source Data Fusion block fuses the passenger flow data, COVID-19 confirmed case data, and the relevant social media data to study the impact of COVID-19 to passenger flow. Experiments on real-world passenger flow datasets demonstrate the superiority of ST-former over the other eleven state-of-the-art methods. Several ablation studies are carried out to verify the effectiveness and reliability of our model structure. Results can provide critical insights for the operation of URT systems.
In this paper, we prove the representation defects of a cascaded convolutional decoder network, considering the capacity of representing different frequency components of an input sample. We conduct the discrete Fourier transform on each channel of the feature map in an intermediate layer of the decoder network. Then, we extend the 2D circular convolution theorem to represent the forward and backward propagations through convolutional layers in the frequency domain. Based on this, we prove three defects in representing feature spectrums. First, we prove that the convolution operation, the zero-padding operation, and a set of other settings all make a convolutional decoder network more likely to weaken high-frequency components. Second, we prove that the upsampling operation generates a feature spectrum, in which strong signals repetitively appear at certain frequencies. Third, we prove that if the frequency components in the input sample and frequency components in the target output for regression have a small shift, then the decoder usually cannot be effectively learned.
TV subtitles are a rich source of transcriptions of many types of speech, ranging from read speech in news reports to conversational and spontaneous speech in talk shows and soaps. However, subtitles are not verbatim (i.e. exact) transcriptions of speech, so they cannot be used directly to improve an Automatic Speech Recognition (ASR) model. We propose a multitask dual-decoder Transformer model that jointly performs ASR and automatic subtitling. The ASR decoder (possibly pre-trained) predicts the verbatim output and the subtitle decoder generates a subtitle, while sharing the encoder. The two decoders can be independent or connected. The model is trained to perform both tasks jointly, and is able to effectively use subtitle data. We show improvements on regular ASR and on spontaneous and conversational ASR by incorporating the additional subtitle decoder. The method does not require preprocessing (aligning, filtering, pseudo-labeling, ...) of the subtitles.