This paper presents a neural network built upon Transformers, namely PlaneTR, to simultaneously detect and reconstruct planes from a single image. Different from previous methods, PlaneTR jointly leverages the context information and the geometric structures in a sequence-to-sequence way to holistically detect plane instances in one forward pass. Specifically, we represent the geometric structures as line segments and conduct the network with three main components: (i) context and line segments encoders, (ii) a structure-guided plane decoder, (iii) a pixel-wise plane embedding decoder. Given an image and its detected line segments, PlaneTR generates the context and line segment sequences via two specially designed encoders and then feeds them into a Transformers-based decoder to directly predict a sequence of plane instances by simultaneously considering the context and global structure cues. Finally, the pixel-wise embeddings are computed to assign each pixel to one predicted plane instance which is nearest to it in embedding space. Comprehensive experiments demonstrate that PlaneTR achieves a state-of-the-art performance on the ScanNet and NYUv2 datasets.
Arbitrary shape text detection is a challenging task due to the high complexity and variety of scene texts. In this work, we propose a novel adaptive boundary proposal network for arbitrary shape text detection, which can learn to directly produce accurate boundary for arbitrary shape text without any post-processing. Our method mainly consists of a boundary proposal model and an innovative adaptive boundary deformation model. The boundary proposal model constructed by multi-layer dilated convolutions is adopted to produce prior information (including classification map, distance field, and direction field) and coarse boundary proposals. The adaptive boundary deformation model is an encoder-decoder network, in which the encoder mainly consists of a Graph Convolutional Network (GCN) and a Recurrent Neural Network (RNN). It aims to perform boundary deformation in an iterative way for obtaining text instance shape guided by prior information from the boundary proposal model. In this way, our method can directly and efficiently generate accurate text boundaries without complex post-processing. Extensive experiments on publicly available datasets demonstrate the state-of-the-art performance of our method.
The U-Net architecture, built upon the fully convolutional network, has proven to be effective in biomedical image segmentation. However, U-Net applies skip connections to merge semantically different low- and high-level convolutional features, resulting in not only blurred feature maps, but also over- and under-segmented target regions. To address these limitations, we propose a simple, yet effective end-to-end depthwise encoder-decoder fully convolutional network architecture, called Sharp U-Net, for binary and multi-class biomedical image segmentation. The key rationale of Sharp U-Net is that instead of applying a plain skip connection, a depthwise convolution of the encoder feature map with a sharpening kernel filter is employed prior to merging the encoder and decoder features, thereby producing a sharpened intermediate feature map of the same size as the encoder map. Using this sharpening filter layer, we are able to not only fuse semantically less dissimilar features, but also to smooth out artifacts throughout the network layers during the early stages of training. Our extensive experiments on six datasets show that the proposed Sharp U-Net model consistently outperforms or matches the recent state-of-the-art baselines in both binary and multi-class segmentation tasks, while adding no extra learnable parameters. Furthermore, Sharp U-Net outperforms baselines that have more than three times the number of learnable parameters.
Since the superiority of Transformer in learning long-term dependency, the sign language Transformer model achieves remarkable progress in Sign Language Recognition (SLR) and Translation (SLT). However, there are several issues with the Transformer that prevent it from better sign language understanding. The first issue is that the self-attention mechanism learns sign video representation in a frame-wise manner, neglecting the temporal semantic structure of sign gestures. Secondly, the attention mechanism with absolute position encoding is direction and distance unaware, thus limiting its ability. To address these issues, we propose a new model architecture, namely PiSLTRc, with two distinctive characteristics: (i) content-aware and position-aware convolution layers. Specifically, we explicitly select relevant features using a novel content-aware neighborhood gathering method. Then we aggregate these features with position-informed temporal convolution layers, thus generating robust neighborhood-enhanced sign representation. (ii) injecting the relative position information to the attention mechanism in the encoder, decoder, and even encoder-decoder cross attention. Compared with the vanilla Transformer model, our model performs consistently better on three large-scale sign language benchmarks: PHOENIX-2014, PHOENIX-2014-T and CSL. Furthermore, extensive experiments demonstrate that the proposed method achieves state-of-the-art performance on translation quality with $+1.6$ BLEU improvements.
Much research in recent years has focused on automatic article commenting. However, few of previous studies focus on the controllable generation of comments. Besides, they tend to generate dull and commonplace comments, which further limits their practical application. In this paper, we make the first step towards controllable generation of comments, by building a system that can explicitly control the emotion of the generated comments. To achieve this, we associate each kind of emotion category with an embedding and adopt a dynamic fusion mechanism to fuse this embedding into the decoder. A sentence-level emotion classifier is further employed to better guide the model to generate comments expressing the desired emotion. To increase the diversity of the generated comments, we propose a hierarchical copy mechanism that allows our model to directly copy words from the input articles. We also propose a restricted beam search (RBS) algorithm to increase intra-sentence diversity. Experimental results show that our model can generate informative and diverse comments that express the desired emotions with high accuracy.
Versatile Video Coding (VVC) is the next generation video coding standard finalized in July 2020. VVC introduces new coding tools enhancing the coding efficiency compared to its predecessor High Efficiency Video Coding (HEVC). These new tools have a significant impact on the VVC software decoder complexity estimated to 2 times HEVC decoder complexity. In particular, the transform module includes in VVC separable and non-separable transforms named Multiple Transform Selection (MTS) and Low Frequency Non-Separable Transform (LFNST) tools, respectively. In this paper, we present an area-efficient hardware architecture of the inverse transform module for a VVC decoder. The proposed design uses a total of 64 regular multipliers in a pipelined architecture targeting Application-Specific Integrated Circuit (ASIC) platforms. It consists in a multi-standard architecture that supports the transform modules of recent MPEG standards including Advanced Video Coding (AVC), HEVC and VVC. The architecture leverages all primary and secondary transforms optimisations including butterfly de-composition, coefficients zeroing and the inherent linear relationship between the transforms. The synthesized results show that the proposed method sustains a constant throughput of 1sample per cycle and a constant latency for all block sizes. The proposed hardware inverse transform module operates at 600MHz frequency enabling to decode in real-time 4K video at 30 frames per second in 4:2:2 chroma sub-sampling format. The proposed module has been integrated in an ASIC UHD decoder targeting energy-aware decoding of VVC videos on consumer devices.
Cross-contrast image translation is an important task for completing missing contrasts in clinical diagnosis. However, most existing methods learn separate translator for each pair of contrasts, which is inefficient due to many possible contrast pairs in real scenarios. In this work, we propose a unified Hyper-GAN model for effectively and efficiently translating between different contrast pairs. Hyper-GAN consists of a pair of hyper-encoder and hyper-decoder to first map from the source contrast to a common feature space, and then further map to the target contrast image. To facilitate the translation between different contrast pairs, contrast-modulators are designed to tune the hyper-encoder and hyper-decoder adaptive to different contrasts. We also design a common space loss to enforce that multi-contrast images of a subject share a common feature space, implicitly modeling the shared underlying anatomical structures. Experiments on two datasets of IXI and BraTS 2019 show that our Hyper-GAN achieves state-of-the-art results in both accuracy and efficiency, e.g., improving more than 1.47 and 1.09 dB in PSNR on two datasets with less than half the amount of parameters.
Brain tumor is the most common and deadliest disease that can be found in all age groups. Generally, MRI modality is adopted for identifying and diagnosing tumors by the radiologists. The correct identification of tumor regions and its type can aid to diagnose tumors with the followup treatment plans. However, for any radiologist analysing such scans is a complex and time-consuming task. Motivated by the deep learning based computer-aided-diagnosis systems, this paper proposes multi-task attention guided encoder-decoder network (MAG-Net) to classify and segment the brain tumor regions using MRI images. The MAG-Net is trained and evaluated on the Figshare dataset that includes coronal, axial, and sagittal views with 3 types of tumors meningioma, glioma, and pituitary tumor. With exhaustive experimental trials the model achieved promising results as compared to existing state-of-the-art models, while having least number of training parameters among other state-of-the-art models.
Dynamic scene graph generation aims at generating a scene graph of the given video. Compared to the task of scene graph generation from images, it is more challenging because of the dynamic relationships between objects and the temporal dependencies between frames allowing for a richer semantic interpretation. In this paper, we propose Spatial-temporal Transformer (STTran), a neural network that consists of two core modules: (1) a spatial encoder that takes an input frame to extract spatial context and reason about the visual relationships within a frame, and (2) a temporal decoder which takes the output of the spatial encoder as input in order to capture the temporal dependencies between frames and infer the dynamic relationships. Furthermore, STTran is flexible to take varying lengths of videos as input without clipping, which is especially important for long videos. Our method is validated on the benchmark dataset Action Genome (AG). The experimental results demonstrate the superior performance of our method in terms of dynamic scene graphs. Moreover, a set of ablative studies is conducted and the effect of each proposed module is justified. Code available at: https://github.com/yrcong/STTran.
Although text recognition has significantly evolved over the years, state-of-the-art (SOTA) models still struggle in the wild scenarios due to complex backgrounds, varying fonts, uncontrolled illuminations, distortions and other artefacts. This is because such models solely depend on visual information for text recognition, thus lacking semantic reasoning capabilities. In this paper, we argue that semantic information offers a complementary role in addition to visual only. More specifically, we additionally utilize semantic information by proposing a multi-stage multi-scale attentional decoder that performs joint visual-semantic reasoning. Our novelty lies in the intuition that for text recognition, the prediction should be refined in a stage-wise manner. Therefore our key contribution is in designing a stage-wise unrolling attentional decoder where non-differentiability, invoked by discretely predicted character labels, needs to be bypassed for end-to-end training. While the first stage predicts using visual features, subsequent stages refine on top of it using joint visual-semantic information. Additionally, we introduce multi-scale 2D attention along with dense and residual connections between different stages to deal with varying scales of character sizes, for better performance and faster convergence during training. Experimental results show our approach to outperform existing SOTA methods by a considerable margin.
Recently, researchers have explored using the encoder-decoder framework to tackle dialogue state tracking (DST), which is a key component of task-oriented dialogue systems. However, they regard a multi-turn dialogue as a flat sequence, failing to focus on useful information when the sequence is long. In this paper, we propose a Hierarchical Dynamic Copy Network (HDCN) to facilitate focusing on the most informative turn, making it easier to extract slot values from the dialogue context. Based on the encoder-decoder framework, we adopt a hierarchical copy approach that calculates two levels of attention at the word- and turn-level, which are then renormalized to obtain the final copy distribution. A focus loss term is employed to encourage the model to assign the highest turn-level attention weight to the most informative turn. Experimental results show that our model achieves 46.76% joint accuracy on the MultiWOZ 2.1 dataset.
Accurate image segmentation plays a crucial role in medical image analysis, yet it faces great challenges of various shapes, diverse sizes, and blurry boundaries. To address these difficulties, square kernel-based encoder-decoder architecture has been proposed and widely used, but its performance remains still unsatisfactory. To further cope with these challenges, we present a novel double-branch encoder architecture. Our architecture is inspired by two observations: 1) Since the discrimination of features learned via square convolutional kernels needs to be further improved, we propose to utilize non-square vertical and horizontal convolutional kernels in the double-branch encoder, so features learned by the two branches can be expected to complement each other. 2) Considering that spatial attention can help models to better focus on the target region in a large-sized image, we develop an attention loss to further emphasize the segmentation on small-sized targets. Together, the above two schemes give rise to a novel double-branch encoder segmentation framework for medical image segmentation, namely Crosslink-Net. The experiments validate the effectiveness of our model on four datasets. The code is released at https://github.com/Qianyu1226/Crosslink-Net.
AI-based methods have been widely applied to tourism demand forecasting. However, current AI-based methods are short of the ability to process long-term dependency, and most of them lack interpretability. The Transformer used initially for machine translation shows an incredible ability to long-term dependency processing. Based on the Transformer, we proposed a time series Transformer (Tsformer) with Encoder-Decoder architecture for tourism demand forecasting. The proposed Tsformer encodes long-term dependency with encoder, captures short-term dependency with decoder, and simplifies the attention interactions under the premise of highlighting dominant attention through a series of attention masking mechanisms. These improvements make the multi-head attention mechanism process the input sequence according to the time relationship, contributing to better interpretability. What's more, the context processing ability of the Encoder-Decoder architecture allows adopting the calendar of days to be forecasted to enhance the forecasting performance. Experiments conducted on the Jiuzhaigou valley and Siguniang mountain tourism demand datasets with other nine baseline methods indicate that the proposed Tsformer outperformed all baseline models in the short-term and long-term tourism demand forecasting tasks. Moreover, ablation studies demonstrate that the adoption of the calendar of days to be forecasted contributes to the forecasting performance of the proposed Tsformer. For better interpretability, the attention weight matrix visualization is performed. It indicates that the Tsformer concentrates on seasonal features and days close to days to be forecast in short-term forecasting.
Automated headline generation for online news articles is not a trivial task - machine generated titles need to be grammatically correct, informative, capture attention and generate search traffic without being "click baits" or "fake news". In this paper we showcase how a pre-trained language model can be leveraged to create an abstractive news headline generator for German language. We incorporate state of the art fine-tuning techniques for abstractive text summarization, i.e. we use different optimizers for the encoder and decoder where the former is pre-trained and the latter is trained from scratch. We modify the headline generation to incorporate frequently sought keywords relevant for search engine optimization. We conduct experiments on a German news data set and achieve a ROUGE-L-gram F-score of 40.02. Furthermore, we address the limitations of ROUGE for measuring the quality of text summarization by introducing a sentence similarity metric and human evaluation.
An autoencoder-based codec employs quantization to turn its bottleneck layer activation into bitstrings, a process that hinders information flow between the encoder and decoder parts. To circumvent this issue, we employ additional skip connections between the corresponding pair of encoder-decoder layers. The assumption is that, in a mirrored autoencoder topology, a decoder layer reconstructs the intermediate feature representation of its corresponding encoder layer. Hence, any additional information directly propagated from the corresponding encoder layer helps the reconstruction. We implement this kind of skip connections in the form of additional autoencoders, each of which is a small codec that compresses the massive data transfer between the paired encoder-decoder layers. We empirically verify that the proposed hyper-autoencoded architecture improves perceptual audio quality compared to an ordinary autoencoder baseline.
This paper presents a simple and effective approach to solving the multi-label classification problem. The proposed approach leverages Transformer decoders to query the existence of a class label. The use of Transformer is rooted in the need of extracting local discriminative features adaptively for different labels, which is a strongly desired property due to the existence of multiple objects in one image. The built-in cross-attention module in the Transformer decoder offers an effective way to use label embeddings as queries to probe and pool class-related features from a feature map computed by a vision backbone for subsequent binary classifications. Compared with prior works, the new framework is simple, using standard Transformers and vision backbones, and effective, consistently outperforming all previous works on five multi-label classification data sets, including MS-COCO, PASCAL VOC, NUS-WIDE, and Visual Genome. Particularly, we establish $91.3\%$ mAP on MS-COCO. We hope its compact structure, simple implementation, and superior performance serve as a strong baseline for multi-label classification tasks and future studies. The code will be available soon at https://github.com/SlongLiu/query2labels.
Transformer-based encoder-decoder models produce a fused token-wise representation after every encoder layer. We investigate the effects of allowing the encoder to preserve and explore alternative hypotheses, combined at the end of the encoding process. To that end, we design and examine a $\textit{Multi-stream Transformer}$ architecture and find that splitting the Transformer encoder into multiple encoder streams and allowing the model to merge multiple representational hypotheses improves performance, with further improvement obtained by adding a skip connection between the first and the final encoder layer.
Power device reliability is a major concern during operation under extreme environments, as doing so reduces the operational lifetime of any power system or sensing infrastructure. Due to a potential for system failure, devices must be experimentally validated before implementation, which is expensive and time-consuming. In this paper, we have utilized machine learning algorithms to predict device reliability, significantly reducing the need for conducting experiments. To train the models, we have tested 224 power devices from 10 different manufacturers. First, we describe a method to process the data for modeling purposes. Based on the in-house testing data, we implemented various ML models and observed that computational models such as Gradient Boosting and LSTM encoder-decoder networks can predict power device failure with high accuracy.
Audio captioning aims to automatically generate a natural language description of an audio clip. Most captioning models follow an encoder-decoder architecture, where the decoder predicts words based on the audio features extracted by the encoder. Convolutional neural networks (CNNs) and recurrent neural networks (RNNs) are often used as the audio encoder. However, CNNs can be limited in modelling temporal relationships among the time frames in an audio signal, while RNNs can be limited in modelling the long-range dependencies among the time frames. In this paper, we propose an Audio Captioning Transformer (ACT), which is a full Transformer network based on an encoder-decoder architecture and is totally convolution-free. The proposed method has a better ability to model the global information within an audio signal as well as capture temporal relationships between audio events. We evaluate our model on AudioCaps, which is the largest audio captioning dataset publicly available. Our model shows competitive performance compared to other state-of-the-art approaches.
Automated Audio captioning (AAC) is a cross-modal translation task that aims to use natural language to describe the content of an audio clip. As shown in the submissions received for Task 6 of the DCASE 2021 Challenges, this problem has received increasing interest in the community. The existing AAC systems are usually based on an encoder-decoder architecture, where the audio signal is encoded into a latent representation, and aligned with its corresponding text descriptions, then a decoder is used to generate the captions. However, training of an AAC system often encounters the problem of data scarcity, which may lead to inaccurate representation and audio-text alignment. To address this problem, we propose a novel encoder-decoder framework called Contrastive Loss for Audio Captioning (CL4AC). In CL4AC, the self-supervision signals derived from the original audio-text paired data are used to exploit the correspondences between audio and texts by contrasting samples, which can improve the quality of latent representation and the alignment between audio and texts, while trained with limited data. Experiments are performed on the Clotho dataset to show the effectiveness of our proposed approach.