Wearable sensor based human activity recognition is a challenging problem due to difficulty in modeling spatial and temporal dependencies of sensor signals. Recognition models in closed-set assumption are forced to yield members of known activity classes as prediction. However, activity recognition models can encounter an unseen activity due to body-worn sensor malfunction or disability of the subject performing the activities. This problem can be addressed through modeling solution according to the assumption of open-set recognition. Hence, the proposed self attention based approach combines data hierarchically from different sensor placements across time to classify closed-set activities and it obtains notable performance improvement over state-of-the-art models on five publicly available datasets. The decoder in this autoencoder architecture incorporates self-attention based feature representations from encoder to detect unseen activity classes in open-set recognition setting. Furthermore, attention maps generated by the hierarchical model demonstrate explainable selection of features in activity recognition. We conduct extensive leave one subject out validation experiments that indicate significantly improved robustness to noise and subject specific variability in body-worn sensor signals. The source code is available at: github.com/saif-mahmud/hierarchical-attention-HAR
Relation extraction is a type of information extraction task that recognizes semantic relationships between entities in a sentence. Many previous studies have focused on extracting only one semantic relation between two entities in a single sentence. However, multiple entities in a sentence are associated through various relations. To address this issue, we propose a relation extraction model based on a dual pointer network with a multi-head attention mechanism. The proposed model finds n-to-1 subject-object relations using a forward object decoder. Then, it finds 1-to-n subject-object relations using a backward subject decoder. Our experiments confirmed that the proposed model outperformed previous models, with an F1-score of 80.8% for the ACE-2005 corpus and an F1-score of 78.3% for the NYT corpus.
With sequentially stacked self-attention, (optional) encoder-decoder attention, and feed-forward layers, Transformer achieves big success in natural language processing (NLP), and many variants have been proposed. Currently, almost all these models assume that the layer order is fixed and kept the same across data samples. We observe that different data samples actually favor different orders of the layers. Based on this observation, in this work, we break the assumption of the fixed layer order in the Transformer and introduce instance-wise layer reordering into the model structure. Our Instance-wise Ordered Transformer (IOT) can model variant functions by reordered layers, which enables each sample to select the better one to improve the model performance under the constraint of almost the same number of parameters. To achieve this, we introduce a light predictor with negligible parameter and inference cost to decide the most capable and favorable layer order for any input sequence. Experiments on 3 tasks (neural machine translation, abstractive summarization, and code generation) and 9 datasets demonstrate consistent improvements of our method. We further show that our method can also be applied to other architectures beyond Transformer. Our code is released at Github.
In this paper, we study the tradeoffs between complexity and reliability for decoding large linear block codes. We show that using artificial neural networks to predict the required order of an ordered statistics based decoder helps in reducing the average complexity and hence the latency of the decoder. We numerically validate the approach through Monte Carlo simulations.
Accurate and fast assessment of resection margins is an essential part of a dermatopathologist's clinical routine. In this work, we successfully develop a deep learning method to assist the pathologists by marking critical regions that have a high probability of exhibiting pathological features in Whole Slide Images (WSI). We focus on detecting Basal Cell Carcinoma (BCC) through semantic segmentation using several models based on the UNet architecture. The study includes 650 WSI with 3443 tissue sections in total. Two clinical dermatopathologists annotated the data, marking tumor tissues' exact location on 100 WSI. The rest of the data, with ground-truth section-wise labels, is used to further validate and test the models. We analyze two different encoders for the first part of the UNet network and two additional training strategies: a) deep supervision, b) linear combination of decoder outputs, and obtain some interpretations about what the network's decoder does in each case. The best model achieves over 96%, accuracy, sensitivity, and specificity on the test set.
The sensibility and sensitivity of the environment play a decisive role in the safe and secure operation of autonomous vehicles. This perception of the surrounding is way similar to human visual representation. The human's brain perceives the environment by utilizing different sensory channels and develop a view-invariant representation model. Keeping in this context, different exteroceptive sensors are deployed on the autonomous vehicle for perceiving the environment. The most common exteroceptive sensors are camera, Lidar and radar for autonomous vehicle's perception. Despite being these sensors have illustrated their benefit in the visible spectrum domain yet in the adverse weather conditions, for instance, at night, they have limited operation capability, which may lead to fatal accidents. In this work, we explore thermal object detection to model a view-invariant model representation by employing the self-supervised contrastive learning approach. For this purpose, we have proposed a deep neural network Self Supervised Thermal Network (SSTN) for learning the feature embedding to maximize the information between visible and infrared spectrum domain by contrastive learning, and later employing these learned feature representation for the thermal object detection using multi-scale encoder-decoder transformer network. The proposed method is extensively evaluated on the two publicly available datasets: the FLIR-ADAS dataset and the KAIST Multi-Spectral dataset. The experimental results illustrate the efficacy of the proposed method.
We present a neural optimization model trained with reinforcement learning to solve the coordinate ordering problem for sets of star glyphs. Given a set of star glyphs associated to multiple class labels, we propose to use shape context descriptors to measure the perceptual distance between pairs of glyphs, and use the derived silhouette coefficient to measure the perception of class separability within the entire set. To find the optimal coordinate order for the given set, we train a neural network using reinforcement learning to reward orderings with high silhouette coefficients. The network consists of an encoder and a decoder with an attention mechanism. The encoder employs a recurrent neural network (RNN) to encode input shape and class information, while the decoder together with the attention mechanism employs another RNN to output a sequence with the new coordinate order. In addition, we introduce a neural network to efficiently estimate the similarity between shape context descriptors, which allows to speed up the computation of silhouette coefficients and thus the training of the axis ordering network. Two user studies demonstrate that the orders provided by our method are preferred by users for perceiving class separation. We tested our model on different settings to show its robustness and generalization abilities and demonstrate that it allows to order input sets with unseen data size, data dimension, or number of classes. We also demonstrate that our model can be adapted to coordinate ordering of other types of plots such as RadViz by replacing the proposed shape-aware silhouette coefficient with the corresponding quality metric to guide network training.
Synthetic aperture imaging (SAI) is able to achieve the see through effect by blurring out the off-focus foreground occlusions and reconstructing the in-focus occluded targets from multi-view images. However, very dense occlusions and extreme lighting conditions may bring significant disturbances to the SAI based on conventional frame-based cameras, leading to performance degeneration. To address these problems, we propose a novel SAI system based on the event camera which can produce asynchronous events with extremely low latency and high dynamic range. Thus, it can eliminate the interference of dense occlusions by measuring with almost continuous views, and simultaneously tackle the over/under exposure problems. To reconstruct the occluded targets, we propose a hybrid encoder-decoder network composed of spiking neural networks (SNNs) and convolutional neural networks (CNNs). In the hybrid network, the spatio-temporal information of the collected events is first encoded by SNN layers, and then transformed to the visual image of the occluded targets by a style-transfer CNN decoder. Through experiments, the proposed method shows remarkable performance in dealing with very dense occlusions and extreme lighting conditions, and high quality visual images can be reconstructed using pure event data.
View synthesis is usually done by an autoencoder, in which the encoder maps a source view image into a latent content code, and the decoder transforms it into a target view image according to the condition. However, the source contents are often not well kept in this setting, which leads to unnecessary changes during the view translation. Although adding skipped connections, like Unet, alleviates the problem, but it often causes the failure on the view conformity. This paper proposes a new architecture by performing the source-to-target deformation in an iterative way. Instead of simply incorporating the features from multiple layers of the encoder, we design soft and hard deformation modules, which warp the encoder features to the target view at different resolutions, and give results to the decoder to complement the details. Particularly, the current warping flow is not only used to align the feature of the same resolution, but also as an approximation to coarsely deform the high resolution feature. Then the residual flow is estimated and applied in the high resolution, so that the deformation is built up in the coarse-to-fine fashion. To better constrain the model, we synthesize a rough target view image based on the intermediate flows and their warped features. The extensive ablation studies and the final results on two different data sets show the effectiveness of the proposed model.
General object grasping is an important yet unsolved problem in the field of robotics. Most of the current methods either generate grasp poses with few DoF that fail to cover most of the success grasps, or only take the unstable depth image or point cloud as input which may lead to poor results in some cases. In this paper, we propose RGBD-Grasp, a pipeline that solves this problem by decoupling 7-DoF grasp detection into two sub-tasks where RGB and depth information are processed separately. In the first stage, an encoder-decoder like convolutional neural network Angle-View Net(AVN) is proposed to predict the SO(3) orientation of the gripper at every location of the image. Consequently, a Fast Analytic Searching(FAS) module calculates the opening width and the distance of the gripper to the grasp point. By decoupling the grasp detection problem and introducing the stable RGB modality, our pipeline alleviates the requirement for the high-quality depth image and is robust to depth sensor noise. We achieve state-of-the-art results on GraspNet-1Billion dataset compared with several baselines. Real robot experiments on a UR5 robot with an Intel Realsense camera and a Robotiq two-finger gripper show high success rates for both single object scenes and cluttered scenes. Our code and trained model will be made publicly available.
We propose an efficient neural network for RAW image denoising. Although neural network-based denoising has been extensively studied for image restoration, little attention has been given to efficient denoising for compute limited and power sensitive devices, such as smartphones and smartwatches. In this paper, we present a novel architecture and a suite of training techniques for high quality denoising in mobile devices. Our work is distinguished by three main contributions. (1) Feature-Align layer that modulates the activations of an encoder-decoder architecture with the input noisy images. The auto modulation layer enforces attention to spatially varying noise that tend to be "washed away" by successive application of convolutions and non-linearity. (2) A novel Feature Matching Loss that allows knowledge distillation from large denoising networks in the form of a perceptual content loss. (3) Empirical analysis of our efficient model trained to specialize on different noise subranges. This opens additional avenue for model size reduction by sacrificing memory for compute. Extensive experimental validation shows that our efficient model produces high quality denoising results that compete with state-of-the-art large networks, while using significantly fewer parameters and MACs. On the Darmstadt Noise Dataset benchmark, we achieve a PSNR of 48.28dB, while using 263 times fewer MACs, and 17.6 times fewer parameters than the state-of-the-art network, which achieves 49.12dB.
The Japan Meteorological Agency operates gridded temperature guidance to predict two-dimensional snowfall amounts and precipitation types, e.g., rain and snow, because surface temperature is one of the key elements to predict them. Operational temperature guidance is based on the Kalman filter, which uses temperature observation and numerical weather prediction (NWP) outputs only around observation sites. Correcting a temperature field when NWP models incorrectly predict a front's location or when observed temperatures are extremely cold or hot has been challenging. In this study, an encoder-decoder-based convolutional neural network has been proposed to predict gridded temperatures at the surface around the Kanto region in Japan. Verification results showed that the proposed model greatly improves the operational guidance and can correct NWP model biases, such as a positional error of fronts and extreme temperatures.
Advances in deep learning have led to promising progress in inferring graphics programs by de-rendering computer-generated images. However, current methods do not explore which decoding methods lead to better inductive bias for inferring graphics programs. In our work, we first explore the effectiveness of LSTM-RNN versus Transformer networks as decoders for order-independent graphics programs. Since these are sequence models, we must choose an ordering of the objects in the graphics programs for likelihood training. We found that the LSTM performance was highly sensitive to the sequence ordering (random order vs. pattern-based order), while Transformer performance was roughly independent of the sequence ordering. Further, we present a policy gradient based reinforcement learning approach for better inductive bias in the decoder via multiple diverse rewards based both on the graphics program specification and the rendered image. We also explore the combination of these complementary rewards. We achieve state-of-the-art results on two graphics program generation datasets.
As in other areas of medical image analysis, e.g. semantic segmentation, deep learning is currently driving the development of new approaches for image registration. Multi-scale encoder-decoder network architectures achieve state-of-the-art accuracy on tasks such as intra-patient alignment of abdominal CT or brain MRI registration, especially when additional supervision, such as anatomical labels, is available. The success of these methods relies to a large extent on the outstanding ability of deep CNNs to extract descriptive visual features from the input images. In contrast to conventional methods, the explicit inclusion of geometric information plays only a minor role, if at all. In this work we take a look at an exactly opposite approach by investigating a deep learning framework for registration based solely on geometric features and optimisation. We combine graph convolutions with loopy belief message passing to enable highly accurate 3D point cloud registration. Our experimental validation is conducted on complex key-point graphs of inner lung structures, strongly outperforming dense encoder-decoder networks and other point set registration methods. Our code is publicly available at https://github.com/multimodallearning/deep-geo-reg.
Street scene change detection continues to capture researchers' interests in the computer vision community. It aims to identify the changed regions of the paired street-view images captured at different times. The state-of-the-art network based on the encoder-decoder architecture leverages the feature maps at the corresponding level between two channels to gain sufficient information of changes. Still, the efficiency of feature extraction, feature correlation calculation, even the whole network requires further improvement. This paper proposes the temporal attention and explores the impact of the dependency-scope size of temporal attention on the performance of change detection. In addition, based on the Temporal Attention Module (TAM), we introduce a more efficient and light-weight version - Dynamic Receptive Temporal Attention Module (DRTAM) and propose the Concurrent Horizontal and Vertical Attention (CHVA) to improve the accuracy of the network on specific challenging entities. On street scene datasets `GSV', `TSUNAMI' and `VL-CMU-CD', our approach gains excellent performance, establishing new state-of-the-art scores without bells and whistles, while maintaining high efficiency applicable in autonomous vehicles.
Scene understanding based on LiDAR point cloud is an essential task for autonomous cars to drive safely, which often employs spherical projection to map 3D point cloud into multi-channel 2D images for semantic segmentation. Most existing methods simply stack different point attributes/modalities (e.g. coordinates, intensity, depth, etc.) as image channels to increase information capacity, but ignore distinct characteristics of point attributes in different image channels. We design FPS-Net, a convolutional fusion network that exploits the uniqueness and discrepancy among the projected image channels for optimal point cloud segmentation. FPS-Net adopts an encoder-decoder structure. Instead of simply stacking multiple channel images as a single input, we group them into different modalities to first learn modality-specific features separately and then map the learned features into a common high-dimensional feature space for pixel-level fusion and learning. Specifically, we design a residual dense block with multiple receptive fields as a building block in the encoder which preserves detailed information in each modality and learns hierarchical modality-specific and fused features effectively. In the FPS-Net decoder, we use a recurrent convolution block likewise to hierarchically decode fused features into output space for pixel-level classification. Extensive experiments conducted on two widely adopted point cloud datasets show that FPS-Net achieves superior semantic segmentation as compared with state-of-the-art projection-based methods. In addition, the proposed modality fusion idea is compatible with typical projection-based methods and can be incorporated into them with consistent performance improvements.
This article describes an efficient training method for online streaming attention-based encoder-decoder (AED) automatic speech recognition (ASR) systems. AED models have achieved competitive performance in offline scenarios by jointly optimizing all components. They have recently been extended to an online streaming framework via models such as monotonic chunkwise attention (MoChA). However, the elaborate attention calculation process is not robust for long-form speech utterances. Moreover, the sequence-level training objective and time-restricted streaming encoder cause a nonnegligible delay in token emission during inference. To address these problems, we propose CTC synchronous training (CTC-ST), in which CTC alignments are leveraged as a reference for token boundaries to enable a MoChA model to learn optimal monotonic input-output alignments. We formulate a purely end-to-end training objective to synchronize the boundaries of MoChA to those of CTC. The CTC model shares an encoder with the MoChA model to enhance the encoder representation. Moreover, the proposed method provides alignment information learned in the CTC branch to the attention-based decoder. Therefore, CTC-ST can be regarded as self-distillation of alignment knowledge from CTC to MoChA. Experimental evaluations on a variety of benchmark datasets show that the proposed method significantly reduces recognition errors and emission latency simultaneously. The robustness to long-form and noisy speech is also demonstrated. We compare CTC-ST with several methods that distill alignment knowledge from a hybrid ASR system and show that the CTC-ST can achieve a comparable tradeoff of accuracy and latency without relying on external alignment information. The best MoChA system shows recognition accuracy comparable to that of RNN-transducer (RNN-T) while achieving lower emission latency.
Despite tremendous efforts, it is very challenging to generate a robust model to assist in the accurate quantification assessment of COVID-19 on chest CT images. Due to the nature of blurred boundaries, the supervised segmentation methods usually suffer from annotation biases. To support unbiased lesion localisation and to minimise the labeling costs, we propose a data-driven framework supervised by only image-level labels. The framework can explicitly separate potential lesions from original images, with the help of a generative adversarial network and a lesion-specific decoder. Experiments on two COVID-19 datasets demonstrate the effectiveness of the proposed framework and its superior performance to several existing methods.
Considering the scarcity of medical data, most datasets in medical image analysis are an order of magnitude smaller than those of natural images. However, most Network Architecture Search (NAS) approaches in medical images focused on specific datasets and did not take into account the generalization ability of the learned architectures on unseen datasets as well as different domains. In this paper, we address this point by proposing to search for generalizable U-shape architectures on a composited dataset that mixes medical images from multiple segmentation tasks and domains creatively, which is named MixSearch. Specifically, we propose a novel approach to mix multiple small-scale datasets from multiple domains and segmentation tasks to produce a large-scale dataset. Then, a novel weaved encoder-decoder structure is designed to search for a generalized segmentation network in both cell-level and network-level. The network produced by the proposed MixSearch framework achieves state-of-the-art results compared with advanced encoder-decoder networks across various datasets.
Recently, some researches are devoted to the topic of end-to-end learning a physical layer secure communication system based on autoencoder under Gaussian wiretap channel. However, in those works, the reliability and security of the encoder model were learned through necessary decoding outputs of not only legitimate receiver but also the eavesdropper. In fact, the assumption of known eavesdropper's decoder or its output is not practical. To address this issue, in this paper we propose a dual mutual information neural estimation (MINE) based neural secure communications model. The security constraints of this method is constructed only with the input and output signal samples of the legal and eavesdropper channels and benefit that training the encoder is completely independent of the decoder. Moreover, since the design of secure coding does not rely on the eavesdropper's decoding results, the security performance would not be affected by the eavesdropper's decoding means. Numerical results show that the performance of our model is guaranteed whether the eavesdropper learns the decoder himself or uses the legal decoder.