We tackle the problem of place recognition from point cloud data and introduce a self-attention and orientation encoding network (SOE-Net) that fully explores the relationship between points and incorporates long-range context into point-wise local descriptors. Local information of each point from eight orientations is captured in a PointOE module, whereas long-range feature dependencies among local descriptors are captured with a self-attention unit. Moreover, we propose a novel loss function called Hard Positive Hard Negative quadruplet loss (HPHN quadruplet), that achieves better performance than the commonly used metric learning loss. Experiments on various benchmark datasets demonstrate superior performance of the proposed network over the current state-of-the-art approaches. Our code is released publicly at https://github.com/Yan-Xia/SOE-Net.
Tsinghua University（清华大学）；University of Maryland, College Park（马里兰大学帕克分校）
Learning discriminative feature directly on point clouds is still challenging in the understanding of 3D shapes. Recent methods usually partition point clouds into local region sets, and then extract the local region features with fixed-size CNN or MLP, and finally aggregate all individual local features into a global feature using simple max pooling. However, due to the irregularity and sparsity in sampled point clouds, it is hard to encode the fine-grained geometry of local regions and their spatial relationships when only using the fixed-size filters and individual local feature integration…
Korea Advanced Institute of Science and Technology（韩国科学技术院）
In this paper, we propose a self-supervised single-view pixel-level accurate depth estimation network, called PLADE-Net. The PLADE-Net is the first work that shows unprecedented accuracy levels, exceeding 95\% in terms of the $δ^1$ metric on the challenging KITTI dataset. Our PLADE-Net is based on a new network architecture with neural positional encoding and a novel loss function that borrows from the closed-form solution of the matting Laplacian to learn pixel-level accurate depth estimation from stereo images. Neural positional encoding allows our PLADE-Net to obtain more consistent depth e…
We present a new permutation-invariant network for 3D point cloud processing. Our network is composed of a recurrent set encoder and a convolutional feature aggregator. Given an unordered point set, the encoder firstly partitions its ambient space into parallel beams. Points within each beam are then modeled as a sequence and encoded into subregional geometric features by a shared recurrent neural network (RNN). The spatial layout of the beams is regular, and this allows the beam features to be further fed into an efficient 2D convolutional neural network (CNN) for hierarchical feature aggrega…
Image classification is an important task in various machine learning applications. In recent years, a number of classification methods based on quantum machine learning and different quantum image encoding techniques have been proposed. In this paper, we study the effect of three different quantum image encoding approaches on the performance of a convolution-inspired hybrid quantum-classical image classification algorithm called quanvolutional neural network (QNN). We furthermore examine the effect of variational - i.e. trainable - quantum circuits on the classification results. Our experimen…
Automatic segmentation of fine-grained brain structures remains a challenging task. Current segmentation methods mainly utilize 2D and 3D deep neural networks. The 2D networks take image slices as input to produce coarse segmentation in less processing time, whereas the 3D networks take the whole image volumes to generated fine-detailed segmentation with more computational burden. In order to obtain accurate fine-grained segmentation efficiently, in this paper, we propose an end-to-end Feature-Fused Context-Encoding Network for brain structure segmentation from MR (magnetic resonance) images. …
This paper introduces partitioning an inference task of a deep neural network between an edge and a host platform in the IoT environment. We present a DNN as an encoding pipeline, and propose to transmit the output feature space of an intermediate layer to the host. The lossless or lossy encoding of the feature space is proposed to enhance the maximum input rate supported by the edge platform and/or reduce the energy of the edge platform. Simulation results show that partitioning a DNN at the end of convolutional (feature extraction) layers coupled with feature space encoding enables significa…
In this work, we present a novel approach to learning an encoding of visual features into graph neural networks with the application on road network data. We propose an architecture that combines state-of-the-art vision backbone networks with graph neural networks. More specifically, we perform a road type classification task on an Open Street Map road network through encoding of satellite imagery using various ResNet architectures. Our architecture further enables fine-tuning and a transfer-learning approach is evaluated by pretraining on the NWPU-RESISC45 image classification dataset for rem…
Event camera is an asynchronous, high frequency vision sensor with low power consumption, which is suitable for human action recognition task. It is vital to encode the spatial-temporal information of event data properly and use standard computer vision tool to learn from the data. In this work, we propose a timestamp image encoding 2D network, which takes the encoded spatial-temporal images of the event data as input and output the action label. Experiment results show that our method can achieve the same level of performance as those RGB-based benchmarks on real world action recognition, and…
The training of deep neural networks (DNNs) requires intensive resources both for computation and for storage performance. Thus, DNNs cannot be efficiently applied to mobile phones and embedded devices, which seriously limits their applicability in industry applications. To address this issue, we propose a novel encoding scheme of using {-1,+1} to decompose quantized neural networks (QNNs) into multi-branch binary networks, which can be efficiently implemented by bitwise operations (xnor and bitcount) to achieve model compression, computational acceleration and resource saving. Based on our me…
We propose a Deep Texture Encoding Network (Deep-TEN) with a novel Encoding Layer integrated on top of convolutional layers, which ports the entire dictionary learning and encoding pipeline into a single model. Current methods build from distinct components, using standard encoders with separate off-the-shelf features such as SIFT descriptors or pre-trained CNN features for material recognition. Our new approach provides an end-to-end learning framework, where the inherent visual vocabularies are learned directly from the loss function. The features, dictionaries and the encoding representatio…
The training of deep neural networks (DNNs) always requires intensive resources for both computation and data storage. Thus, DNNs cannot be efficiently applied to mobile phones and embedded devices, which severely limits their applicability in industrial applications. To address this issue, we propose a novel encoding scheme using {-1, +1} to decompose quantized neural networks (QNNs) into multi-branch binary networks, which can be efficiently implemented by bitwise operations (i.e., xnor and bitcount) to achieve model compression, computational acceleration, and resource saving. By using our …
Although current deep learning methods have achieved impressive results for semantic segmentation, they incur high computational costs and have a huge number of parameters. For real-time applications, inference speed and memory usage are two important factors. To address the challenge, we propose a lightweight feature pyramid encoding network (FPENet) to make a good trade-off between accuracy and speed. Specifically, we use a feature pyramid encoding block to encode multi-scale contextual features with depthwise dilated convolutions in all stages of the encoder. A mutual embedding upsample mod…
In this paper, we propose a multi-level texture encoding and representation network (MuLTER) for texture-related applications. Based on a multi-level pooling architecture, the MuLTER network simultaneously leverages low- and high-level features to maintain both texture details and spatial information. Such a pooling architecture involves few extra parameters and keeps feature dimensions fixed despite of the changes of image sizes. In comparison with state-of-the-art texture descriptors, the MuLTER network yields higher recognition accuracy on typical texture datasets such as MINC-2500 and GTOS…
Interdisciplinary Centre for Security, Reliability and Trust (SnT)（安全、可靠性与信任跨学科中心（SnT））；University of Luxembourg（卢森堡大学）
This paper extends the Spatial-Temporal Graph Convolutional Network (ST-GCN) for skeleton-based action recognition by introducing two novel modules, namely, the Graph Vertex Feature Encoder (GVFE) and the Dilated Hierarchical Temporal Convolutional Network (DH-TCN). On the one hand, the GVFE module learns appropriate vertex features for action recognition by encoding raw skeleton data into a new feature space. On the other hand, the DH-TCN module is capable of capturing both short-term and long-term temporal dependencies using a hierarchical dilated convolutional network. Experiments have been…
Most approaches for semantic segmentation use only information from color cameras to parse the scenes, yet recent advancements show that using depth data allows to further improve performances. In this work, we focus on transformer-based deep learning architectures, that have achieved state-of-the-art performances on the segmentation task, and we propose to employ depth information by embedding it in the positional encoding. Effectively, we extend the network to multimodal data without adding any parameters and in a natural way that makes use of the strength of transformers' self-attention mod…
The CNN-encoding of features from entire videos for the representation of human actions has rarely been addressed. Instead, CNN work has focused on approaches to fuse spatial and temporal networks, but these were typically limited to processing shorter sequences. We present a new video representation, called temporal linear encoding (TLE) and embedded inside of CNNs as a new layer, which captures the appearance and motion throughout entire videos. It encodes this aggregated information into a robust video feature representation, via end-to-end learning. Advantages of TLEs are: (a) they encode …
Deep hashing has been widely applied to large-scale image retrieval tasks owing to efficient computation and low storage cost by encoding high-dimensional image data into binary codes. Since binary codes do not contain as much information as float features, the essence of binary encoding is preserving the main context to guarantee retrieval quality. However, the existing hashing methods have great limitations on suppressing redundant background information and accurately encoding from Euclidean space to Hamming space by a simple sign function. In order to solve these problems, a Cross-Scale Co…
It is a challenging task to deploy computationally and memory intensive State-of-the-art deep neural networks (DNNs) on embedded systems with limited hardware resources and power budgets. Recently developed techniques like Deep Compression make it possible to fit large DNNs, such as AlexNet and VGGNet, fully in on-chip SRAM. But sparse networks compressed using existing encoding formats, like CSR or CSC, complex the computation at runtime due to their irregular memory access characteristics. In [1], we introduce a computation dataflow, stacked filters stationary dataflow (SFS), and a correspon…
Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）
Many of the leading approaches for video understanding are data-hungry and time-consuming, failing to capture the gist of spatial-temporal evolution in an efficient manner. The latest research shows that CNN network can reason about static relation of entities in images. To further exploit its capacity in dynamic evolution reasoning, we introduce a novel network module called DenseImage Network(DIN) with two main contributions. 1) A novel compact representation of video which distills its significant spatial-temporal evolution into a matrix called DenseImage, primed for efficient video encodin…
In this paper, we propose Orthogonal Generative Adversarial Networks (O-GANs). We decompose the network of discriminator orthogonally and add an extra loss into the objective of common GANs, which can enforce discriminator become an effective encoder. The same extra loss can be embedded into any kind of GANs and there is almost no increase in computation. Furthermore, we discuss the principle of our method, which is relative to the fully-exploiting of the remaining degrees of freedom of discriminator. As we know, our solution is the simplest approach to train a generative adversarial network w…
Revisiting Direct Encoding: Learnable Temporal Dynamics for Static Image Spiking Neural Networks
School of Computer and Information Engineering, Henan University（河南大学计算机与信息工程学院）；Henan Key Laboratory of Big Data Analysis and Processing, Henan University（河南大学大数据分析与处理重点实验室）
This brief paper reports the shortcoming of a variant of convolutional neural network whose components are developed based on the pattern theory framework.
Megvii Inc.（旷视科技有限公司）；The Hong Kong University of Science and Technology（香港科技大学）；Beihang University（北京航空航天大学）；University of Michigan, Ann Arbor（密歇根大学安娜堡分校）；Harbin Institute of Technology（哈尔滨工业大学）；Tsinghua University（清华大学）
This technical report presents an effective method for motion prediction in autonomous driving. We develop a Transformer-based method for input encoding and trajectory prediction. Besides, we propose the Temporal Flow Header to enhance the trajectory encoding. In the end, an efficient K-means ensemble method is used. Using our Transformer network and ensemble method, we win the first place of Argoverse 2 Motion Forecasting Challenge with the state-of-the-art brier-minFDE score of 1.90.
It is shown analytically how a neural network can be used optimally to encode input data that is derived from a toroidal manifold. The case of a 2-layer network is considered, where the output is assumed to be a set of discrete neural firing events. The network objective function measures the average Euclidean error that occurs when the network attempts to reconstruct its input from its output. This optimisation problem is solved analytically for a toroidal input manifold, and two types of solution are obtained: a joint encoder in which the network acts as a soft vector quantiser, and a factor…
Segmentation of brain structures from magnetic resonance (MR) scans plays an important role in the quantification of brain morphology. Since 3D deep learning models suffer from high computational cost, 2D deep learning methods are favored for their computational efficiency. However, existing 2D deep learning methods are not equipped to effectively capture 3D spatial contextual information that is needed to achieve accurate brain structure segmentation. In order to overcome this limitation, we develop an Anatomical Context-Encoding Network (ACEnet) to incorporate 3D spatial and anatomical conte…
Current state-of-the-art methods of image classification using convolutional neural networks are often constrained by both latency and power consumption. This places a limit on the devices, particularly low-power edge devices, that can employ these methods. Spiking neural networks (SNNs) are considered to be the third generation of artificial neural networks which aim to address these latency and power constraints by taking inspiration from biological neuronal communication processes. Before data such as images can be input into an SNN, however, they must be first encoded into spike trains. He…
Deep neural networks are used for a wide range of regression problems. However, there exists a significant gap in accuracy between specialized approaches and generic direct regression in which a network is trained by minimizing the squared or absolute error of output labels. Prior work has shown that solving a regression problem with a set of binary classifiers can improve accuracy by utilizing well-studied binary classification algorithms. We introduce binary-encoded labels (BEL), which generalizes the application of binary classification to regression by providing a framework for considering…
Target encoding is an effective technique to deliver better performance for conventional machine learning methods, and recently, for deep neural networks as well. However, the existing target encoding approaches require significant increase in the learning capacity, thus demand higher computation power and more training data. In this paper, we present a novel and efficient target encoding scheme, MUTE to improve both generalizability and robustness of a target model by understanding the inter-class characteristics of a target dataset. By extracting the confusion level between the target classe…
Nanjing University of Science and Technology（南京理工大学）
The prevalence of digital sensors, such as digital cameras and mobile phones, simplifies the acquisition of photos. Digital sensors, however, suffer from producing Moire when photographing objects having complex textures, which deteriorates the quality of photos. Moire spreads across various frequency bands of images and is a dynamic texture with varying colors and shapes, which pose two main challenges in demoireing---an important task in image restoration. In this paper, towards addressing the first challenge, we design a multi-scale network to process images at different spatial resolutions…
In this paper, we propose a bottleneck supervised (BS) U-Net model for liver and tumor segmentation. Our main contributions are: first, we propose a variation of the original U-Net that incorporates dense modules, inception modules and dilated convolution in the encoding path; second, we propose a bottleneck supervised (BS) U-Net that contains an encoding U-Net and a segmentation U-Net. To train the BS U-Net, the encoding U-Net is first trained to get encodings of the label maps that contain the anatomical information (shape and location). Subsequently, this information is used to guide the tr…
We hypothesize that anatomical priors can be viable mediums to infuse domain-specific clinical knowledge into state-of-the-art convolutional neural networks (CNN) based on the U-Net architecture. We introduce a probabilistic population prior which captures the spatial prevalence and zonal distinction of clinically significant prostate cancer (csPCa), in order to improve its computer-aided detection (CAD) in bi-parametric MR imaging (bpMRI). To evaluate performance, we train 3D adaptations of the U-Net, U-SEResNet, UNet++ and Attention U-Net using 800 institutional training-validation scans, pa…
National Digital Switching System Engineering and Technological Research Center（国家数字交换系统工程技术研究中心）；University of Minnesota at Twin Cities（明尼苏达大学双城分校）
Background: Building visual encoding models to accurately predict visual responses is a central challenge for current vision-based brain-machine interface techniques. To achieve high prediction accuracy on neural signals, visual encoding models should include precise visual features and appropriate prediction algorithms. Most existing visual encoding models employ hand-craft visual features (e.g., Gabor wavelets or semantic labels) or data-driven features (e.g., features extracted from deep neural networks (DNN)). They also assume a linear mapping between feature representation to brain activi…
School of Information and Electronics & Advanced Research Institute of Multidisciplinary Science, Beijing Institute of Technology（北京理工大学信息与电子学院及多学科科学前沿研究研究院）
Using single-pixel detection, the end-to-end neural network that jointly optimizes both encoding and decoding enables high-precision imaging and high-level semantic sensing. However, for varied sampling rates, the large-scale network requires retraining that is laboursome and computation-consuming. In this letter, we report a weighted optimization technique for dynamic rate-adaptive single-pixel imaging and sensing, which only needs to train the network for one time that is available for any sampling rates. Specifically, we introduce a novel weighting scheme in the encoding process to characte…
Insight Centre for Data Analytics（洞察数据分析中心）；Dublin City University（都柏林城市大学）
Current deep learning based video classification architectures are typically trained end-to-end on large volumes of data and require extensive computational resources. This paper aims to exploit audio-visual information in video classification with a 1 frame per second sampling rate. We propose Temporal Bilinear Encoding Networks (TBEN) for encoding both audio and visual long range temporal information using bilinear pooling and demonstrate bilinear pooling is better than average pooling on the temporal dimension for videos with low sampling rate. We also embed the label hierarchy in TBEN to f…
Deep regression networks are widely used to tackle the problem of predicting a continuous value for a given input. Task-specialized approaches for training regression networks have shown significant improvement over generic approaches, such as direct regression. More recently, a generic approach based on regression by binary classification using binary-encoded labels has shown significant improvement over direct regression. The space of label encodings for regression is large. Lacking heretofore have been automated approaches to find a good label encoding for a given application. This paper in…
Indian Institute of Technology Kharagpur（印度理工学院卡拉格普尔分校）
Removing undesired reflections from a photo taken in front of glass is of great importance for enhancing visual computing systems' efficiency. Previous learning-based approaches have produced visually plausible results for some reflections type, however, failed to generalize against other reflection types. There is a dearth of literature for efficient methods concerning single image reflection removal, which can generalize well in large-scale reflection types. In this study, we proposed an iterative gradient encoding network for single image reflection removal. Next, to further supervise the n…
Practical insights on the effect of different encodings, ansätze and measurements in quantum and hybrid convolutional neural networks
Quantum Lab, CTIC Centro Tecnol\'ogico, Parque Cient\'ifico Tecnol\'ogico de Gij\'on, Asturias, Spain；Eurecat, Centre Tecnol\`ogic de Catalunya, Multimedia Technologies, Barcelona, Spain；Centre de Visi\'o per Computador (CVC), Barcelona, Spain.；Fsas International Quantum Center (Fujitsu), Santiago de Compostela, Spain.
There has been significant recent interest towards achieving highly efficient deep neural network architectures. A promising paradigm for achieving this is the concept of evolutionary deep intelligence, which attempts to mimic biological evolution processes to synthesize highly-efficient deep neural networks over successive generations. An important aspect of evolutionary deep intelligence is the genetic encoding scheme used to mimic heredity, which can have a significant impact on the quality of offspring deep neural networks. Motivated by the neurobiological phenomenon of synaptic clustering…
The brain is known to be a highly complex, asynchronous dynamical system that is highly tailored to encode temporal information. However, recent deep learning approaches to not take advantage of this temporal coding. Spiking Neural Networks (SNNs) can be trained using biologically-realistic learning mechanisms, and can have neuronal activation rules that are biologically relevant. This type of network is also structured fundamentally around accepting temporal information through a time-decaying voltage update, a kind of input that current rate-encoding networks have difficulty with. Here we sh…
Motivated by an important insight from neural science, we propose a new framework for understanding the success of the recently proposed "maxout" networks. The framework is based on encoding information on sparse pathways and recognizing the correct pathway at inference time. Elaborating further on this insight, we propose a novel deep network architecture, called "channel-out" network, which takes a much better advantage of sparse pathway encoding. In channel-out networks, pathways are not only formed a posteriori, but they are also actively selected according to the inference outputs from th…
Academy of information systems engineering, PLA strategy support force information engineering university（中国人民解放军战略支援部队信息工程大学信息系统工程学院）
On basis of functional magnetic resonance imaging (fMRI), researchers are devoted to designing visual encoding models to predict the neuron activity of human in response to presented image stimuli and analyze inner mechanism of human visual cortices. Deep network structure composed of hierarchical processing layers forms deep network models by learning features of data on specific task through big dataset. Deep network models have powerful and hierarchical representation of data, and have brought about breakthroughs for visual encoding, while revealing hierarchical structural similarity with t…
The landscape of city-wide mobility behaviour has altered significantly over the past 18 months. The ability to make accurate and reliable predictions on such behaviour has likewise changed drastically with COVID-19 measures impacting how populations across the world interact with the different facets of mobility. This raises the question: "How does one use an abundance of pre-covid mobility data to make predictions on future behaviour in a present/post-covid environment?" This paper seeks to address this question by introducing an approach for traffic frame prediction using a lightweight Dual…
