Search

This paper introduces Grounding DINO 1.5, a suite of advanced open-set object detection models developed by IDEA Research, which aims to advance the "Edge" of open-set object detection. The suite encompasses two models: Grounding DINO 1.5 Pro, a high-performance model designed for stronger generalization capability across a wide range of scenarios, and Grounding DINO 1.5 Edge, an efficient model optimized for faster speed demanded in many applications requiring edge deployment. The Grounding DINO 1.5 Pro model advances its predecessor by scaling up the model architecture, integrating an enhanced vision backbone, and expanding the training dataset to over 20 million images with grounding annotations, thereby achieving a richer semantic understanding. The Grounding DINO 1.5 Edge model, while designed for efficiency with reduced feature scales, maintains robust detection capabilities by being trained on the same comprehensive dataset. Empirical results demonstrate the effectiveness of Grounding DINO 1.5, with the Grounding DINO 1.5 Pro model attaining a 54.3 AP on the COCO detection benchmark and a 55.7 AP on the LVIS-minival zero-shot transfer benchmark, setting new records for open-set object detection. Furthermore, the Grounding DINO 1.5 Edge model, when optimized with TensorRT, achieves a speed of 75.2 FPS while attaining a zero-shot performance of 36.2 AP on the LVIS-minival benchmark, making it more suitable for edge computing scenarios. Model examples and demos with API will be released at https://github.com/IDEA-Research/Grounding-DINO-1.5-API, Comment: homepage: https://deepdataspace.com/home

BGP is the de facto inter-domain routing protocol to ensure global connectivity of the Internet. However, various reasons, such as deliberate attacks or misconfigurations, could cause BGP routing anomalies. Traditional methods for BGP routing anomaly detection require significant manual investigation of routes by network operators. Although machine learning has been applied to automate the process, prior arts typically impose significant training overhead (such as large-scale data labeling and feature crafting), and only produce uninterpretable results. To address these limitations, this paper presents a routing anomaly detection system centering around a novel network representation learning model named BEAM. The core design of BEAM is to accurately learn the unique properties (defined as \emph{routing role}) of each Autonomous System (AS) in the Internet by incorporating BGP semantics. As a result, routing anomaly detection, given BEAM, is reduced to a matter of discovering unexpected routing role churns upon observing new route announcements. We implement a prototype of our routing anomaly detection system and extensively evaluate its performance. The experimental results, based on 18 real-world RouteViews datasets containing over 11 billion route announcement records, demonstrate that our system can detect all previously-confirmed routing anomalies, while only introducing at most five false alarms every 180 million route announcements. We also deploy our system at a large ISP to perform real-world detection for one month. During the course of deployment, our system detects 497 true anomalies in the wild with an average of only 1.65 false alarms per day., Comment: To be published in USENIX Security 2024

In machine learning (ML), efficient asset management, including ML models, datasets, algorithms, and tools, is vital for resource optimization, consistent performance, and a streamlined development lifecycle. This enables quicker iterations, adaptability, reduced development-to-deployment time, and reliable outputs. Despite existing research, a significant knowledge gap remains in operational challenges like model versioning, data traceability, and collaboration, which are crucial for the success of ML projects. Our study aims to address this gap by analyzing 15,065 posts from developer forums and platforms, employing a mixed-method approach to classify inquiries, extract challenges using BERTopic, and identify solutions through open card sorting and BERTopic clustering. We uncover 133 topics related to asset management challenges, grouped into 16 macro-topics, with software dependency, model deployment, and model training being the most discussed. We also find 79 solution topics, categorized under 18 macro-topics, highlighting software dependency, feature development, and file management as key solutions. This research underscores the need for further exploration of identified pain points and the importance of collaborative efforts across academia, industry, and the research community.

An intrinsic feature of disordered and out-of-equilibrium materials, such as glasses, is the dependence of their properties on their history. An important example is rheological memory, in which disordered solids obtain properties based on their mechanical history. Here, we employ x-ray photon correlation spectroscopy (XPCS) with \textit{in situ} rheometry to characterize memory formation in a nanocolloidal soft glass due to cyclic shear. During a cycle, particles undergo irreversible displacements composed of a combination of shear-induced diffusion and strain fields. The magnitudes of these displacements decrease with each cycle before reaching a steady state where the microstructure has become trained to achieve enhanced reversibility. The displacements resemble a random walk in which the directions in each cycle are independent of those in preceding cycles. Associated with these displacements is a gradual evolution in the amplidute of the residual stress after each cycle towards a steady state value. Memory of this training is revealed by measurements in which the amplitude of the shear is changed after steady state is reached. The magnitude of the particle displacements as well as the change in residual stress vary non-monotonically with the new strain amplitude, having minima near the training amplitude, thereby revealing both microscopic and macroscopic signatures of memory.

[Context]: Containerization ensures the resilience of distributed applications by Kubernetes. Helm is a package manager for Kubernetes applications. A Helm package, namely "Chart'', is a set of pre-configured resources that one could quickly deploy a complex application. However, Helm broadens the attack surface of the distributed applications. [Objective]: This study aims to investigate the prevalence of fixable vulnerabilities, the factors related to the vulnerabilities, and current mitigation strategies in Helm Charts. [Method]: We conduct a mixed-methods study on 11,035 Helm Charts affected by 10,982 fixable vulnerabilities. We analyze the complexity of Charts and compare the distribution of vulnerabilities between official and unofficial Charts. Subsequently, we investigate vulnerability mitigation strategies from the Chart-associated repositories by a grounded theory. [Results]: Our findings highlight that the complexity of a Chart correlates with the number of vulnerabilities, and the official Charts do not contain fewer vulnerabilities compared to unofficial Charts. The 10,982 fixable vulnerabilities are at a median of high severity and can be easily exploited. In addition, we identify 11 vulnerability mitigation strategies in three categories. Due to the complexity of Charts, maintainers are required to investigate where a vulnerability impacts and how to mitigate it. The use of automated strategies is low as automation has limited capability(e.g., a higher number of false positives) in such complex Charts. [Conclusion]: There exists need for automation tools that assist maintainers in mitigating vulnerabilities to reduce manual effort. In addition, Chart maintainers lack incentives to mitigate vulnerabilities, given a lack of guidelines for mitigation responsibilities. Adopting a shared responsibility model in the Helm ecosystem would increase its security.

Recently segment anything model (SAM) has shown powerful segmentation capability and has drawn great attention in computer vision fields. Massive following works have developed various applications based on the pretrained SAM and achieved impressive performance on downstream vision tasks. However, SAM consists of heavy architectures and requires massive computational capacity, which hinders the further application of SAM on computation constrained edge devices. To this end, in this paper we propose a framework to obtain a tiny segment anything model (TinySAM) while maintaining the strong zero-shot performance. We first propose a full-stage knowledge distillation method with hard prompt sampling and hard mask weighting strategy to distill a lightweight student model. We also adapt the post-training quantization to the promptable segmentation task and further reduce the computational cost. Moreover, a hierarchical segmenting everything strategy is proposed to accelerate the everything inference by $2\times$ with almost no performance degradation. With all these proposed methods, our TinySAM leads to orders of magnitude computational reduction and pushes the envelope for efficient segment anything task. Extensive experiments on various zero-shot transfer tasks demonstrate the significantly advantageous performance of our TinySAM against counterpart methods. Pre-trained models and codes are available at https://github.com/xinghaochen/TinySAM and https://gitee.com/mindspore/models/tree/master/research/cv/TinySAM.

Large Language Models (LLMs) have demonstrated exceptional capabilities across various natural language processing tasks. Yet, many of these advanced LLMs are tailored for broad, general-purpose applications. In this technical report, we introduce AcademicGPT, designed specifically to empower academic research. AcademicGPT is a continual training model derived from LLaMA2-70B. Our training corpus mainly consists of academic papers, thesis, content from some academic domain, high-quality Chinese data and others. While it may not be extensive in data scale, AcademicGPT marks our initial venture into a domain-specific GPT tailored for research area. We evaluate AcademicGPT on several established public benchmarks such as MMLU and CEval, as well as on some specialized academic benchmarks like PubMedQA, SCIEval, and our newly-created ComputerScienceQA, to demonstrate its ability from general knowledge ability, to Chinese ability, and to academic ability. Building upon AcademicGPT's foundation model, we also developed several applications catered to the academic area, including General Academic Question Answering, AI-assisted Paper Reading, Paper Review, and AI-assisted Title and Abstract Generation., Comment: Technical Report. arXiv admin note: text overlap with arXiv:2310.12081, arXiv:2310.10053 by other authors

Machine learning (ML) is promising in accurately detecting malicious flows in encrypted network traffic; however, it is challenging to collect a training dataset that contains a sufficient amount of encrypted malicious data with correct labels. When ML models are trained with low-quality training data, they suffer degraded performance. In this paper, we aim at addressing a real-world low-quality training dataset problem, namely, detecting encrypted malicious traffic generated by continuously evolving malware. We develop RAPIER that fully utilizes different distributions of normal and malicious traffic data in the feature space, where normal data is tightly distributed in a certain area and the malicious data is scattered over the entire feature space to augment training data for model training. RAPIER includes two pre-processing modules to convert traffic into feature vectors and correct label noises. We evaluate our system on two public datasets and one combined dataset. With 1000 samples and 45% noises from each dataset, our system achieves the F1 scores of 0.770, 0.776, and 0.855, respectively, achieving average improvements of 352.6%, 284.3%, and 214.9% over the existing methods, respectively. Furthermore, We evaluate RAPIER with a real-world dataset obtained from a security enterprise. RAPIER effectively achieves encrypted malicious traffic detection with the best F1 score of 0.773 and improves the F1 score of existing methods by an average of 272.5%.

The ground state search of the Ising model can be used to solve many combinatorial optimization problems. Under the current computer architecture, an Ising ground state search algorithm suitable for hardware computing is necessary for solving practical problems. Inspired by the potential energy conversion of springs, we propose a point convolutional neural network algorithm for ground state search based on spring vibration model, called Spring-Ising Algorithm. Spring-Ising Algorithm regards the spin as a moving mass point connected to a spring and establish the equation of motion for all spins. Spring-Ising Algorithm can be mapped on the GPU or AI chips through the basic structure of the neural network for fast and efficient parallel computing. The algorithm has very productive results for solving the Ising model and has been test in the recognized test benchmark K2000. The algorithm introduces the concept of dynamic equilibrium to achieve a more detailed local search by dynamically adjusting the weight of the Ising model in the spring oscillation model. Finally, there is the simple hardware test speed evaluation. Spring-Ising Algorithm can provide the possibility to calculate the Ising model on a chip which focuses on accelerating neural network calculations., Comment: 15 pages, 6 figures

Localizing root causes for multi-dimensional data is critical to ensure online service systems' reliability. When a fault occurs, only the measure values within specific attribute combinations are abnormal. Such attribute combinations are substantial clues to the underlying root causes and thus are called root causes of multidimensional data. This paper proposes a generic and robust root cause localization approach for multi-dimensional data, PSqueeze. We propose a generic property of root cause for multi-dimensional data, generalized ripple effect (GRE). Based on it, we propose a novel probabilistic cluster method and a robust heuristic search method. Moreover, we identify the importance of determining external root causes and propose an effective method for the first time in literature. Our experiments on two real-world datasets with 5400 faults show that the F1-score of PSqueeze outperforms baselines by 32.89%, while the localization time is around 10 seconds across all cases. The F1-score in determining external root causes of PSqueeze achieves 0.90. Furthermore, case studies in several production systems demonstrate that PSqueeze is helpful to fault diagnosis in the real world., Comment: Accepted by Journal of Systems and Software at May 4 2023

We present a Lipschitz continuous Transformer, called LipsFormer, to pursue training stability both theoretically and empirically for Transformer-based models. In contrast to previous practical tricks that address training instability by learning rate warmup, layer normalization, attention formulation, and weight initialization, we show that Lipschitz continuity is a more essential property to ensure training stability. In LipsFormer, we replace unstable Transformer component modules with Lipschitz continuous counterparts: CenterNorm instead of LayerNorm, spectral initialization instead of Xavier initialization, scaled cosine similarity attention instead of dot-product attention, and weighted residual shortcut. We prove that these introduced modules are Lipschitz continuous and derive an upper bound on the Lipschitz constant of LipsFormer. Our experiments show that LipsFormer allows stable training of deep Transformer architectures without the need of careful learning rate tuning such as warmup, yielding a faster convergence and better generalization. As a result, on the ImageNet 1K dataset, LipsFormer-Swin-Tiny based on Swin Transformer training for 300 epochs can obtain 82.7\% without any learning rate warmup. Moreover, LipsFormer-CSwin-Tiny, based on CSwin, training for 300 epochs achieves a top-1 accuracy of 83.5\% with 4.7G FLOPs and 24M parameters. The code will be released at \url{https://github.com/IDEA-Research/LipsFormer}., Comment: To appear in ICLR 2023, our code will be public at https://github.com/IDEA-Research/LipsFormer

We propose DisCo-CLIP, a distributed memory-efficient CLIP training approach, to reduce the memory consumption of contrastive loss when training contrastive learning models. Our approach decomposes the contrastive loss and its gradient computation into two parts, one to calculate the intra-GPU gradients and the other to compute the inter-GPU gradients. According to our decomposition, only the intra-GPU gradients are computed on the current GPU, while the inter-GPU gradients are collected via all_reduce from other GPUs instead of being repeatedly computed on every GPU. In this way, we can reduce the GPU memory consumption of contrastive loss computation from $\bigO(B^2)$ to $\bigO(\frac{B^2}{N})$, where $B$ and $N$ are the batch size and the number of GPUs used for training. Such a distributed solution is mathematically equivalent to the original non-distributed contrastive loss computation, without sacrificing any computation accuracy. It is particularly efficient for large-batch CLIP training. For instance, DisCo-CLIP can enable contrastive training of a ViT-B/32 model with a batch size of 32K or 196K using 8 or 64 A100 40GB GPUs, compared with the original CLIP solution which requires 128 A100 40GB GPUs to train a ViT-B/32 model with a batch size of 32K. The code will be released at https://github.com/IDEA-Research/DisCo-CLIP, Comment: To appear in CVPR 2023 as a highlight, our code will be public at https://github.com/IDEA-Research/DisCo-CLIP

Score-based diffusion models have captured widespread attention and funded fast progress of recent vision generative tasks. In this paper, we focus on diffusion model backbone which has been much neglected before. We systematically explore vision Transformers as diffusion learners for various generative tasks. With our improvements the performance of vanilla ViT-based backbone (IU-ViT) is boosted to be on par with traditional U-Net-based methods. We further provide a hypothesis on the implication of disentangling the generative backbone as an encoder-decoder structure and show proof-of-concept experiments verifying the effectiveness of a stronger encoder for generative tasks with ASymmetriC ENcoder Decoder (ASCEND). Our improvements achieve competitive results on CIFAR-10, CelebA, LSUN, CUB Bird and large-resolution text-to-image tasks. To the best of our knowledge, we are the first to successfully train a single diffusion model on text-to-image task beyond 64x64 resolution. We hope this will motivate people to rethink the modeling choices and the training pipelines for diffusion-based generative models.

This paper describes speaker verification (SV) systems submitted by the SpeakIn team to the Task 1 and Task 2 of the Far-Field Speaker Verification Challenge 2022 (FFSVC2022). SV tasks of the challenge focus on the problem of fully supervised far-field speaker verification (Task 1) and semi-supervised far-field speaker verification (Task 2). In Task 1, we used the VoxCeleb and FFSVC2020 datasets as train datasets. And for Task 2, we only used the VoxCeleb dataset as train set. The ResNet-based and RepVGG-based architectures were developed for this challenge. Global statistic pooling structure and MQMHA pooling structure were used to aggregate the frame-level features across time to obtain utterance-level representation. We adopted AM-Softmax and AAM-Softmax to classify the resulting embeddings. We innovatively propose a staged transfer learning method. In the pre-training stage we reserve the speaker weights, and there are no positive samples to train them in this stage. Then we fine-tune these weights with both positive and negative samples in the second stage. Compared with the traditional transfer learning strategy, this strategy can better improve the model performance. The Sub-Mean and AS-Norm backend methods were used to solve the problem of domain mismatch. In the fusion stage, three models were fused in Task1 and two models were fused in Task2. On the FFSVC2022 leaderboard, the EER of our submission is 3.0049% and the corresponding minDCF is 0.2938 in Task1. In Task2, EER and minDCF are 6.2060% and 0.5232 respectively. Our approach leads to excellent performance and ranks 1st in both challenge tasks., Comment: 5 pages. arXiv admin note: text overlap with arXiv:2209.10846

This report describes our speaker verification systems for the tasks of the CN-Celeb Speaker Recognition Challenge 2022 (CNSRC 2022). This challenge includes two tasks, namely speaker verification(SV) and speaker retrieval(SR). The SV task involves two tracks: fixed track and open track. In the fixed track, we only used CN-Celeb.T as the training set. For the open track of the SV task and SR task, we added our open-source audio data. The ResNet-based, RepVGG-based, and TDNN-based architectures were developed for this challenge. Global statistic pooling structure and MQMHA pooling structure were used to aggregate the frame-level features across time to obtain utterance-level representation. We adopted AM-Softmax and AAM-Softmax combined with the Sub-Center method to classify the resulting embeddings. We also used the Large-Margin Fine-Tuning strategy to further improve the model performance. In the backend, Sub-Mean and AS-Norm were used. In the SV task fixed track, our system was a fusion of five models, and two models were fused in the SV task open track. And we used a single system in the SR task. Our approach leads to superior performance and comes the 1st place in the open track of the SV task, the 2nd place in the fixed track of the SV task, and the 3rd place in the SR task., Comment: 4 pages

Virus infection is one of the major diseases that seriously threaten human health. To meet the growing demand for mining and sharing data resources related to antiviral drugs and to accelerate the design and discovery of new antiviral drugs, we presented an open-access antiviral drug resource and machine learning platform (VDDB), which, to the best of our knowledge, is the first comprehensive dedicated resource for experimentally verified potential drugs/molecules based on manually curated data. Currently, VDDB highlights 848 clinical vaccines, 199 clinical antibodies, as well as over 710,000 small molecules targeting 39 medically important viruses including SARS-CoV-2. Furthermore, VDDB stores approximately 3 million records of pharmacological data for these collected potential antiviral drugs/molecules, involving 314 cell infection-based phenotypic and 234 target-based genotypic assays. Based on these annotated pharmacological data, VDDB allows users to browse, search and download reliable information about these collects for various viruses of interest. In particular, VDDB also integrates 57 cell infection- and 117 target-based associated high-accuracy machine learning models to support various antivirals identification-related tasks, such as compound activity prediction, virtual screening, drug repositioning and target fishing. VDDB is freely accessible at http://vddb.idruglab.cn.

Dense prediction in medical volume provides enriched guidance for clinical analysis. CNN backbones have met bottleneck due to lack of long-range dependencies and global context modeling power. Recent works proposed to combine vision transformer with CNN, due to its strong global capture ability and learning capability. However, most works are limited to simply applying pure transformer with several fatal flaws (i.e., lack of inductive bias, heavy computation and little consideration for 3D data). Therefore, designing an elegant and efficient vision transformer learner for dense prediction in medical volume is promising and challenging. In this paper, we propose a novel 3D Shuffle-Mixer network of a new Local Vision Transformer-MLP paradigm for medical dense prediction. In our network, a local vision transformer block is utilized to shuffle and learn spatial context from full-view slices of rearranged volume, a residual axial-MLP is designed to mix and capture remaining volume context in a slice-aware manner, and a MLP view aggregator is employed to project the learned full-view rich context to the volume feature in a view-aware manner. Moreover, an Adaptive Scaled Enhanced Shortcut is proposed for local vision transformer to enhance feature along spatial and channel dimensions adaptively, and a CrossMerge is proposed to skip-connects the multi-scale feature appropriately in the pyramid architecture. Extensive experiments demonstrate the proposed model outperforms other state-of-the-art medical dense prediction methods.

Crack nucleation is crucial in many industrial applications. The phase field method for fracture transforms the crack nucleation problem into a minimization problem of the sum of the elastic potential energy and the crack surface energy. Due to the polyconvexity of the formulation, starting from a crackless solid, a standard Newton iteration may lead to a solution with no crack, even though a cracked solution has a lower total energy. As such, the critical load for cracking is highly overestimated. Here, we propose an algorithm termed "parallel universe" algorithm to capture the global minimum. This algorithm has two key ingredients: (a) a necessary condition for cracking solely based on the current crackless solution, and (b) beginning from when this condition is met, Newton iteration with two initial guesses, a crackles one and a cracked one, will both be performed and the converged candidate solution with lower energy is accepted as the solution at that load step. Once the cracked candidate solution is accepted, the crackless one is discarded, i.e., only one universe is retained. This cracked initial guess is obtained only once for all load steps by solving a series of similar minimization problems with a progressively reduced critical crack energy release rate. Numerical examples with isotropic and anisotropic critical crack energy release rates indicate that the proposed algorithm is more reliable (as there is no need to retrace) and more efficient than the standard Newton iteration and a well-known backtracking algorithm.

Doctors often make diagonostic decisions based on patient's image scans, such as magnetic resonance imaging (MRI), and patient's electronic health records (EHR) such as age, gender, blood pressure and so on. Despite a lot of automatic methods have been proposed for either image or text analysis in computer vision or natural language research areas, much fewer studies have been developed for the fusion of medical image and EHR data for medical problems. Among existing early or intermediate fusion methods, concatenation of features from both modalities is still a mainstream. For a better exploiting of image and EHR data, we propose a multi-modal attention module which use EHR data to help the selection of important regions during image feature extraction process conducted by traditional CNN. Moreover, we propose to incorporate multi-head machnism to gated multimodal unit (GMU) to make it able to parallelly fuse image and EHR features in different subspaces. With the help of the two modules, existing CNN architecture can be enhanced using both modalities. Experiments on predicting Glasgow outcome scale (GOS) of intracerebral hemorrhage patients and classifying Alzheimer's Disease showed the proposed method can automatically focus on task-related areas and achieve better results by making better use of image and EHR features.

In this technical report, we present our 1st place solution for the ICDAR 2021 competition on mathematical formula detection (MFD). The MFD task has three key challenges including a large scale span, large variation of the ratio between height and width, and rich character set and mathematical expressions. Considering these challenges, we used Generalized Focal Loss (GFL), an anchor-free method, instead of the anchor-based method, and prove the Adaptive Training Sampling Strategy (ATSS) and proper Feature Pyramid Network (FPN) can well solve the important issue of scale variation. Meanwhile, we also found some tricks, e.g., Deformable Convolution Network (DCN), SyncBN, and Weighted Box Fusion (WBF), were effective in MFD task. Our proposed method ranked 1st in the final 15 teams., Comment: 1st Place Solution for ICDAR 2021 Competition on Mathematical Formula Detection. http://transcriptorium.eu/~htrcontest/MathsICDAR2021/

TextVQA requires models to read and reason about text in images to answer questions about them. Specifically, models need to incorporate a new modality of text present in the images and reason over it to answer TextVQA questions. In this challenge, we use generative model T5 for TextVQA task. Based on pre-trained checkpoint T5-3B from HuggingFace repository, two other pre-training tasks including masked language modeling(MLM) and relative position prediction(RPP) are designed to better align object feature and scene text. In the stage of pre-training, encoder is dedicate to handle the fusion among multiple modalities: question text, object text labels, scene text labels, object visual features, scene visual features. After that decoder generates the text sequence step-by-step, cross entropy loss is required by default. We use a large-scale scene text dataset in pre-training and then fine-tune the T5-3B with the TextVQA dataset only., Comment: Winner of TextVQA 2021

This paper presents our solution for ICDAR 2021 competition on scientific literature parsing taskB: table recognition to HTML. In our method, we divide the table content recognition task into foursub-tasks: table structure recognition, text line detection, text line recognition, and box assignment.Our table structure recognition algorithm is customized based on MASTER [1], a robust image textrecognition algorithm. PSENet [2] is used to detect each text line in the table image. For text linerecognition, our model is also built on MASTER. Finally, in the box assignment phase, we associatedthe text boxes detected by PSENet with the structure item reconstructed by table structure prediction,and fill the recognized content of the text line into the corresponding item. Our proposed methodachieves a 96.84% TEDS score on 9,115 validation samples in the development phase, and a 96.32%TEDS score on 9,064 samples in the final evaluation phase., Comment: 8 Pages, 7 Figures

This paper presents our solution for the ICDAR 2021 Competition on Scientific Table Image Recognition to LaTeX. This competition has two sub-tasks: Table Structure Reconstruction (TSR) and Table Content Reconstruction (TCR). We treat both sub-tasks as two individual image-to-sequence recognition problems. We leverage our previously proposed algorithm MASTER \cite{lu2019master}, which is originally proposed for scene text recognition. We optimize the MASTER model from several perspectives: network structure, optimizer, normalization method, pre-trained model, resolution of input image, data augmentation, and model ensemble. Our method achieves 0.7444 Exact Match and 0.8765 Exact Match @95\% on the TSR task, and obtains 0.5586 Exact Match and 0.7386 Exact Match 95\% on the TCR task., Comment: 7 pages, 4 figures

Automatic lyrics generation has received attention from both music and AI communities for years. Early rule-based approaches have~---due to increases in computational power and evolution in data-driven models---~mostly been replaced with deep-learning-based systems. Many existing approaches, however, either rely heavily on prior knowledge in music and lyrics writing or oversimplify the task by largely discarding melodic information and its relationship with the text. We propose an end-to-end melody-conditioned lyrics generation system based on Sequence Generative Adversarial Networks (SeqGAN), which generates a line of lyrics given the corresponding melody as the input. Furthermore, we investigate the performance of the generator with an additional input condition: the theme or overarching topic of the lyrics to be generated. We show that the input conditions have no negative impact on the evaluation metrics while enabling the network to produce more meaningful results.

Graph Neural Networks (GNNs) have attracted considerable attention and have emerged as a new promising paradigm to process graph-structured data. GNNs are usually stacked to multiple layers and the node representations in each layer are computed through propagating and aggregating the neighboring node features with respect to the graph. By stacking to multiple layers, GNNs are able to capture the long-range dependencies among the data on the graph and thus bring performance improvements. To train a GNN with multiple layers effectively, some normalization techniques (e.g., node-wise normalization, batch-wise normalization) are necessary. However, the normalization techniques for GNNs are highly task-relevant and different application tasks prefer to different normalization techniques, which is hard to know in advance. To tackle this deficiency, in this paper, we propose to learn graph normalization by optimizing a weighted combination of normalization techniques at four different levels, including node-wise normalization, adjacency-wise normalization, graph-wise normalization, and batch-wise normalization, in which the adjacency-wise normalization and the graph-wise normalization are newly proposed in this paper to take into account the local structure and the global structure on the graph, respectively. By learning the optimal weights, we are able to automatically select a single best or a best combination of multiple normalizations for a specific task. We conduct extensive experiments on benchmark datasets for different tasks, including node classification, link prediction, graph classification and graph regression, and confirm that the learned graph normalization leads to competitive results and that the learned weights suggest the appropriate normalization techniques for the specific task. Source code is released here https://github.com/cyh1112/GraphNormalization., Comment: 15 pages, 3 figures, 6 tables

Recently, inspired by Transformer, self-attention-based scene text recognition approaches have achieved outstanding performance. However, we find that the size of model expands rapidly with the lexicon increasing. Specifically, the number of parameters for softmax classification layer and output embedding layer are proportional to the vocabulary size. It hinders the development of a lightweight text recognition model especially applied for Chinese and multiple languages. Thus, we propose a lightweight scene text recognition model named Hamming OCR. In this model, a novel Hamming classifier, which adopts locality sensitive hashing (LSH) algorithm to encode each character, is proposed to replace the softmax regression and the generated LSH code is directly employed to replace the output embedding. We also present a simplified transformer decoder to reduce the number of parameters by removing the feed-forward network and using cross-layer parameter sharing technique. Compared with traditional methods, the number of parameters in both classification and embedding layers is independent on the size of vocabulary, which significantly reduces the storage requirement without loss of accuracy. Experimental results on several datasets, including four public benchmaks and a Chinese text dataset synthesized by SynthText with more than 20,000 characters, shows that Hamming OCR achieves competitive results., Comment: 9 Pages, 4 Figure

How can we effectively utilise the 2D monocular image information for recovering the 6D pose (6-DoF) of the visual objects? Deep learning has shown to be effective for robust and real-time monocular pose estimation. Oftentimes, the network learns to regress the 6-DoF pose using a naive loss function. However, due to a lack of geometrical scene understanding from the directly regressed pose estimation, there are misalignments between the rendered mesh from the 3D object and the 2D instance segmentation result, e.g., bounding boxes and masks prediction. This paper bridges the gap between 2D mask generation and 3D location prediction via a differentiable neural mesh renderer. We utilise the overlay between the accurate mask prediction and less accurate mesh prediction to iteratively optimise the direct regressed 6D pose information with a focus on translation estimation. By leveraging geometry, we demonstrate that our technique significantly improves direct regression performance on the difficult task of translation estimation and achieve the state of the art results on Peking University/Baidu - Autonomous Driving dataset and the ApolloScape 3D Car Instance dataset. The code can be found at \url{https://bit.ly/2IRihfU}.

Attention-based scene text recognizers have gained huge success, which leverages a more compact intermediate representation to learn 1d- or 2d- attention by a RNN-based encoder-decoder architecture. However, such methods suffer from attention-drift problem because high similarity among encoded features leads to attention confusion under the RNN-based local attention mechanism. Moreover, RNN-based methods have low efficiency due to poor parallelization. To overcome these problems, we propose the MASTER, a self-attention based scene text recognizer that (1) not only encodes the input-output attention but also learns self-attention which encodes feature-feature and target-target relationships inside the encoder and decoder and (2) learns a more powerful and robust intermediate representation to spatial distortion, and (3) owns a great training efficiency because of high training parallelization and a high-speed inference because of an efficient memory-cache mechanism. Extensive experiments on various benchmarks demonstrate the superior performance of our MASTER on both regular and irregular scene text. Pytorch code can be found at https://github.com/wenwenyu/MASTER-pytorch, and Tensorflow code can be found at https://github.com/jiangxiluning/MASTER-TF., Comment: Accepted by Pattern Recognition. Ning Lu and Wenwen Yu are co-first authors