In principal modern detectors, the task of object localization is implemented by the box subnet which concentrates on bounding box regression. The box subnet customarily predicts the position of the object by regressing box center position and scaling factors. Although this approach is frequently adopted, we observe that the result of localization remains defective, which makes the performance of the detector unsatisfactory. In this paper, we prove the flaws in the previous method through theoretical analysis and experimental verification and propose a novel solution to detect objects precisely. Rather than plainly focusing on center and size, our approach refines the edges of the bounding box on previous localization results by estimating the distribution at the boundary of the object. Experimental results have shown the potentiality and generalization of our proposed method.
The research focus of scene text detection has shifted to arbitrary shape text in recent years, in which text representation is a fundamental problem. An ideal representation should be compact, complete, integral, and reusable for subsequent recognition in our opinion. However, previous representations suffer from one or several aspects. Thin-Plate-Spline (TPS) transformation has achieved great success in scene text recognition. Inspired from this, we reversely think its usage and sophisticatedly take TPS as an exquisite representation for arbitrary shape text detection. The TPS representation is compact, complete and integral, and with the predicted TPS parameters, the detected text region can be rectified to near-horizontal one which is beneficial for subsequent recognition. To solve the supervision problem of TPS training without key point annotations, two novel losses including the boundary set loss and the shape alignment loss are proposed. Extensive evaluation and ablation on several public benchmarks demonstrate the effectiveness and superiority of the proposed method.
The advances in attention-based encoder-decoder (AED) networks have brought great progress to end-to-end (E2E) automatic speech recognition (ASR). One way to further improve the performance of AED-based E2E ASR is to introduce an extra text encoder for leveraging extensive text data and thus capture more context-aware linguistic information. However, this approach brings a mismatch problem between the speech encoder and the text encoder due to the different units used for modeling. In this paper, we propose an embedding aligner and modality switch training to better align the speech and text latent spaces. The embedding aligner is a shared linear projection between text encoder and speech encoder trained by masked language modeling (MLM) loss and connectionist temporal classification (CTC), respectively. The modality switch training randomly swaps speech and text embeddings based on the forced alignment result to learn a joint representation space. Experimental results show that our proposed approach achieves a relative 14% to 19% word error rate (WER) reduction on Librispeech ASR task. We further verify its effectiveness on spoken language understanding (SLU), i.e., an absolute 2.5% to 2.8% F1 score improvement on SNIPS slot filling task.
Keyphrases are phrases in a document providing a concise summary of core content, helping readers to understand what the article is talking about in a minute. However, existing unsupervised works are not robust enough to handle various types of documents owing to the mismatch of sequence length for comparison. In this paper, we propose a novel unsupervised keyword extraction method by leveraging the BERT-based model to select and rank candidate keyphrases with a MASK strategy. In addition, we further enhance the model, denoted as Keyphrases Extraction BERT (KPEBERT), via designing a compatible self-supervised task and conducting a contrast learning. We conducted extensive experimental evaluation to demonstrate the superiority and robustness of the proposed method as well as the effectiveness of KPEBERT.
Approximate nearest neighbor (ANN) search is a fundamental problem in areas such as data management,information retrieval and machine learning. Recently, Li et al. proposed a learned approach named AdaptNN to support adaptive ANN query processing. In the middle of query execution, AdaptNN collects a number of runtime features and predicts termination condition for each individual query, by which better end-to-end latency is attained. Despite its efficiency, using runtime features complicates the learning process and leads to performance degradation. Radically different from AdaptNN, we argue that it is promising to predict termination condition before query exetution. Particularly, we developed Tao, a general learning framework for Terminating ANN queries Adaptively using Only static features. Upon the arrival of a query, Tao first maps the query to a local intrinsic dimension (LID) number, and then predicts the termination condition using LID instead of runtime features. By decoupling prediction procedure from query execution, Tao eliminates the laborious feature selection process involved in AdaptNN. Besides, two design principles are formulated to guide the application of Tao and improve the explainability of the prediction model. We integrate two state-of-the-art indexing approaches, i.e., IMI and HNSW, into Tao, and evaluate the performance over several million to billion-scale datasets. Experimental results show that, in addition to its simplicity and generality , Tao achieves up to 2.69x speedup even compared to its counterpart, at the same high accuracy targets.
Homomorphic encryption (HE) is a promising privacy-preserving technique for cross-silo federated learning (FL), where organizations perform collaborative model training on decentralized data. Despite the strong privacy guarantee, general HE schemes result in significant computation and communication overhead. Prior works employ batch encryption to address this problem, but it is still suboptimal in mitigating communication overhead and is incompatible with sparsification techniques. In this paper, we propose FLASHE, an HE scheme tailored for cross-silo FL. To capture the minimum requirements of security and functionality, FLASHE drops the asymmetric-key design and only involves modular addition operations with random numbers. Depending on whether to accommodate sparsification techniques, FLASHE is optimized in computation efficiency with different approaches. We have implemented FLASHE as a pluggable module atop FATE, an industrial platform for cross-silo FL. Compared to plaintext training, FLASHE slightly increases the training time by $\leq6\%$, with no communication overhead.
Background: The worldwide surge in coronavirus cases has led to the COVID-19 testing demand surge. Rapid, accurate, and cost-effective COVID-19 screening tests working at a population level are in imperative demand globally. Methods: Based on the eye symptoms of COVID-19, we developed and tested a COVID-19 rapid prescreening model using the eye-region images captured in China and Spain with cellphone cameras. The convolutional neural networks (CNNs)-based model was trained on these eye images to complete binary classification task of identifying the COVID-19 cases. The performance was measured using area under receiver-operating-characteristic curve (AUC), sensitivity, specificity, accuracy, and F1. The application programming interface was open access. Findings: The multicenter study included 2436 pictures corresponding to 657 subjects (155 COVID-19 infection, 23.6%) in development dataset (train and validation) and 2138 pictures corresponding to 478 subjects (64 COVID-19 infections, 13.4%) in test dataset. The image-level performance of COVID-19 prescreening model in the China-Spain multicenter study achieved an AUC of 0.913 (95% CI, 0.898-0.927), with a sensitivity of 0.695 (95% CI, 0.643-0.748), a specificity of 0.904 (95% CI, 0.891 -0.919), an accuracy of 0.875(0.861-0.889), and a F1 of 0.611(0.568-0.655). Interpretation: The CNN-based model for COVID-19 rapid prescreening has reliable specificity and sensitivity. This system provides a low-cost, fully self-performed, non-invasive, real-time feedback solution for continuous surveillance and large-scale rapid prescreening for COVID-19. Funding: This project is supported by Aimomics (Shanghai) Intelligent
Self-supervised representation learning for visual pre-training has achieved remarkable success with sample (instance or pixel) discrimination and semantics discovery of instance, whereas there still exists a non-negligible gap between pre-trained model and downstream dense prediction tasks. Concretely, these downstream tasks require more accurate representation, in other words, the pixels from the same object must belong to a shared semantic category, which is lacking in the previous methods. In this work, we present Dense Semantic Contrast (DSC) for modeling semantic category decision boundaries at a dense level to meet the requirement of these tasks. Furthermore, we propose a dense cross-image semantic contrastive learning framework for multi-granularity representation learning. Specially, we explicitly explore the semantic structure of the dataset by mining relations among pixels from different perspectives. For intra-image relation modeling, we discover pixel neighbors from multiple views. And for inter-image relations, we enforce pixel representation from the same semantic class to be more similar than the representation from different classes in one mini-batch. Experimental results show that our DSC model outperforms state-of-the-art methods when transferring to downstream dense prediction tasks, including object detection, semantic segmentation, and instance segmentation. Code will be made available.
The unprecedented demand for collaborative machine learning in a privacy-preserving manner gives rise to a novel machine learning paradigm called federated learning (FL). Given a sufficient level of privacy guarantees, the practicality of an FL system mainly depends on its time-to-accuracy performance during the training process. Despite bearing some resemblance with traditional distributed training, FL has four distinct challenges that complicate the optimization towards shorter time-to-accuracy: information deficiency, coupling for contrasting factors, client heterogeneity, and huge configuration space. Motivated by the need for inspiring related research, in this paper we survey highly relevant attempts in the FL literature and organize them by the related training phases in the standard workflow: selection, configuration, and reporting. We also review exploratory work including measurement studies and benchmarking tools to friendly support FL developers. Although a few survey articles on FL already exist, our work differs from them in terms of the focus, classification, and implications.
Object SLAM introduces the concept of objects into Simultaneous Localization and Mapping (SLAM) and helps understand indoor scenes for mobile robots and object-level interactive applications. The state-of-art object SLAM systems face challenges such as partial observations, occlusions, unobservable problems, limiting the mapping accuracy and robustness. This paper proposes a novel monocular Semantic Object SLAM (SO-SLAM) system that addresses the introduction of object spatial constraints. We explore three representative spatial constraints, including scale proportional constraint, symmetrical texture constraint and plane supporting constraint. Based on these semantic constraints, we propose two new methods - a more robust object initialization method and an orientation fine optimization method. We have verified the performance of the algorithm on the public datasets and an author-recorded mobile robot dataset and achieved a significant improvement on mapping effects. We will release the code here: https://github.com/XunshanMan/SoSLAM.