Harbin Institute of Technology

About: Harbin Institute of Technology is a education organization based out in Harbin, China. It is known for research contribution in the topics: Microstructure & Control theory. The organization has 88259 authors who have published 109297 publications receiving 1603393 citations. The organization is also known as: HIT.

DeepGauge: multi-granularity testing criteria for deep learning systems

Abstract: Deep learning (DL) defines a new data-driven programming paradigm that constructs the internal system logic of a crafted neuron network through a set of training data. We have seen wide adoption of DL in many safety-critical scenarios. However, a plethora of studies have shown that the state-of-the-art DL systems suffer from various vulnerabilities which can lead to severe consequences when applied to real-world applications. Currently, the testing adequacy of a DL system is usually measured by the accuracy of test data. Considering the limitation of accessible high quality test data, good accuracy performance on test data can hardly provide confidence to the testing adequacy and generality of DL systems. Unlike traditional software systems that have clear and controllable logic and functionality, the lack of interpretability in a DL system makes system analysis and defect detection difficult, which could potentially hinder its real-world deployment. In this paper, we propose DeepGauge, a set of multi-granularity testing criteria for DL systems, which aims at rendering a multi-faceted portrayal of the testbed. The in-depth evaluation of our proposed testing criteria is demonstrated on two well-known datasets, five DL systems, and with four state-of-the-art adversarial attack techniques against DL. The potential usefulness of DeepGauge sheds light on the construction of more generic and robust DL systems.

GraphCodeBERT: Pre-training Code Representations with Data Flow

Abstract: Pre-trained models for programming language have achieved dramatic empirical improvements on a variety of code-related tasks such as code search, code completion, code summarization, etc. However, existing pre-trained models regard a code snippet as a sequence of tokens, while ignoring the inherent structure of code, which provides crucial code semantics and would enhance the code understanding process. We present GraphCodeBERT, a pre-trained model for programming language that considers the inherent structure of code. Instead of taking syntactic-level structure of code like abstract syntax tree (AST), we use data flow in the pre-training stage, which is a semantic-level structure of code that encodes the relation of "where-the-value-comes-from" between variables. Such a semantic-level structure is neat and does not bring an unnecessarily deep hierarchy of AST, the property of which makes the model more efficient. We develop GraphCodeBERT based on Transformer. In addition to using the task of masked language modeling, we introduce two structure-aware pre-training tasks. One is to predict code structure edges, and the other is to align representations between source code and code structure. We implement the model in an efficient way with a graph-guided masked attention function to incorporate the code structure. We evaluate our model on four tasks, including code search, clone detection, code translation, and code refinement. Results show that code structure and newly introduced pre-training tasks can improve GraphCodeBERT and achieves state-of-the-art performance on the four downstream tasks. We further show that the model prefers structure-level attentions over token-level attentions in the task of code search.

U2Fusion: A Unified Unsupervised Image Fusion Network.

Abstract: This study proposes a novel unified and unsupervised end-to-end image fusion network, termed as U2Fusion, which is capable of solving different fusion problems, including multi-modal, multi-exposure, and multi-focus cases. Using feature extraction and information measurement, U2Fusion automatically estimates the importance of corresponding source images and comes up with adaptive information preservation degrees. Hence, different fusion tasks are unified in the same framework. Based on the adaptive degrees, a network is trained to preserve the adaptive similarity between the fusion result and source images. Therefore, the stumbling blocks in applying deep learning for image fusion, e.g., the requirement of ground-truth and specifically designed metrics, are greatly mitigated. By avoiding the loss of previous fusion capabilities when training a single model for different tasks sequentially, we obtain a unified model that is applicable to multiple fusion tasks. Moreover, a new aligned infrared and visible image dataset, RoadScene (available at https://github.com/hanna-xu/RoadScene), is released to provide a new option for benchmark evaluation. Qualitative and quantitative experimental results on three typical image fusion tasks validate the effectiveness and universality of U2Fusion. Our code is publicly available at https://github.com/hanna-xu/U2Fusion.

Initiating a mild aqueous electrolyte Co3O4/Zn battery with 2.2 V-high voltage and 5000-cycle lifespan by a Co(III) rich-electrode

Abstract: The Zn/Co3O4 battery is one of the few aqueous electrolyte batteries with a potential >2 V voltage. Unfortunately, so far, all reported Zn/Co3O4 batteries are using an alkaline electrolyte, resulting in poor cycling stability and environmental problems. Here, we report a Co(III) rich-Co3O4 nanorod material with vastly improved electrochemical kinetics. Zn/Co(III) rich-Co3O4 batteries can work well in ZnSO4 with a CoSO4 additive aqueous solution as a mild electrolyte, delivering a high voltage of 2.2 V, a capacity of 205 mA h g−1 (Co3O4) and an extreme cycling stability of 92% capacity retention even after 5000 cycles. Further mechanistic study reveals a conversion reaction between in situ formed CoO and Co3O4, which has never been observed in an alkaline Zn/Co3O4 battery. Subsequently, a flexible solid-state battery is constructed and reveals high flexibility and a high energy density of 360.8 W h kg−1 at a current density of 0.5 A g−1. Our research initiates the first Zn/Co3O4 battery working in a mild electrolyte, resulting in excellent electrochemical performance. It also indicates that the electrochemical kinetics can be effectively enhanced by fine tuning the atomic structure of electrode materials, opening a new door to improve the performance of aqueous electrolyte batteries.