Search

Automatically constructing GUI groups of different granularities constitutes a critical intelligent step towards automating GUI design and implementation tasks. Specifically, in the industrial GUI-to-code process, fragmented layers may decrease the readability and maintainability of generated code, which can be alleviated by grouping semantically consistent fragmented layers in the design prototypes. This study aims to propose a graph-learning-based approach to tackle the fragmented layer grouping problem according to multi-modal information in design prototypes. Our graph learning module consists of self-attention and graph neural network modules. By taking the multimodal fused representation of GUI layers as input, we innovatively group fragmented layers by classifying GUI layers and regressing the bounding boxes of the corresponding GUI components simultaneously. Experiments on two real-world datasets demonstrate that our model achieves state-of-the-art performance. A further user study is also conducted to validate that our approach can assist an intelligent downstream tool in generating more maintainable and readable front-end code., Comment: 28 pages,6 figures

Inspired by the would-be ${\eta}_{t}$ meson and promising prospects at the LHC, the ${\eta}_{t}$ ${\to}$ $W^{+}W^{-}$ decay is proposed to identify the ${\eta}_{t}$ meson. It is found that branching ratio for the ${\eta}_{t}$ ${\to}$ $W^{+}W^{-}$ decay is about $4.2{\times}10^{-5}$, and more than 800 events can be observed with the accumulated data of $2.7{\times}10^{7}$ ${\eta}_{t}$ meson at the HL-LHC in the future.

In this paper, the nonfactorizable photonic corrections to the effective four-fermion vertex for the $\overline{B}$ ${\to}$ $D^{({\ast})}$ $+$ ${\ell}^{-}$ $+$ $\bar{\nu}_{\ell}$ decays are considered at the quark level within SM, where ${\ell}$ $=$ $e$, ${\mu}$ and ${\tau}$. It is found that the QED corrections are closely related with the mass of the charged lepton. The QED contributions will enhance branching ratios, which results in the slight reduction of ratios $R(D^{(\ast)})$ and the relationship $R(D^{(\ast)})_{e}$ $<$ $R(D^{(\ast)})_{\mu}$., Comment: 27pages

Modern deep learning models have demonstrated outstanding performance on discovering the underlying mechanisms when both visual appearance and intrinsic relations (e.g., causal structure) data are sufficient, such as Disentangled Representation Learning (DRL), Causal Representation Learning (CRL) and Visual Question Answering (VQA) methods. However, generalization ability of these models is challenged when the visual domain shifts and the relations data is absent during finetuning. To address this challenge, we propose a novel learning framework, Look, Learn and Leverage (L$^3$), which decomposes the learning process into three distinct phases and systematically utilize the class-agnostic segmentation masks as the common symbolic space to align visual domains. Thus, a relations discovery model can be trained on the source domain, and when the visual domain shifts and the intrinsic relations are absent, the pretrained relations discovery model can be directly reused and maintain a satisfactory performance. Extensive performance evaluations are conducted on three different tasks: DRL, CRL and VQA, and show outstanding results on all three tasks, which reveals the advantages of L$^3$., Comment: 17 pages, 9 figures, 6 tables

Despite the success of vision-based dynamics prediction models, which predict object states by utilizing RGB images and simple object descriptions, they were challenged by environment misalignments. Although the literature has demonstrated that unifying visual domains with both environment context and object abstract, such as semantic segmentation and bounding boxes, can effectively mitigate the visual domain misalignment challenge, discussions were focused on the abstract of environment context, and the insight of using bounding box as the object abstract is under-explored. Furthermore, we notice that, as empirical results shown in the literature, even when the visual appearance of objects is removed, object bounding boxes alone, instead of being directly fed into the network, can indirectly provide sufficient position information via the Region of Interest Pooling operation for dynamics prediction. However, previous literature overlooked discussions regarding how such position information is implicitly encoded in the dynamics prediction model. Thus, in this paper, we provide detailed studies to investigate the process and necessary conditions for encoding position information via using the bounding box as the object abstract into output features. Furthermore, we study the limitation of solely using object abstracts, such that the dynamics prediction performance will be jeopardized when the environment context varies., Comment: 13 pages, 4 tables, and 3 figures. Accepted to ECCV2024 eXCV workshop

Accurate estimation of counterfactual outcomes in high-dimensional data is crucial for decision-making and understanding causal relationships and intervention outcomes in various domains, including healthcare, economics, and social sciences. However, existing methods often struggle to generate accurate and consistent counterfactuals, particularly when the causal relationships are complex. We propose a novel framework that incorporates causal mechanisms and diffusion models to generate high-quality counterfactual samples guided by causal representation. Our approach introduces a novel, theoretically grounded training and sampling process that enables the model to consistently generate accurate counterfactual high-dimensional data under multiple intervention steps. Experimental results on various synthetic and real benchmarks demonstrate the proposed approach outperforms state-of-the-art methods in generating accurate and high-quality counterfactuals, using different evaluation metrics.

UI-to-code technology has streamlined the front-end development process, reducing repetitive tasks for engineers. prior research mainly use design prototypes as inputs, with the effectiveness of the generated code heavily dependent on these prototypes' quality, leading to compromised robustness. Moreover, these approaches also exhibit shortcomings in code quality, including issues such as disorganized UI structures and the inability to support responsive layouts. To address these challenges, we introduce Prototype2Code, which achieves end-to-end front-end code generation with business demands. For Prototype2Code, we incorporate design linting into the workflow, addressing the detection of fragmented elements and perceptual groups, enhancing the robustness of the generated outcomes. By optimizing the hierarchical structure and intelligently recognizing UI element types, Prototype2Code generates code that is more readable and structurally clearer. To meet responsive design requirements, Prototype2Code primarily supports flexbox layout model, ensuring code compatibility across various device sizes. To validate the efficacy, we compare Prototype2Code with the commercial code generation platform CodeFun and Screenshot-to-code based on GPT-4 with vision. Employing structural similarity index measure (SSIM), peak signal-to-noise ratio (PSNR), and mean squared error (MSE) for visual similarity assessment, Prototype2Code's rendered UI effects align most closely with the design prototypes, exhibiting the minimal errors. We also conduct a user study with five experienced front-end engineers, inviting them to review and revise code generated by the three methods. As a result, Prototype2Code surpasses other methods in readability, usability, and maintainability, better meeting the business needs of industrial development., Comment: 11 pages, 6 figures

In this article, a \underline{S}tate-dependent \underline{M}ulti-\underline{A}gent \underline{D}eep \underline{D}eterministic \underline{P}olicy \underline{G}radient (\textbf{SMADDPG}) method is proposed in order to learn an optimal control policy for regionally switched systems. We observe good performance of this method and explain it in a rigorous mathematical language using some simplifying assumptions in order to motivate the ideas and to apply them to some canonical examples. Using reinforcement learning, the performance of the switched learning-based multi-agent method is compared with the vanilla DDPG in two customized demonstrative environments with one and two-dimensional state spaces.

Ensuring a neural network is not relying on protected attributes (e.g., race, sex, age) for prediction is crucial in advancing fair and trustworthy AI. While several promising methods for removing attribute bias in neural networks have been proposed, their limitations remain under-explored. To that end, in this work, we mathematically and empirically reveal the limitation of existing attribute bias removal methods in presence of strong bias and propose a new method that can mitigate this limitation. Specifically, we first derive a general non-vacuous information-theoretical upper bound on the performance of any attribute bias removal method in terms of the bias strength, revealing that they are effective only when the inherent bias in the dataset is relatively weak. Next, we derive a necessary condition for the existence of any method that can remove attribute bias regardless of the bias strength. Inspired by this condition, we then propose a new method using an adversarial objective that directly filters out protected attributes in the input space while maximally preserving all other attributes, without requiring any specific target label. The proposed method achieves state-of-the-art performance in both strong and moderate bias settings. We provide extensive experiments on synthetic, image, and census datasets, to verify the derived theoretical bound and its consequences in practice, and evaluate the effectiveness of the proposed method in removing strong attribute bias., Comment: 35 pages, 18 figures, 32 tables. This work is an extended version of our paper (arXiv:2310.04955). Code will be released at https://github.com/jiazhi412/strong_attribute_bias

Ensuring a neural network is not relying on protected attributes (e.g., race, sex, age) for predictions is crucial in advancing fair and trustworthy AI. While several promising methods for removing attribute bias in neural networks have been proposed, their limitations remain under-explored. In this work, we mathematically and empirically reveal an important limitation of attribute bias removal methods in presence of strong bias. Specifically, we derive a general non-vacuous information-theoretical upper bound on the performance of any attribute bias removal method in terms of the bias strength. We provide extensive experiments on synthetic, image, and census datasets to verify the theoretical bound and its consequences in practice. Our findings show that existing attribute bias removal methods are effective only when the inherent bias in the dataset is relatively weak, thus cautioning against the use of these methods in smaller datasets where strong attribute bias can occur, and advocating the need for methods that can overcome this limitation., Comment: 15 pages, 4 figures, 3 tables. To appear in Algorithmic Fairness through the Lens of Time Workshop at NeurIPS 2023

Discovering causal relations among semantic factors is an emergent topic in representation learning. Most causal representation learning (CRL) methods are fully supervised, which is impractical due to costly labeling. To resolve this restriction, weakly supervised CRL methods were introduced. To evaluate CRL performance, four existing datasets, Pendulum, Flow, CelebA(BEARD) and CelebA(SMILE), are utilized. However, existing CRL datasets are limited to simple graphs with few generative factors. Thus we propose two new datasets with a larger number of diverse generative factors and more sophisticated causal graphs. In addition, current real datasets, CelebA(BEARD) and CelebA(SMILE), the originally proposed causal graphs are not aligned with the dataset distributions. Thus, we propose modifications to them.

Dynamics prediction, which is the problem of predicting future states of scene objects based on current and prior states, is drawing increasing attention as an instance of learning physics. To solve this problem, Region Proposal Convolutional Interaction Network (RPCIN), a vision-based model, was proposed and achieved state-of-the-art performance in long-term prediction. RPCIN only takes raw images and simple object descriptions, such as the bounding box and segmentation mask of each object, as input. However, despite its success, the model's capability can be compromised under conditions of environment misalignment. In this paper, we investigate two challenging conditions for environment misalignment: Cross-Domain and Cross-Context by proposing four datasets that are designed for these challenges: SimB-Border, SimB-Split, BlenB-Border, and BlenB-Split. The datasets cover two domains and two contexts. Using RPCIN as a probe, experiments conducted on the combinations of the proposed datasets reveal potential weaknesses of the vision-based long-term dynamics prediction model. Furthermore, we propose a promising direction to mitigate the Cross-Domain challenge and provide concrete evidence supporting such a direction, which provides dramatic alleviation of the challenge on the proposed datasets., Comment: 14 pages, 5 figures, 10 tables. Accepted to ICML 2023

As the social impact of visual recognition has been under scrutiny, several protected-attribute balanced datasets emerged to address dataset bias in imbalanced datasets. However, in facial attribute classification, dataset bias stems from both protected attribute level and facial attribute level, which makes it challenging to construct a multi-attribute-level balanced real dataset. To bridge the gap, we propose an effective pipeline to generate high-quality and sufficient facial images with desired facial attributes and supplement the original dataset to be a balanced dataset at both levels, which theoretically satisfies several fairness criteria. The effectiveness of our method is verified on sex classification and facial attribute classification by yielding comparable task performance as the original dataset and further improving fairness in a comprehensive fairness evaluation with a wide range of metrics. Furthermore, our method outperforms both resampling and balanced dataset construction to address dataset bias, and debiasing models to address task bias.

While some work attempt to generate front-end code intelligently from UI screenshots, it may be more convenient to utilize UI design drafts in Sketch which is a popular UI design software, because we can access multimodal UI information directly such as layers type, position, size, and visual images. However, fragmented layers could degrade the code quality without being merged into a whole part if all of them are involved in the code generation. In this paper, we propose a pipeline to merge fragmented layers automatically. We first construct a graph representation for the layer tree of a UI draft and detect all fragmented layers based on the visual features and graph neural networks. Then a rule-based algorithm is designed to merge fragmented layers. Through experiments on a newly constructed dataset, our approach can retrieve most fragmented layers in UI design drafts, and achieve 87% accuracy in the detection task, and the post-processing algorithm is developed to cluster associative layers under simple and general circumstances.

As equality issues in the use of face recognition have garnered a lot of attention lately, greater efforts have been made to debiased deep learning models to improve fairness to minorities. However, there is still no clear definition nor sufficient analysis for bias assessment metrics. We propose an information-theoretic, independent bias assessment metric to identify degree of bias against protected demographic attributes from learned representations of pretrained facial recognition systems. Our metric differs from other methods that rely on classification accuracy or examine the differences between ground truth and predicted labels of protected attributes predicted using a shallow network. Also, we argue, theoretically and experimentally, that logits-level loss is not adequate to explain bias since predictors based on neural networks will always find correlations. Further, we present a synthetic dataset that mitigates the issue of insufficient samples in certain cohorts. Lastly, we establish a benchmark metric by presenting advantages in clear discrimination and small variation comparing with other metrics, and evaluate the performance of different debiased models with the proposed metric., Comment: IEEE International Conference on Automatic Face and Gesture Recognition 2021