Yang Xu

Xu Yang, Hanwang Zhang, Chongyang Gao et al.

Humans tend to decompose a sentence into different parts like \textsc{sth do sth at someplace} and then fill each part with certain content. Inspired by this, we follow the \textit{principle of modular design} to propose a novel image captioner: learning to Collocate Visual-Linguistic Neural Modules (CVLNM). Unlike the \re{widely used} neural module networks in VQA, where the language (\ie, question) is fully observable, \re{the task of collocating visual-linguistic modules is more challenging.} This is because the language is only partially observable, for which we need to dynamically collocate the modules during the process of image captioning. To sum up, we make the following technical contributions to design and train our CVLNM: 1) \textit{distinguishable module design} -- \re{four modules in the encoder} including one linguistic module for function words and three visual modules for different content words (\ie, noun, adjective, and verb) and another linguistic one in the decoder for commonsense reasoning, 2) a self-attention based \textit{module controller} for robustifying the visual reasoning, 3) a part-of-speech based \textit{syntax loss} imposed on the module controller for further regularizing the training of our CVLNM. Extensive experiments on the MS-COCO dataset show that our CVLNM is more effective, \eg, achieving a new state-of-the-art 129.5 CIDEr-D, and more robust, \eg, being less likely to overfit to dataset bias and suffering less when fewer training samples are available. Codes are available at \url{https://github.com/GCYZSL/CVLMN}

Yang Xu, Li Li, Haiyang Xu et al.

Image Captioning (IC) has achieved astonishing developments by incorporating various techniques into the CNN-RNN encoder-decoder architecture. However, since CNN and RNN do not share the basic network component, such a heterogeneous pipeline is hard to be trained end-to-end where the visual encoder will not learn anything from the caption supervision. This drawback inspires the researchers to develop a homogeneous architecture that facilitates end-to-end training, for which Transformer is the perfect one that has proven its huge potential in both vision and language domains and thus can be used as the basic component of the visual encoder and language decoder in an IC pipeline. Meantime, self-supervised learning releases the power of the Transformer architecture that a pre-trained large-scale one can be generalized to various tasks including IC. The success of these large-scale models seems to weaken the importance of the single IC task. However, we demonstrate that IC still has its specific significance in this age by analyzing the connections between IC with some popular self-supervised learning paradigms. Due to the page limitation, we only refer to highly important papers in this short survey and more related works can be found at https://github.com/SjokerLily/awesome-image-captioning.

Yang Xu, Ronghao Zheng, Senlin Zhang et al.

In this paper, we consider improving the efficiency of information-based autonomous robot exploration in unknown and complex environments. We first utilize Gaussian process (GP) regression to learn a surrogate model to infer the confidence-rich mutual information (CRMI) of querying control actions, then adopt an objective function consisting of predicted CRMI values and prediction uncertainties to conduct Bayesian optimization (BO), i.e., GP-based BO (GPBO). The trade-off between the best action with the highest CRMI value (exploitation) and the action with high prediction variance (exploration) can be realized. To further improve the efficiency of GPBO, we propose a novel lightweight information gain inference method based on Bayesian kernel inference and optimization (BKIO), achieving an approximate logarithmic complexity without the need for training. BKIO can also infer the CRMI and generate the best action using BO with bounded cumulative regret, which ensures its comparable accuracy to GPBO with much higher efficiency. Extensive numerical and real-world experiments show the desired efficiency of our proposed methods without losing exploration performance in different unstructured, cluttered environments. We also provide our open-source implementation code at https://github.com/Shepherd-Gregory/BKIO-Exploration.

Aida Ramezani, Yang Xu · utoronto

Moral norms vary across cultures. A recent line of work suggests that English large language models contain human-like moral biases, but these studies typically do not examine moral variation in a diverse cultural setting. We investigate the extent to which monolingual English language models contain knowledge about moral norms in different countries. We consider two levels of analysis: 1) whether language models capture fine-grained moral variation across countries over a variety of topics such as ``homosexuality'' and ``divorce''; 2) whether language models capture cultural diversity and shared tendencies in which topics people around the globe tend to diverge or agree on in their moral judgment. We perform our analyses with two public datasets from the World Values Survey (across 55 countries) and PEW global surveys (across 40 countries) on morality. We find that pre-trained English language models predict empirical moral norms across countries worse than the English moral norms reported previously. However, fine-tuning language models on the survey data improves inference across countries at the expense of a less accurate estimate of the English moral norms. We discuss the relevance and challenges of incorporating cultural knowledge into the automated inference of moral norms.

Bowen Xie, Yuxuan Sun, Sheng Zhou et al.

Federated learning (FL) is a promising approach to enable the future Internet of vehicles consisting of intelligent connected vehicles (ICVs) with powerful sensing, computing and communication capabilities. We consider a base station (BS) coordinating nearby ICVs to train a neural network in a collaborative yet distributed manner, in order to limit data traffic and privacy leakage. However, due to the mobility of vehicles, the connections between the BS and ICVs are short-lived, which affects the resource utilization of ICVs, and thus, the convergence speed of the training process. In this paper, we propose an accelerated FL-ICV framework, by optimizing the duration of each training round and the number of local iterations, for better convergence performance of FL. We propose a mobility-aware optimization algorithm called MOB-FL, which aims at maximizing the resource utilization of ICVs under short-lived wireless connections, so as to increase the convergence speed. Simulation results based on the beam selection and the trajectory prediction tasks verify the effectiveness of the proposed solution.

Zhewei Sun, Richard Zemel, Yang Xu

Slang is a predominant form of informal language making flexible and extended use of words that is notoriously hard for natural language processing systems to interpret. Existing approaches to slang interpretation tend to rely on context but ignore semantic extensions common in slang word usage. We propose a semantically informed slang interpretation (SSI) framework that considers jointly the contextual and semantic appropriateness of a candidate interpretation for a query slang. We perform rigorous evaluation on two large-scale online slang dictionaries and show that our approach not only achieves state-of-the-art accuracy for slang interpretation in English, but also does so in zero-shot and few-shot scenarios where training data is sparse. Furthermore, we show how the same framework can be applied to enhancing machine translation of slang from English to other languages. Our work creates opportunities for the automated interpretation and translation of informal language.

Zihua Wang, Xu Yang, Hanwang Zhang et al.

We propose a novel Transformer-based image-to-text generation model termed as \textbf{ACF} that adaptively clusters vision patches into object regions and language words into phrases to implicitly learn object-phrase alignments for better visual-text coherence. To achieve this, we design a novel self-attention layer that applies self-attention over the elements in a local cluster window instead of the whole sequence. The window size is softly decided by a clustering matrix that is calculated by the current input data and thus this process is adaptive. By stacking these revised self-attention layers to construct ACF, the small clusters in the lower layers can be grouped into a bigger cluster, \eg vision/language. ACF clusters small objects/phrases into bigger ones. In this gradual clustering process, a parsing tree is generated which embeds the hierarchical knowledge of the input sequence. As a result, by using ACF to build the vision encoder and language decoder, the hierarchical object-phrase alignments are embedded and then transferred from vision to language domains in two popular image-to-text tasks: Image captioning and Visual Question Answering. The experiment results demonstrate the effectiveness of ACF, which outperforms most SOTA captioning and VQA models and achieves comparable scores compared with some large-scale pre-trained models. Our code is available \href{https://github.com/ZihuaEvan/ACFModel/}{[here]}.

Xu Yang, Zhangzikang Li, Haiyang Xu et al.

In a video, an object usually appears as the trajectory, i.e., it spans over a few spatial but longer temporal patches, that contains abundant spatiotemporal contexts. However, modern Video-Language BERTs (VDL-BERTs) neglect this trajectory characteristic that they usually follow image-language BERTs (IL-BERTs) to deploy the patch-to-word (P2W) attention that may over-exploit trivial spatial contexts and neglect significant temporal contexts. To amend this, we propose a novel TW-BERT to learn Trajectory-Word alignment by a newly designed trajectory-to-word (T2W) attention for solving video-language tasks. Moreover, previous VDL-BERTs usually uniformly sample a few frames into the model while different trajectories have diverse graininess, i.e., some trajectories span longer frames and some span shorter, and using a few frames will lose certain useful temporal contexts. However, simply sampling more frames will also make pre-training infeasible due to the largely increased training burdens. To alleviate the problem, during the fine-tuning stage, we insert a novel Hierarchical Frame-Selector (HFS) module into the video encoder. HFS gradually selects the suitable frames conditioned on the text context for the later cross-modal encoder to learn better trajectory-word alignments. By the proposed T2W attention and HFS, our TW-BERT achieves SOTA performances on text-to-video retrieval tasks, and comparable performances on video question-answering tasks with some VDL-BERTs trained on much more data. The code will be available in the supplementary material.

Hongxin Li, Xu Yang, Yuran Yang et al.

Image-goal navigation is a challenging task, as it requires the agent to navigate to a target indicated by an image in a previously unseen scene. Current methods introduce diverse memory mechanisms which save navigation history to solve this task. However, these methods use all observations in the memory for generating navigation actions without considering which fraction of this memory is informative. To address this limitation, we present the MemoNav, a novel memory mechanism for image-goal navigation, which retains the agent's informative short-term memory and long-term memory to improve the navigation performance on a multi-goal task. The node features on the agent's topological map are stored in the short-term memory, as these features are dynamically updated. To aid the short-term memory, we also generate long-term memory by continuously aggregating the short-term memory via a graph attention module. The MemoNav retains the informative fraction of the short-term memory via a forgetting module based on a Transformer decoder and then incorporates this retained short-term memory and the long-term memory into working memory. Lastly, the agent uses the working memory for action generation. We evaluate our model on a new multi-goal navigation dataset. The experimental results show that the MemoNav outperforms the SoTA methods by a large margin with a smaller fraction of navigation history. The results also empirically show that our model is less likely to be trapped in a deadlock, which further validates that the MemoNav improves the agent's navigation efficiency by reducing redundant steps.

Zhida Jiang, Yang Xu, Hongli Xu et al.

Federated learning (FL) allows multiple clients cooperatively train models without disclosing local data. However, the existing works fail to address all these practical concerns in FL: limited communication resources, dynamic network conditions and heterogeneous client properties, which slow down the convergence of FL. To tackle the above challenges, we propose a heterogeneity-aware FL framework, called FedCG, with adaptive client selection and gradient compression. Specifically, the parameter server (PS) selects a representative client subset considering statistical heterogeneity and sends the global model to them. After local training, these selected clients upload compressed model updates matching their capabilities to the PS for aggregation, which significantly alleviates the communication load and mitigates the straggler effect. We theoretically analyze the impact of both client selection and gradient compression on convergence performance. Guided by the derived convergence rate, we develop an iteration-based algorithm to jointly optimize client selection and compression ratio decision using submodular maximization and linear programming. Extensive experiments on both real-world prototypes and simulations show that FedCG can provide up to 5.3$\times$ speedup compared to other methods.

Yang Xu, Chengchun Shi, Shikai Luo et al.

Off-Policy evaluation (OPE) is concerned with evaluating a new target policy using offline data generated by a potentially different behavior policy. It is critical in a number of sequential decision making problems ranging from healthcare to technology industries. Most of the work in existing literature is focused on evaluating the mean outcome of a given policy, and ignores the variability of the outcome. However, in a variety of applications, criteria other than the mean may be more sensible. For example, when the reward distribution is skewed and asymmetric, quantile-based metrics are often preferred for their robustness. In this paper, we propose a doubly-robust inference procedure for quantile OPE in sequential decision making and study its asymptotic properties. In particular, we propose utilizing state-of-the-art deep conditional generative learning methods to handle parameter-dependent nuisance function estimation. We demonstrate the advantages of this proposed estimator through both simulations and a real-world dataset from a short-video platform. In particular, we find that our proposed estimator outperforms classical OPE estimators for the mean in settings with heavy-tailed reward distributions.

Lu Zhang, Siqi Zhang, Xu Yang et al.

Segmenting unseen objects is a crucial ability for the robot since it may encounter new environments during the operation. Recently, a popular solution is leveraging RGB-D features of large-scale synthetic data and directly applying the model to unseen real-world scenarios. However, the domain shift caused by the sim2real gap is inevitable, posing a crucial challenge to the segmentation model. In this paper, we emphasize the adaptation process across sim2real domains and model it as a learning problem on the BatchNorm parameters of a simulation-trained model. Specifically, we propose a novel non-parametric entropy objective, which formulates the learning objective for the test-time adaptation in an open-world manner. Then, a cross-modality knowledge distillation objective is further designed to encourage the test-time knowledge transfer for feature enhancement. Our approach can be efficiently implemented with only test images, without requiring annotations or revisiting the large-scale synthetic training data. Besides significant time savings, the proposed method consistently improves segmentation results on the overlap and boundary metrics, achieving state-of-the-art performance on unseen object instance segmentation.

Fu Feng, Jing Wang, Xu Yang et al.

The genes in nature give the lives on earth the current biological intelligence through transmission and accumulation over billions of years. Inspired by the biological intelligence, artificial intelligence (AI) has devoted to building the machine intelligence. Although it has achieved thriving successes, the machine intelligence still lags far behind the biological intelligence. The reason may lie in that animals are born with some intelligence encoded in their genes, but machines lack such intelligence and learn from scratch. Inspired by the genes of animals, we define the ``genes'' of machines named as the ``learngenes'' and propose the Genetic Reinforcement Learning (GRL). GRL is a computational framework that simulates the evolution of organisms in reinforcement learning (RL) and leverages the learngenes to learn and evolve the intelligence agents. Leveraging GRL, we first show that the learngenes take the form of the fragments of the agents' neural networks and can be inherited across generations. Second, we validate that the learngenes can transfer ancestral experience to the agents and bring them instincts and strong learning abilities. Third, we justify the Lamarckian inheritance of the intelligent agents and the continuous evolution of the learngenes. Overall, the learngenes have taken the machine intelligence one more step toward the biological intelligence.

Hao Zhou, Tiancheng Shen, Xu Yang et al.

In this paper, we highlight a problem of evaluation metrics adopted in the open-vocabulary segmentation. That is, the evaluation process still heavily relies on closed-set metrics on zero-shot or cross-dataset pipelines without considering the similarity between predicted and ground truth categories. To tackle this issue, we first survey eleven similarity measurements between two categorical words using WordNet linguistics statistics, text embedding, and language models by comprehensive quantitative analysis and user study. Built upon those explored measurements, we designed novel evaluation metrics, namely Open mIoU, Open AP, and Open PQ, tailored for three open-vocabulary segmentation tasks. We benchmarked the proposed evaluation metrics on 12 open-vocabulary methods of three segmentation tasks. Even though the relative subjectivity of similarity distance, we demonstrate that our metrics can still well evaluate the open ability of the existing open-vocabulary segmentation methods. We hope that our work can bring with the community new thinking about how to evaluate the open ability of models. The evaluation code is released in github.

Wei-Dong Qiao, Yang Xu, Hui Li

The weight-sharing mechanism of convolutional kernels ensures translation-equivariance of convolution neural networks (CNNs). Recently, rotation-equivariance has been investigated. However, research on scale-equivariance or simultaneous scale-rotation-equivariance is insufficient. This study proposes a Lie group-CNN, which can keep scale-rotation-equivariance for image classification tasks. The Lie group-CNN includes a lifting module, a series of group convolution modules, a global pooling layer, and a classification layer. The lifting module transfers the input image from Euclidean space to Lie group space, and the group convolution is parameterized through a fully connected network using Lie-algebra of Lie-group elements as inputs to achieve scale-rotation-equivariance. The Lie group SIM(2) is utilized to establish the Lie group-CNN with scale-rotation-equivariance. Scale-rotation-equivariance of Lie group-CNN is verified and achieves the best recognition accuracy on the blood cell dataset (97.50%) and the HAM10000 dataset (77.90%) superior to Lie algebra convolution network, dilation convolution, spatial transformer network, and scale-equivariant steerable network. In addition, the generalization ability of the Lie group-CNN on SIM(2) on rotation-equivariance is verified on rotated-MNIST and rotated-CIFAR10, and the robustness of the network is verified on SO(2) and SE(2). Therefore, the Lie group-CNN can successfully extract geometric features and performs equivariant recognition on images with rotation and scale transformations.

Lei Yu, Yang Xu

Humans often make creative use of words to express novel senses. A long-standing effort in natural language processing has been focusing on word sense disambiguation (WSD), but little has been explored about how the sense inventory of a word may be extended toward novel meanings. We present a paradigm of word sense extension (WSE) that enables words to spawn new senses toward novel context. We develop a framework that simulates novel word sense extension by first partitioning a polysemous word type into two pseudo-tokens that mark its different senses, and then inferring whether the meaning of a pseudo-token can be extended to convey the sense denoted by the token partitioned from the same word type. Our framework combines cognitive models of chaining with a learning scheme that transforms a language model embedding space to support various types of word sense extension. We evaluate our framework against several competitive baselines and show that it is superior in predicting plausible novel senses for over 7,500 English words. Furthermore, we show that our WSE framework improves performance over a range of transformer-based WSD models in predicting rare word senses with few or zero mentions in the training data.

Ze Mao, Yang Xu, Erick Suarez

The quality of the data in a dataset can have a substantial impact on the performance of a machine learning model that is trained and/or evaluated using the dataset. Effective dataset management, including tasks such as data cleanup, versioning, access control, dataset transformation, automation, integrity and security, etc., can help improve the efficiency and speed of the machine learning process. Currently, engineers spend a substantial amount of manual effort and time to manage dataset versions or to prepare datasets for machine learning tasks. This disclosure describes a platform to manage and use datasets effectively. The techniques integrate dataset management and dataset transformation mechanisms. A storage engine is described that acts as a source of truth for all data and handles versioning, access control etc. The dataset transformation mechanism is a key part to generate a dataset (snapshot) to serve different purposes. The described techniques can support different workflows, pipelines, or data orchestration needs, e.g., for training and/or evaluation of machine learning models.

Yudong Li, Yunlin Lei, Xu Yang

Spiking neural networks (SNNs) have made great progress on both performance and efficiency over the last few years,but their unique working pattern makes it hard to train a high-performance low-latency SNN.Thus the development of SNNs still lags behind traditional artificial neural networks (ANNs).To compensate this gap,many extraordinary works have been proposed.Nevertheless,these works are mainly based on the same kind of network structure (i.e.CNN) and their performance is worse than their ANN counterparts,which limits the applications of SNNs.To this end,we propose a novel Transformer-based SNN,termed "Spikeformer",which outperforms its ANN counterpart on both static dataset and neuromorphic dataset and may be an alternative architecture to CNN for training high-performance SNNs.First,to deal with the problem of "data hungry" and the unstable training period exhibited in the vanilla model,we design the Convolutional Tokenizer (CT) module,which improves the accuracy of the original model on DVS-Gesture by more than 16%.Besides,in order to better incorporate the attention mechanism inside Transformer and the spatio-temporal information inherent to SNN,we adopt spatio-temporal attention (STA) instead of spatial-wise or temporal-wise attention.With our proposed method,we achieve competitive or state-of-the-art (SOTA) SNN performance on DVS-CIFAR10,DVS-Gesture,and ImageNet datasets with the least simulation time steps (i.e.low latency).Remarkably,our Spikeformer outperforms other SNNs on ImageNet by a large margin (i.e.more than 5%) and even outperforms its ANN counterpart by 3.1% and 2.2% on DVS-Gesture and ImageNet respectively,indicating that Spikeformer is a promising architecture for training large-scale SNNs and may be more suitable for SNNs compared to CNN.We believe that this work shall keep the development of SNNs in step with ANNs as much as possible.Code will be available.

Zihao Lin, Jinrong Li, Fan Yang et al.

Offline Handwritten Mathematical Expression Recognition (HMER) has been dramatically advanced recently by employing tree decoders as part of the encoder-decoder method. Despite the tree decoder-based methods regard the expressions as a tree and parse 2D spatial structure to the tree nodes sequence, the performance of existing works is still poor due to the inevitable tree nodes prediction errors. Besides, they lack syntax rules to regulate the output of expressions. In this paper, we propose a novel model called Spatial Attention and Syntax Rule Enhanced Tree Decoder (SS-TD), which is equipped with spatial attention mechanism to alleviate the prediction error of tree structure and use syntax masks (obtained from the transformation of syntax rules) to constrain the occurrence of ungrammatical mathematical expression. In this way, our model can effectively describe tree structure and increase the accuracy of output expression. Experiments show that SS-TD achieves better recognition performance than prior models on CROHME 14/16/19 datasets, demonstrating the effectiveness of our model.

Chunhui Ai, Derui Wang, Xu Yan et al.

With so many articles of varying qualities being produced every moment, it is a very urgent task to screen outstanding articles and commit them to social media. To our best knowledge, there is a lack of datasets and mature research works in identifying high-quality articles. Consequently, we conduct some surveys and finalize 7 objective indicators to annotate the quality of 10k articles. During annotation, we find that many characteristics of high-quality articles (e.g., background) rely more on extensive external knowledge than inner semantic information of articles. In response, we link extracted article entities to Baidu Encyclopedia, then propose Knowledge Enhanced article Quality Identification (KE-QI) dataset. To make better use of external knowledge, we propose a compound model which fuses the text and external knowledge information via a gate unit to classify the quality of an article. Our experimental results on KE-QI show that with initialization of our pre-trained Node2Vec model, our model achieves about 78\% $F_1$, outperforming other baselines.

Xinyao Shu, Shiyang Yan, Xu Yang et al.

Visual question answering (VQA) is a critical multimodal task in which an agent must answer questions according to the visual cue. Unfortunately, language bias is a common problem in VQA, which refers to the model generating answers only by associating with the questions while ignoring the visual content, resulting in biased results. We tackle the language bias problem by proposing a self-supervised counterfactual metric learning (SC-ML) method to focus the image features better. SC-ML can adaptively select the question-relevant visual features to answer the question, reducing the negative influence of question-irrelevant visual features on inferring answers. In addition, question-irrelevant visual features can be seamlessly incorporated into counterfactual training schemes to further boost robustness. Extensive experiments have proved the effectiveness of our method with improved results on the VQA-CP dataset. Our code will be made publicly available.

Yuchu Jiang, Jiale Fu, Chenduo Hao et al.

Recently, In-context Learning (ICL) has become a significant inference paradigm in Large Multimodal Models (LMMs), utilizing a few in-context demonstrations (ICDs) to prompt LMMs for new tasks. However, the synergistic effects in multimodal data increase the sensitivity of ICL performance to the configurations of ICDs, stimulating the need for a more stable and general mapping function. Mathematically, in Transformer-based models, ICDs act as "shift vectors" added to the hidden states of query tokens. Inspired by this, we introduce Mimic In-Context Learning (MimIC) to learn stable and generalizable shift effects from ICDs. Specifically, compared with some previous shift vector-based methods, MimIC more strictly approximates the shift effects by integrating lightweight learnable modules into LMMs with four key enhancements: 1) inserting shift vectors after attention layers, 2) assigning a shift vector to each attention head, 3) making shift magnitude query-dependent, and 4) employing a layer-wise alignment loss. Extensive experiments on two LMMs (Idefics-9b and Idefics2-8b-base) across three multimodal tasks (VQAv2, OK-VQA, Captioning) demonstrate that MimIC outperforms existing shift vector-based methods. The code is available at https://github.com/Kamichanw/MimIC.

Jiale Fu, Yuchu Jiang, Junkai Chen et al.

Large Language Model (LLM) collaborative decoding techniques improve output quality by combining the outputs of multiple models at each generation step, but they incur high computational costs. In this paper, we introduce Collaborative decoding via Speculation (CoS), a novel framework that accelerates collaborative decoding without compromising performance. Inspired by Speculative Decoding--where a small proposal model generates tokens sequentially, and a larger target model verifies them in parallel, our approach builds on two key insights: (1) the verification distribution can be the combined distribution of both the proposal and target models, and (2) alternating each model as the proposer and verifier can further enhance efficiency. We generalize this method to collaboration among n models and theoretically prove that CoS is never slower than standard collaborative decoding, typically achieving faster speed. Extensive experiments demonstrate CoS is 1.11x-2.23x faster than standard collaborative decoding without compromising generation quality. Our code is available at https://github.com/Kamichanw/CoS/.

Xu Yang, Yongliang Wu, Mingzhuo Yang et al.

After discovering that Language Models (LMs) can be good in-context few-shot learners, numerous strategies have been proposed to optimize in-context sequence configurations. Recently, researchers in Vision-Language (VL) domains also develop their few-shot learners, while they only use the simplest way, ie., randomly sampling, to configure in-context image-text pairs. In order to explore the effects of varying configurations on VL in-context learning, we devised four strategies for image selection and four for caption assignment to configure in-context image-text pairs for image captioning. Here Image Captioning is used as the case study since it can be seen as the visually-conditioned LM. Our comprehensive experiments yield two counter-intuitive but valuable insights, highlighting the distinct characteristics of VL in-context learning due to multi-modal synergy, as compared to the NLP case. Furthermore, in our exploration of optimal combination strategies, we observed an average performance enhancement of 20.9 of CIDEr scores compared to the baseline. The code is given in https://github.com/yongliang-wu/ExploreCfg.

Zixuan Cao, Yang Xu, Zhewei Huang et al.

The Machine Learning for Combinatorial Optimization (ML4CO) NeurIPS 2021 competition aims to improve state-of-the-art combinatorial optimization solvers by replacing key heuristic components with machine learning models. On the dual task, we design models to make branching decisions to promote the dual bound increase faster. We propose a knowledge inheritance method to generalize knowledge of different models from the dataset aggregation process, named KIDA. Our improvement overcomes some defects of the baseline graph-neural-networks-based methods. Further, we won the $1$\textsuperscript{st} Place on the dual task. We hope this report can provide useful experience for developers and researchers. The code is available at https://github.com/megvii-research/NeurIPS2021-ML4CO-KIDA.

Boyu Zhang, Jiayuan Chen, Yinfei Xu et al.

The action quality assessment (AQA) of videos is a challenging vision task since the relation between videos and action scores is difficult to model. Thus, AQA has been widely studied in the literature. Traditionally, AQA is treated as a regression problem to learn the underlying mappings between videos and action scores. But previous methods ignored data uncertainty in AQA dataset. To address aleatoric uncertainty, we further develop a plug-and-play module Distribution Auto-Encoder (DAE). Specifically, it encodes videos into distributions and uses the reparameterization trick in variational auto-encoders (VAE) to sample scores, which establishes a more accurate mapping between videos and scores. Meanwhile, a likelihood loss is used to learn the uncertainty parameters. We plug our DAE approach into MUSDL and CoRe. Experimental results on public datasets demonstrate that our method achieves state-of-the-art on AQA-7, MTL-AQA, and JIGSAWS datasets. Our code is available at https://github.com/InfoX-SEU/DAE-AQA.

Xu Yang, Changxing Ding, Zhibin Hong et al.

Image-based virtual try-on is an increasingly important task for online shopping. It aims to synthesize images of a specific person wearing a specified garment. Diffusion model-based approaches have recently become popular, as they are excellent at image synthesis tasks. However, these approaches usually employ additional image encoders and rely on the cross-attention mechanism for texture transfer from the garment to the person image, which affects the try-on's efficiency and fidelity. To address these issues, we propose an Texture-Preserving Diffusion (TPD) model for virtual try-on, which enhances the fidelity of the results and introduces no additional image encoders. Accordingly, we make contributions from two aspects. First, we propose to concatenate the masked person and reference garment images along the spatial dimension and utilize the resulting image as the input for the diffusion model's denoising UNet. This enables the original self-attention layers contained in the diffusion model to achieve efficient and accurate texture transfer. Second, we propose a novel diffusion-based method that predicts a precise inpainting mask based on the person and reference garment images, further enhancing the reliability of the try-on results. In addition, we integrate mask prediction and image synthesis into a single compact model. The experimental results show that our approach can be applied to various try-on tasks, e.g., garment-to-person and person-to-person try-ons, and significantly outperforms state-of-the-art methods on popular VITON, VITON-HD databases.

Shuai Yuan, Shuang Chen, Tianwu Lin et al.

Accurate remote sensing geographic mapping requires timely and representative samples. However, rapid land surface changes often render static samples obsolete within months, making manual sample updates labor-intensive and unsustainable. To address this challenge, we propose TasGen, a two-stage Temporal spectral-aware Automatic Sample Generation method for generating dynamic training samples from single-date static labels without human intervention. Land surface dynamics often manifest as anomalies in temporal-spectral sequences. %These anomalies are multivariate yet unified: temporal, spectral, or joint anomalies stem from different mechanisms and cannot be naively coupled, as this may obscure the nature of changes. Yet, any land surface state corresponds to a coherent temporal-spectral signature, which would be lost if the two dimensions are modeled separately. To effectively capture these dynamics, TasGen first disentangles temporal and spectral features to isolate their individual contributions, and then couples them to model their synergistic interactions. In the first stage, we introduce a hierarchical temporal-spectral variational autoencoder (HTS-VAE) with a dual-dimension embedding to learn low-dimensional latent patterns of normal samples by first disentangling and then jointly embedding temporal and spectral information. This temporal-spectral embedding enables robust anomaly detection by identifying deviations from learned joint patterns. In the second stage, a classifier trained on stable samples relabels change points across time to generate dynamic samples. To not only detect but also explain surface dynamics, we further propose an anomaly interpretation method based on Gibbs sampling, which attributes changes to specific spectral-temporal dimensions.

Xu Yang, Rui Wang, Kaiwen Li et al.

Differential evolution (DE) algorithm is recognized as one of the most effective evolutionary algorithms, demonstrating remarkable efficacy in black-box optimization due to its derivative-free nature. Numerous enhancements to the fundamental DE have been proposed, incorporating innovative mutation strategies and sophisticated parameter tuning techniques to improve performance. However, no single variant has proven universally superior across all problems. To address this challenge, we introduce a novel framework that employs reinforcement learning (RL) to automatically design DE for black-box optimization through meta-learning. RL acts as an advanced meta-optimizer, generating a customized DE configuration that includes an optimal initialization strategy, update rule, and hyperparameters tailored to a specific black-box optimization problem. This process is informed by a detailed analysis of the problem characteristics. In this proof-of-concept study, we utilize a double deep Q-network for implementation, considering a subset of 40 possible strategy combinations and parameter optimizations simultaneously. The framework's performance is evaluated against black-box optimization benchmarks and compared with state-of-the-art algorithms. The experimental results highlight the promising potential of our proposed framework.

Yang Xu, Ronghao Zheng, Senlin Zhang et al.

This paper mainly studies the localization and mapping of range sensing robots in the confidence-rich map (CRM) and then extends it to provide a full state estimate for information-theoretic exploration. Most previous works about active simultaneous localization and mapping and exploration always assumed the known robot poses or utilized inaccurate information metrics to approximate pose uncertainty, resulting in imbalanced exploration performance and efficiency in the unknown environment. This inspires us to extend the confidence-rich mutual information (CRMI) with measurable pose uncertainty. Specifically, we propose a Rao-Blackwellized particle filter-based localization and mapping scheme (RBPF-CLAM) for CRM, then we develop a new closed-form weighting method to improve the localization accuracy without scan matching. We further derive the uncertain CRMI (UCRMI) with the weighted particles by a more accurate approximation. Simulations and experimental evaluations show the localization accuracy and exploration performance of the proposed methods.

Xinyu Li, Yang Xu, Xiaohu Zhang et al.

As an important task for the management of bike sharing systems, accurate forecast of travel demand could facilitate dispatch and relocation of bicycles to improve user satisfaction. In recent years, many deep learning algorithms have been introduced to improve bicycle usage forecast. A typical practice is to integrate convolutional (CNN) and recurrent neural network (RNN) to capture spatial-temporal dependency in historical travel demand. For typical CNN, the convolution operation is conducted through a kernel that moves across a "matrix-format" city to extract features over spatially adjacent urban areas. This practice assumes that areas close to each other could provide useful information that improves prediction accuracy. However, bicycle usage in neighboring areas might not always be similar, given spatial variations in built environment characteristics and travel behavior that affect cycling activities. Yet, areas that are far apart can be relatively more similar in temporal usage patterns. To utilize the hidden linkage among these distant urban areas, the study proposes an irregular convolutional Long-Short Term Memory model (IrConv+LSTM) to improve short-term bike sharing demand forecast. The model modifies traditional CNN with irregular convolutional architecture to extract dependency among "semantic neighbors". The proposed model is evaluated with a set of benchmark models in five study sites, which include one dockless bike sharing system in Singapore, and four station-based systems in Chicago, Washington, D.C., New York, and London. We find that IrConv+LSTM outperforms other benchmark models in the five cities. The model also achieves superior performance in areas with varying levels of bicycle usage and during peak periods. The findings suggest that "thinking beyond spatial neighbors" can further improve short-term travel demand prediction of urban bike sharing systems.

Xiaoteng Zhou, Changli Yu, Xin Yuan et al.

In the field of deep-sea exploration, sonar is presently the only efficient long-distance sensing device. The complicated underwater environment, such as noise interference, low target intensity or background dynamics, has brought many negative effects on sonar imaging. Among them, the problem of nonlinear intensity is extremely prevalent. It is also known as the anisotropy of acoustic sensor imaging, that is, when autonomous underwater vehicles (AUVs) carry sonar to detect the same target from different angles, the intensity variation between image pairs is sometimes very large, which makes the traditional matching algorithm almost ineffective. However, image matching is the basis of comprehensive tasks such as navigation, positioning, and mapping. Therefore, it is very valuable to obtain robust and accurate matching results. This paper proposes a combined matching method based on phase information and deep convolution features. It has two outstanding advantages: one is that the deep convolution features could be used to measure the similarity of the local and global positions of the sonar image; the other is that local feature matching could be performed at the key target position of the sonar image. This method does not need complex manual designs, and completes the matching task of nonlinear intensity sonar images in a close end-to-end manner. Feature matching experiments are carried out on the deep-sea sonar images captured by AUVs, and the results show that our proposal has preeminent matching accuracy and robustness.

Ruofei Bai, Ronghao Zheng, Yang Xu et al.

This paper presents a hierarchical framework to solve the multi-robot temporal task planning problem. We assume that each robot has its individual task specification and the robots have to jointly satisfy a global collaborative task specification, both described in linear temporal logic. Specifically, a central server firstly extracts and decomposes a collaborative task sequence from the automaton corresponding to the collaborative task specification, and allocates the subtasks in the sequence to robots. The robots can then synthesize their initial execution strategies based on locally constructed product automatons, combining the assigned collaborative tasks and their individual task specifications. Furthermore, we propose a distributed execution strategy adjusting mechanism to iteratively improve the time efficiency, by reducing wait time in collaborations caused by potential synchronization constraints. We prove the completeness of the proposed framework under assumptions, and analyze its time complexity and optimality. Extensive simulation results verify the scalability and optimization efficiency of the proposed method.

Yang Xu, Ronghao Zheng, Senlin Zhang et al.

This article focuses on feature-based underwater localization and navigation for autonomous underwater vehicles (AUVs) using 2D imaging sonar measurements. The sparsity of underwater acoustic features and the loss of elevation angle in sonar images may introduce wrong feature matches or insufficient features for optimization-based underwater localization (i.e. under-constrained/degeneracy cases). This motivates us to propose a novel inertial-aided sliding window optimization framework to improve the estimation accuracy and the robustness to front-end outliers. Concretely, we first discriminate under-constrained/ well-constrained sonar frames and define sonar keyframes (SKFs) based on the Jacobian matrix derived from odometry and sonar measurements. To utilize the past well-constrained SKFs mostly, we design a size-adjustable windowed back-end optimization scheme based on singular values. We also prove that the landmark triangulation failure (navigation problem) caused by sonar motion can be solved in 2D scenes. Comparative simulation and evaluation on a public dataset show the proposed method outperforms the existing ones in pose estimation and robustness even without loop closure and also ensures the real-time performance for online applications.

Wenliang Qian, Yang Xu, Wangmeng Zuo et al.

Generative Adversarial Networks (GANs) are an unsupervised generative model that learns data distribution through adversarial training. However, recent experiments indicated that GANs are difficult to train due to the requirement of optimization in the high dimensional parameter space and the zero gradient problem. In this work, we propose a Self Sparse Generative Adversarial Network (Self-Sparse GAN) that reduces the parameter space and alleviates the zero gradient problem. In the Self-Sparse GAN, we design a Self-Adaptive Sparse Transform Module (SASTM) comprising the sparsity decomposition and feature-map recombination, which can be applied on multi-channel feature maps to obtain sparse feature maps. The key idea of Self-Sparse GAN is to add the SASTM following every deconvolution layer in the generator, which can adaptively reduce the parameter space by utilizing the sparsity in multi-channel feature maps. We theoretically prove that the SASTM can not only reduce the search space of the convolution kernel weight of the generator but also alleviate the zero gradient problem by maintaining meaningful features in the Batch Normalization layer and driving the weight of deconvolution layers away from being negative. The experimental results show that our method achieves the best FID scores for image generation compared with WGAN-GP on MNIST, Fashion-MNIST, CIFAR-10, STL-10, mini-ImageNet, CELEBA-HQ, and LSUN bedrooms, and the relative decrease of FID is 4.76% ~ 21.84%.