Ke Wang

Mingzhe Guo, Zhipeng Zhang, Liping Jing et al.

We propose a unified object-aware temporal learning framework for multi-view 3D detection and tracking tasks. Having observed that the efficacy of the temporal fusion strategy in recent multi-view perception methods may be weakened by distractors and background clutters in historical frames, we propose a cyclic learning mechanism to improve the robustness of multi-view representation learning. The essence is constructing a backward bridge to propagate information from model predictions (e.g., object locations and sizes) to image and BEV features, which forms a circle with regular inference. After backward refinement, the responses of target-irrelevant regions in historical frames would be suppressed, decreasing the risk of polluting future frames and improving the object awareness ability of temporal fusion. We further tailor an object-aware association strategy for tracking based on the cyclic learning model. The cyclic learning model not only provides refined features, but also delivers finer clues (e.g., scale level) for tracklet association. The proposed cycle learning method and association module together contribute a novel and unified multi-task framework. Experiments on nuScenes show that the proposed model achieves consistent performance gains over baselines of different designs (i.e., dense query-based BEVFormer, sparse query-based SparseBEV and LSS-based BEVDet4D) on both detection and tracking evaluation.

Zimao Lu, Hui Xu, Bing Liu et al.

Text-only training provides an attractive approach to address data scarcity challenges in zero-shot image captioning (ZIC), avoiding the expense of collecting paired image-text annotations. However, although these approaches perform well within training domains, they suffer from poor cross-domain generalization, often producing hallucinated content when encountering novel visual environments. Retrieval-based methods attempt to mitigate this limitation by leveraging external knowledge, but they can paradoxically exacerbate hallucination when retrieved captions contain entities irrelevant to the inputs. We introduce the concept of negative entities--objects that appear in generated caption but are absent from the input--and propose Negative Entity Suppression (NES) to tackle this challenge. NES seamlessly integrates three stages: (1) it employs synthetic images to ensure consistent image-to-text retrieval across both training and inference; (2) it filters negative entities from retrieved content to enhance accuracy; and (3) it applies attention-level suppression using identified negative entities to further minimize the impact of hallucination-prone features. Evaluation across multiple benchmarks demonstrates that NES maintains competitive in-domain performance while improving cross-domain transfer and reducing hallucination rates, achieving new state-of-the-art results in ZIC. Our code is available at https://github.com/nidongpinyinme/NESCap.

Ke Wang, Sai Ma, Junlan Chen et al.

Recently, the philosophy of visual saliency and attention has started to gain popularity in the robotics community. Therefore, this paper aims to mimic this mechanism in SLAM framework by using saliency prediction model. Comparing with traditional SLAM that treated all feature points as equal important in optimization process, we think that the salient feature points should play more important role in optimization process. Therefore, we proposed a saliency model to predict the saliency map, which can capture both scene semantic and geometric information. Then, we proposed Salient Bundle Adjustment by using the value of saliency map as the weight of the feature points in traditional Bundle Adjustment approach. Exhaustive experiments conducted with the state-of-the-art algorithm in KITTI and EuRoc datasets show that our proposed algorithm outperforms existing algorithms in both indoor and outdoor environments. Finally, we will make our saliency dataset and relevant source code open-source for enabling future research.

Zhongliang Yang, Ke Wang, Sai Ma et al.

In order to promote the rapid development of image steganalysis technology, in this paper, we construct and release a multivariable large-scale image steganalysis dataset called IStego100K. It contains 208,104 images with the same size of 1024*1024. Among them, 200,000 images (100,000 cover-stego image pairs) are divided as the training set and the remaining 8,104 as testing set. In addition, we hope that IStego100K can help researchers further explore the development of universal image steganalysis algorithms, so we try to reduce limits on the images in IStego100K. For each image in IStego100K, the quality factors is randomly set in the range of 75-95, the steganographic algorithm is randomly selected from three well-known steganographic algorithms, which are J-uniward, nsF5 and UERD, and the embedding rate is also randomly set to be a value of 0.1-0.4. In addition, considering the possible mismatch between training samples and test samples in real environment, we add a test set (DS-Test) whose source of samples are different from the training set. We hope that this test set can help to evaluate the robustness of steganalysis algorithms. We tested the performance of some latest steganalysis algorithms on IStego100K, with specific results and analysis details in the experimental part. We hope that the IStego100K dataset will further promote the development of universal image steganalysis technology. The description of IStego100K and instructions for use can be found at https://github.com/YangzlTHU/IStego100K

Junlan Chen, Ke Wang, Huanhuan Bao et al.

Cooperative overtaking is believed to have the capability of improving road safety and traffic efficiency by means of the real-time information exchange between traffic participants, including road infrastructures, nearby vehicles and others. In this paper, we focused on the critical issues of modeling, computation, and analysis of cooperative overtaking and made it playing a key role in the road overtaking area. In detail, for the purpose of extending the awareness of the surrounding environment, the lane markings in front of ego vehicle were detected and modeled with Bezier curve using an onboard camera. While the nearby vehicle positions were obtained through the vehicle-to-vehicle communication scheme making assure of the accuracy of localization. Then, Gaussian-based conflict potential field was proposed to guarantee the overtaking safety, which can quantitatively estimate the oncoming collision danger. To support the proposed method, many experiments were conducted on the human-in-the-loop simulation platform. The results demonstrated that our proposed method achieves better performance, especially in some unpredictable nature road circumstances.

Ke Wang, Siyuan Zhang, Junlan Chen et al.

The adverse haze weather condition has brought considerable difficulties in vision-based environmental applications. While, until now, most of the existing environmental monitoring studies are under ordinary conditions, and the studies of complex haze weather conditions have been ignored. Thence, this paper proposes a feature-supervised learning network based on generative adversarial networks (GAN) for environmental monitoring during hazy days. Its main idea is to train the model under the supervision of feature maps from the ground truth. Four key technical contributions are made in the paper. First, pairs of hazy and clean images are used as inputs to supervise the encoding process and obtain high-quality feature maps. Second, the basic GAN formulation is modified by introducing perception loss, style loss, and feature regularization loss to generate better results. Third, multi-scale images are applied as the input to enhance the performance of discriminator. Finally, a hazy remote sensing dataset is created for testing our dehazing method and environmental detection. Extensive experimental results show that the proposed method has achieved better performance than current state-of-the-art methods on both synthetic datasets and real-world remote sensing images.

Ke Wang, Gang Li, Junlan Chen et al.

China is the world's largest automotive market and is ambitious for autonomous vehicles (AVs) development. As one of the key goals of AVs, pedestrian safety is an important issue in China. Despite the rapid development of driverless technologies in recent years, there is a lack of researches on the adaptability of AVs to pedestrians. To fill the gap, this study would discuss the adaptability of current driverless technologies to China urban pedestrians by reviewing the latest researches. The paper firstly analyzed typical Chinese pedestrian behaviors and summarized the safety demands of pedestrians for AVs through articles and open database data, which are worked as the evaluation criteria. Then, corresponding driverless technologies are carefully reviewed. Finally, the adaptability would be given combining the above analyses. Our review found that autonomous vehicles have trouble in the occluded pedestrian environment and Chinese pedestrians do not accept AVs well. And more explorations should be conducted on standard human-machine interaction, interaction information overload avoidance, occluded pedestrians detection and nation-based receptivity research. The conclusions are very useful for motor corporations and driverless car researchers to place more attention on the complexity of the Chinese pedestrian environment, for transportation experts to protect pedestrian safety in the context of AVs, and for governors to think about making new pedestrians policies to welcome the upcoming driverless cars.

Zhenyuan Ning, Ke Wang, Shengzhou Zhong et al.

Breast ultrasound (BUS) image segmentation plays a crucial role in a computer-aided diagnosis system, which is regarded as a useful tool to help increase the accuracy of breast cancer diagnosis. Recently, many deep learning methods have been developed for segmentation of BUS image and show some advantages compared with conventional region-, model-, and traditional learning-based methods. However, previous deep learning methods typically use skip-connection to concatenate the encoder and decoder, which might not make full fusion of coarse-to-fine features from encoder and decoder. Since the structure and edge of lesion in BUS image are common blurred, these would make it difficult to learn the discriminant information of structure and edge, and reduce the performance. To this end, we propose and evaluate a coarse-to-fine fusion convolutional network (CF2-Net) based on a novel feature integration strategy (forming an 'E'-like type) for BUS image segmentation. To enhance contour and provide structural information, we concatenate a super-pixel image and the original image as the input of CF2-Net. Meanwhile, to highlight the differences in the lesion regions with variable sizes and relieve the imbalance issue, we further design a weighted-balanced loss function to train the CF2-Net effectively. The proposed CF2-Net was evaluated on an open dataset by using four-fold cross validation. The results of the experiment demonstrate that the CF2-Net obtains state-of-the-art performance when compared with other deep learning-based methods

Ke Wang, Kaixuan Wang, Shaojie Shen

Many approaches have been proposed to estimate camera poses by directly minimizing photometric error. However, due to the non-convex property of direct alignment, proper initialization is still required for these methods. Many robust norms (e.g. Huber norm) have been proposed to deal with the outlier terms caused by incorrect initializations. These robust norms are solely defined on the magnitude of each error term. In this paper, we propose a novel robust norm, named FlowNorm, that exploits the information from both the local error term and the global image registration information. While the local information is defined on patch alignments, the global information is estimated using a learning-based network. Using both the local and global information, we achieve an unprecedented convergence range in which images can be aligned given large view angle changes or small overlaps. We further demonstrate the usability of the proposed robust norm by integrating it into the direct methods DSO and BA-Net, and generate more robust and accurate results in real-time.

Andrey Ignatov, Radu Timofte, Andrei Kulik et al.

The performance of mobile AI accelerators has been evolving rapidly in the past two years, nearly doubling with each new generation of SoCs. The current 4th generation of mobile NPUs is already approaching the results of CUDA-compatible Nvidia graphics cards presented not long ago, which together with the increased capabilities of mobile deep learning frameworks makes it possible to run complex and deep AI models on mobile devices. In this paper, we evaluate the performance and compare the results of all chipsets from Qualcomm, HiSilicon, Samsung, MediaTek and Unisoc that are providing hardware acceleration for AI inference. We also discuss the recent changes in the Android ML pipeline and provide an overview of the deployment of deep learning models on mobile devices. All numerical results provided in this paper can be found and are regularly updated on the official project website: http://ai-benchmark.com.

Andrey Ignatov, Radu Timofte, William Chou et al.

Over the last years, the computational power of mobile devices such as smartphones and tablets has grown dramatically, reaching the level of desktop computers available not long ago. While standard smartphone apps are no longer a problem for them, there is still a group of tasks that can easily challenge even high-end devices, namely running artificial intelligence algorithms. In this paper, we present a study of the current state of deep learning in the Android ecosystem and describe available frameworks, programming models and the limitations of running AI on smartphones. We give an overview of the hardware acceleration resources available on four main mobile chipset platforms: Qualcomm, HiSilicon, MediaTek and Samsung. Additionally, we present the real-world performance results of different mobile SoCs collected with AI Benchmark that are covering all main existing hardware configurations.

Ke Wang, Junbo Zhang, Sining Sun et al.

We investigate the use of generative adversarial networks (GANs) in speech dereverberation for robust speech recognition. GANs have been recently studied for speech enhancement to remove additive noises, but there still lacks of a work to examine their ability in speech dereverberation and the advantages of using GANs have not been fully established. In this paper, we provide deep investigations in the use of GAN-based dereverberation front-end in ASR. First, we study the effectiveness of different dereverberation networks (the generator in GAN) and find that LSTM leads a significant improvement as compared with feed-forward DNN and CNN in our dataset. Second, further adding residual connections in the deep LSTMs can boost the performance as well. Finally, we find that, for the success of GAN, it is important to update the generator and the discriminator using the same mini-batch data during training. Moreover, using reverberant spectrogram as a condition to discriminator, as suggested in previous studies, may degrade the performance. In summary, our GAN-based dereverberation front-end achieves 14%-19% relative CER reduction as compared to the baseline DNN dereverberation network when tested on a strong multi-condition training acoustic model.

Lovedeep Gondara, Ke Wang

Missing data is a significant problem impacting all domains. State-of-the-art framework for minimizing missing data bias is multiple imputation, for which the choice of an imputation model remains nontrivial. We propose a multiple imputation model based on overcomplete deep denoising autoencoders. Our proposed model is capable of handling different data types, missingness patterns, missingness proportions and distributions. Evaluation on several real life datasets show our proposed model significantly outperforms current state-of-the-art methods under varying conditions while simultaneously improving end of the line analytics.