Xu Liu

Yuting Yang, Licheng Jiao, Xu Liu et al.

Dynamic attention mechanism and global modeling ability make Transformer show strong feature learning ability. In recent years, Transformer has become comparable to CNNs methods in computer vision. This review mainly investigates the current research progress of Transformer in image and video applications, which makes a comprehensive overview of Transformer in visual learning understanding. First, the attention mechanism is reviewed, which plays an essential part in Transformer. And then, the visual Transformer model and the principle of each module are introduced. Thirdly, the existing Transformer-based models are investigated, and their performance is compared in visual learning understanding applications. Three image tasks and two video tasks of computer vision are investigated. The former mainly includes image classification, object detection, and image segmentation. The latter contains object tracking and video classification. It is significant for comparing different models' performance in various tasks on several public benchmark data sets. Finally, ten general problems are summarized, and the developing prospects of the visual Transformer are given in this review.

Yanbiao Ma, Licheng Jiao, Fang Liu et al.

Model bias triggered by long-tailed data has been widely studied. However, measure based on the number of samples cannot explicate three phenomena simultaneously: (1) Given enough data, the classification performance gain is marginal with additional samples. (2) Classification performance decays precipitously as the number of training samples decreases when there is insufficient data. (3) Model trained on sample-balanced datasets still has different biases for different classes. In this work, we define and quantify the semantic scale of classes, which is used to measure the feature diversity of classes. It is exciting to find experimentally that there is a marginal effect of semantic scale, which perfectly describes the first two phenomena. Further, the quantitative measurement of semantic scale imbalance is proposed, which can accurately reflect model bias on multiple datasets, even on sample-balanced data, revealing a novel perspective for the study of class imbalance. Due to the prevalence of semantic scale imbalance, we propose semantic-scale-balanced learning, including a general loss improvement scheme and a dynamic re-weighting training framework that overcomes the challenge of calculating semantic scales in real-time during iterations. Comprehensive experiments show that dynamic semantic-scale-balanced learning consistently enables the model to perform superiorly on large-scale long-tailed and non-long-tailed natural and medical datasets, which is a good starting point for mitigating the prevalent but unnoticed model bias.

Yutong Xia, Yuxuan Liang, Haomin Wen et al.

Spatio-Temporal Graph (STG) forecasting is a fundamental task in many real-world applications. Spatio-Temporal Graph Neural Networks have emerged as the most popular method for STG forecasting, but they often struggle with temporal out-of-distribution (OoD) issues and dynamic spatial causation. In this paper, we propose a novel framework called CaST to tackle these two challenges via causal treatments. Concretely, leveraging a causal lens, we first build a structural causal model to decipher the data generation process of STGs. To handle the temporal OoD issue, we employ the back-door adjustment by a novel disentanglement block to separate invariant parts and temporal environments from input data. Moreover, we utilize the front-door adjustment and adopt the Hodge-Laplacian operator for edge-level convolution to model the ripple effect of causation. Experiments results on three real-world datasets demonstrate the effectiveness and practicality of CaST, which consistently outperforms existing methods with good interpretability.

Haoran Wei, Xu Liu, Shouchun Xu et al.

Many current works directly adopt multi-rate depth-wise dilated convolutions to capture multi-scale contextual information simultaneously from one input feature map, thus improving the feature extraction efficiency for real-time semantic segmentation. However, this design may lead to difficult access to multi-scale contextual information because of the unreasonable structure and hyperparameters. To lower the difficulty of drawing multi-scale contextual information, we propose a highly efficient multi-scale feature extraction method, which decomposes the original single-step method into two steps, Region Residualization-Semantic Residualization. In this method, the multi-rate depth-wise dilated convolutions take a simpler role in feature extraction: performing simple semantic-based morphological filtering with one desired receptive field in the second step based on each concise feature map of region form provided by the first step, to improve their efficiency. Moreover, the dilation rates and the capacity of dilated convolutions for each network stage are elaborated to fully utilize all the feature maps of region form that can be achieved.Accordingly, we design a novel Dilation-wise Residual (DWR) module and a Simple Inverted Residual (SIR) module for the high and low level network, respectively, and form a powerful DWR Segmentation (DWRSeg) network. Extensive experiments on the Cityscapes and CamVid datasets demonstrate the effectiveness of our method by achieving a state-of-the-art trade-off between accuracy and inference speed, in addition to being lighter weight. Without pretraining or resorting to any training trick, we achieve an mIoU of 72.7% on the Cityscapes test set at a speed of 319.5 FPS on one NVIDIA GeForce GTX 1080 Ti card, which exceeds the latest methods of a speed of 69.5 FPS and 0.8% mIoU. The code and trained models are publicly available.

Yunjie Peng, Saihui Hou, Chunshui Cao et al.

Occluded person re-identification (Re-ID) aims at addressing the occlusion problem when retrieving the person of interest across multiple cameras. With the promotion of deep learning technology and the increasing demand for intelligent video surveillance, the frequent occlusion in real-world applications has made occluded person Re-ID draw considerable interest from researchers. A large number of occluded person Re-ID methods have been proposed while there are few surveys that focus on occlusion. To fill this gap and help boost future research, this paper provides a systematic survey of occluded person Re-ID. Through an in-depth analysis of the occlusion in person Re-ID, most existing methods are found to only consider part of the problems brought by occlusion. Therefore, we review occlusion-related person Re-ID methods from the perspective of issues and solutions. We summarize four issues caused by occlusion in person Re-ID, i.e., position misalignment, scale misalignment, noisy information, and missing information. The occlusion-related methods addressing different issues are then categorized and introduced accordingly. After that, we summarize and compare the performance of recent occluded person Re-ID methods on four popular datasets: Partial-ReID, Partial-iLIDS, Occluded-ReID, and Occluded-DukeMTMC. Finally, we provide insights on promising future research directions.

Xu Liu, Yuxuan Liang, Chao Huang et al.

Spatio-temporal graph neural networks (STGNN) have become the most popular solution to traffic forecasting. While successful, they rely on the message passing scheme of GNNs to establish spatial dependencies between nodes, and thus inevitably inherit GNNs' notorious inefficiency. Given these facts, in this paper, we propose an embarrassingly simple yet remarkably effective spatio-temporal learning approach, entitled SimST. Specifically, SimST approximates the efficacies of GNNs by two spatial learning techniques, which respectively model local and global spatial correlations. Moreover, SimST can be used alongside various temporal models and involves a tailored training strategy. We conduct experiments on five traffic benchmarks to assess the capability of SimST in terms of efficiency and effectiveness. Empirical results show that SimST improves the prediction throughput by up to 39 times compared to more sophisticated STGNNs while attaining comparable performance, which indicates that GNNs are not the only option for spatial modeling in traffic forecasting.

Chao Wang, Licheng Jiao, Jiaxuan Zhao et al.

The construction of machine learning models involves many bi-level multi-objective optimization problems (BL-MOPs), where upper level (UL) candidate solutions must be evaluated via training weights of a model in the lower level (LL). Due to the Pareto optimality of sub-problems and the complex dependency across UL solutions and LL weights, an UL solution is feasible if and only if the LL weight is Pareto optimal. It is computationally expensive to determine which LL Pareto weight in the LL Pareto weight set is the most appropriate for each UL solution. This paper proposes a bi-level multi-objective learning framework (BLMOL), coupling the above decision-making process with the optimization process of the UL-MOP by introducing LL preference $r$. Specifically, the UL variable and $r$ are simultaneously searched to minimize multiple UL objectives by evolutionary multi-objective algorithms. The LL weight with respect to $r$ is trained to minimize multiple LL objectives via gradient-based preference multi-objective algorithms. In addition, the preference surrogate model is constructed to replace the expensive evaluation process of the UL-MOP. We consider a novel case study on multi-task graph neural topology search. It aims to find a set of Pareto topologies and their Pareto weights, representing different trade-offs across tasks at UL and LL, respectively. The found graph neural network is employed to solve multiple tasks simultaneously, including graph classification, node classification, and link prediction. Experimental results demonstrate that BLMOL can outperform some state-of-the-art algorithms and generate well-representative UL solutions and LL weights.

Fan Zhang, Lingling Li, Licheng Jiao et al.

Satellite imagery, due to its long-range imaging, brings with it a variety of scale-preferred tasks, such as the detection of tiny/small objects, making the precise localization and detection of small objects of interest a challenging task. In this article, we design a Knowledge Discovery Network (KDN) to implement the renormalization group theory in terms of efficient feature extraction. Renormalized connection (RC) on the KDN enables ``synergistic focusing'' of multi-scale features. Based on our observations of KDN, we abstract a class of RCs with different connection strengths, called n21C, and generalize it to FPN-based multi-branch detectors. In a series of FPN experiments on the scale-preferred tasks, we found that the ``divide-and-conquer'' idea of FPN severely hampers the detector's learning in the right direction due to the large number of large-scale negative samples and interference from background noise. Moreover, these negative samples cannot be eliminated by the focal loss function. The RCs extends the multi-level feature's ``divide-and-conquer'' mechanism of the FPN-based detectors to a wide range of scale-preferred tasks, and enables synergistic effects of multi-level features on the specific learning goal. In addition, interference activations in two aspects are greatly reduced and the detector learns in a more correct direction. Extensive experiments of 17 well-designed detection architectures embedded with n21s on five different levels of scale-preferred tasks validate the effectiveness and efficiency of the RCs. Especially the simplest linear form of RC, E421C performs well in all tasks and it satisfies the scaling property of RGT. We hope that our approach will transfer a large number of well-designed detectors from the computer vision community to the remote sensing community.

Yu Du, Xu Liu, Yansong Chua

Speech enhancement seeks to extract clean speech from noisy signals. Traditional deep learning methods face two challenges: efficiently using information in long speech sequences and high computational costs. To address these, we introduce the Spiking Structured State Space Model (Spiking-S4). This approach merges the energy efficiency of Spiking Neural Networks (SNN) with the long-range sequence modeling capabilities of Structured State Space Models (S4), offering a compelling solution. Evaluation on the DNS Challenge and VoiceBank+Demand Datasets confirms that Spiking-S4 rivals existing Artificial Neural Network (ANN) methods but with fewer computational resources, as evidenced by reduced parameters and Floating Point Operations (FLOPs).

Xu Liu, Zhouhui Lian

Remote Sensing Vision-Language Models (RS VLMs) have made much progress in the tasks of remote sensing (RS) image comprehension. While performing well in multi-modal reasoning and multi-turn conversations, the existing models lack pixel-level understanding and struggle with multi-image inputs. In this work, we propose RSUniVLM, a unified, end-to-end RS VLM designed for comprehensive vision understanding across multiple granularity, including image-level, region-level, and pixel-level tasks. RSUniVLM also performs effectively in multi-image analysis, with instances of change detection and change captioning. To enhance the model's ability to capture visual information at different levels without increasing model size, we design a novel architecture called Granularity-oriented Mixture of Experts to constraint the model to about 1 billion parameters. We also construct a large-scale RS instruction-following dataset based on a variety of existing datasets in both RS and general domain, encompassing various tasks such as object localization, visual question answering, and semantic segmentation. Substantial experiments have been conducted to validate the superiority of the proposed RSUniVLM up to state-of-the-art across various RS tasks. Code and model will be available at \href{https://github.com/xuliu-cyber/RSUniVLM}{here}.

Dianze Li, Jianing Li, Xu Liu et al.

Combining the complementary benefits of frames and events has been widely used for object detection in challenging scenarios. However, most object detection methods use two independent Artificial Neural Network (ANN) branches, limiting cross-modality information interaction across the two visual streams and encountering challenges in extracting temporal cues from event streams with low power consumption. To address these challenges, we propose HDI-Former, a Hybrid Dynamic Interaction ANN-SNN Transformer, marking the first trial to design a directly trained hybrid ANN-SNN architecture for high-accuracy and energy-efficient object detection using frames and events. Technically, we first present a novel semantic-enhanced self-attention mechanism that strengthens the correlation between image encoding tokens within the ANN Transformer branch for better performance. Then, we design a Spiking Swin Transformer branch to model temporal cues from event streams with low power consumption. Finally, we propose a bio-inspired dynamic interaction mechanism between ANN and SNN sub-networks for cross-modality information interaction. The results demonstrate that our HDI-Former outperforms eleven state-of-the-art methods and our four baselines by a large margin. Our SNN branch also shows comparable performance to the ANN with the same architecture while consuming 10.57$\times$ less energy on the DSEC-Detection dataset. Our open-source code is available in the supplementary material.

Shuo Li, Fang Liu, Zehua Hao et al.

With its powerful visual-language alignment capability, CLIP performs well in zero-shot and few-shot learning tasks. However, we found in experiments that CLIP's logits suffer from serious inter-class confusion problems in downstream tasks, and the ambiguity between categories seriously affects the accuracy. To address this challenge, we propose a novel method called Logits DeConfusion, which effectively learns and eliminates inter-class confusion in logits by combining our Multi-level Adapter Fusion (MAF) module with our Inter-Class Deconfusion (ICD) module. Our MAF extracts features from different levels and fuses them uniformly to enhance feature representation. Our ICD learnably eliminates inter-class confusion in logits with a residual structure. Experimental results show that our method can significantly improve the classification performance and alleviate the inter-class confusion problem. The code is available at https://github.com/LiShuo1001/LDC.

Xu Liu, Shu Zhou, Yurong Song et al.

Face recognition technology is widely used in the financial field, and various types of liveness attack behaviors need to be addressed. Existing liveness detection algorithms are trained on specific training datasets and tested on testing datasets, but their performance and robustness in transferring to unseen datasets are relatively poor. To tackle this issue, we propose a face liveness detection method based on image-text pairs and contrastive learning, dividing liveness attack problems in the financial field into eight categories and using text information to describe the images of these eight types of attacks. The text encoder and image encoder are used to extract feature vector representations for the classification description text and face images, respectively. By maximizing the similarity of positive samples and minimizing the similarity of negative samples, the model learns shared representations between images and texts. The proposed method is capable of effectively detecting specific liveness attack behaviors in certain scenarios, such as those occurring in dark environments or involving the tampering of ID card photos. Additionally, it is also effective in detecting traditional liveness attack methods, such as printing photo attacks and screen remake attacks. The zero-shot capabilities of face liveness detection on five public datasets, including NUAA, CASIA-FASD, Replay-Attack, OULU-NPU and MSU-MFSD also reaches the level of commercial algorithms. The detection capability of proposed algorithm was verified on 5 types of testing datasets, and the results show that the method outperformed commercial algorithms, and the detection rates reached 100% on multiple datasets. Demonstrating the effectiveness and robustness of introducing image-text pairs and contrastive learning into liveness detection tasks as proposed in this paper.

Xu Liu, Licheng Jiao, Xu Tang et al.

The approaches for analyzing the polarimetric scattering matrix of polarimetric synthetic aperture radar (PolSAR) data have always been the focus of PolSAR image classification. Generally, the polarization coherent matrix and the covariance matrix obtained by the polarimetric scattering matrix only show a limited number of polarimetric information. In order to solve this problem, we propose a sparse scattering coding way to deal with polarimetric scattering matrix and obtain a close complete feature. This encoding mode can also maintain polarimetric information of scattering matrix completely. At the same time, in view of this encoding way, we design a corresponding classification algorithm based on convolution network to combine this feature. Based on sparse scattering coding and convolution neural network, the polarimetric convolutional network is proposed to classify PolSAR images by making full use of polarimetric information. We perform the experiments on the PolSAR images acquired by AIRSAR and RADARSAT-2 to verify the proposed method. The experimental results demonstrate that the proposed method get better results and has huge potential for PolSAR data classification. Source code for sparse scattering coding is available at https://github.com/liuxuvip/Polarimetric-Scattering-Coding.

Chao Wang, Jiaxuan Zhao, Lingling Li et al.

Graph neural architecture search (GNAS) can customize high-performance graph neural network architectures for specific graph tasks or datasets. However, existing GNAS methods begin searching for architectures from a zero-knowledge state, ignoring the prior knowledge that may improve the search efficiency. The available knowledge base (e.g. NAS-Bench-Graph) contains many rich architectures and their multiple performance metrics, such as the accuracy (#Acc) and number of parameters (#Params). This study proposes exploiting such prior knowledge to accelerate the multi-objective evolutionary search on a new graph dataset, named knowledge-aware evolutionary GNAS (KEGNAS). KEGNAS employs the knowledge base to train a knowledge model and a deep multi-output Gaussian process (DMOGP) in one go, which generates and evaluates transfer architectures in only a few GPU seconds. The knowledge model first establishes a dataset-to-architecture mapping, which can quickly generate candidate transfer architectures for a new dataset. Subsequently, the DMOGP with architecture and dataset encodings is designed to predict multiple performance metrics for candidate transfer architectures on the new dataset. According to the predicted metrics, non-dominated candidate transfer architectures are selected to warm-start the multi-objective evolutionary algorithm for optimizing the #Acc and #Params on a new dataset. Empirical studies on NAS-Bench-Graph and five real-world datasets show that KEGNAS swiftly generates top-performance architectures, achieving 4.27% higher accuracy than advanced evolutionary baselines and 11.54% higher accuracy than advanced differentiable baselines. In addition, ablation studies demonstrate that the use of prior knowledge significantly improves the search performance.

Yanbiao Ma, Licheng Jiao, Fang Liu et al.

In semi-supervised learning, methods that rely on confidence learning to generate pseudo-labels have been widely proposed. However, increasing research finds that when faced with noisy and biased data, the model's representation network is more reliable than the classification network. Additionally, label generation methods based on model predictions often show poor adaptability across different datasets, necessitating customization of the classification network. Therefore, we propose a Hierarchical Dynamic Labeling (HDL) algorithm that does not depend on model predictions and utilizes image embeddings to generate sample labels. We also introduce an adaptive method for selecting hyperparameters in HDL, enhancing its versatility. Moreover, HDL can be combined with general image encoders (e.g., CLIP) to serve as a fundamental data processing module. We extract embeddings from datasets with class-balanced and long-tailed distributions using pre-trained semi-supervised models. Subsequently, samples are re-labeled using HDL, and the re-labeled samples are used to further train the semi-supervised models. Experiments demonstrate improved model performance, validating the motivation that representation networks are more reliable than classifiers or predictors. Our approach has the potential to change the paradigm of pseudo-label generation in semi-supervised learning.

Xiao Huang, Xu Liu, Enze Zhang et al.

Offline-to-online Reinforcement Learning (O2O RL) aims to perform online fine-tuning on an offline pre-trained policy to minimize costly online interactions. Existing work used offline datasets to generate data that conform to the online data distribution for data augmentation. However, generated data still exhibits a gap with the online data, limiting overall performance. To address this, we propose a new data augmentation approach, Classifier-Free Diffusion Generation (CFDG). Without introducing additional classifier training overhead, CFDG leverages classifier-free guidance diffusion to significantly enhance the generation quality of offline and online data with different distributions. Additionally, it employs a reweighting method to enable more generated data to align with the online data, enhancing performance while maintaining the agent's stability. Experimental results show that CFDG outperforms replaying the two data types or using a standard diffusion model to generate new data. Our method is versatile and can be integrated with existing offline-to-online RL algorithms. By implementing CFDG to popular methods IQL, PEX and APL, we achieve a notable 15% average improvement in empirical performance on the D4RL benchmark such as MuJoCo and AntMaze.

Panjian Huang, Xu Liu, Yongzhen Huang

Computer-assisted diagnosis (CAD) based on deep learning has become a crucial diagnostic technology in the medical industry, effectively improving diagnosis accuracy. However, the scarcity of brain tumor Magnetic Resonance (MR) image datasets causes the low performance of deep learning algorithms. The distribution of transformed images generated by traditional data augmentation (DA) intrinsically resembles the original ones, resulting in a limited performance in terms of generalization ability. This work improves Progressive Growing of GANs with a structural similarity loss function (PGGAN-SSIM) to solve image blurriness problems and model collapse. We also explore other GAN-based data augmentation to demonstrate the effectiveness of the proposed model. Our results show that PGGAN-SSIM successfully generates 256x256 realistic brain tumor MR images which fill the real image distribution uncovered by the original dataset. Furthermore, PGGAN-SSIM exceeds other GAN-based methods, achieving promising performance improvement in Frechet Inception Distance (FID) and Multi-scale Structural Similarity (MS-SSIM).

Jing Liu, Bohan Zhuang, Mingkui Tan et al.

In many real-world applications, we often need to handle various deployment scenarios, where the resource constraint and the superclass of interest corresponding to a group of classes are dynamically specified. How to efficiently deploy deep models for diverse deployment scenarios is a new challenge. Previous NAS approaches seek to design architectures for all classes simultaneously, which may not be optimal for some individual superclasses. A straightforward solution is to search an architecture from scratch for each deployment scenario, which however is computation-intensive and impractical. To address this, we present a novel and general framework, called Elastic Architecture Search (EAS), permitting instant specializations at runtime for diverse superclasses with various resource constraints. To this end, we first propose to effectively train an over-parameterized network via a superclass dropout strategy during training. In this way, the resulting model is robust to the subsequent superclasses dropping at inference time. Based on the well-trained over-parameterized network, we then propose an efficient architecture generator to obtain promising architectures within a single forward pass. Experiments on three image classification datasets show that EAS is able to find more compact networks with better performance while remarkably being orders of magnitude faster than state-of-the-art NAS methods, e.g., outperforming OFA (once-for-all) by 1.3% on Top-1 accuracy at a budget around 361M #MAdds on ImageNet-10. More critically, EAS is able to find compact architectures within 0.1 second for 50 deployment scenarios.

Xu Liu, Xiaoya Zhang, Wei Peng et al.

Physics-informed neural networks (PINNs) have been widely used to solve various scientific computing problems. However, large training costs limit PINNs for some real-time applications. Although some works have been proposed to improve the training efficiency of PINNs, few consider the influence of initialization. To this end, we propose a New Reptile initialization based Physics-Informed Neural Network (NRPINN). The original Reptile algorithm is a meta-learning initialization method based on labeled data. PINNs can be trained with less labeled data or even without any labeled data by adding partial differential equations (PDEs) as a penalty term into the loss function. Inspired by this idea, we propose the new Reptile initialization to sample more tasks from the parameterized PDEs and adapt the penalty term of the loss. The new Reptile initialization can acquire initialization parameters from related tasks by supervised, unsupervised, and semi-supervised learning. Then, PINNs with initialization parameters can efficiently solve PDEs. Besides, the new Reptile initialization can also be used for the variants of PINNs. Finally, we demonstrate and verify the NRPINN considering both forward problems, including solving Poisson, Burgers, and Schrödinger equations, as well as inverse problems, where unknown parameters in the PDEs are estimated. Experimental results show that the NRPINN training is much faster and achieves higher accuracy than PINNs with other initialization methods.

Deng Huang, Wenhao Wu, Weiwen Hu et al.

We study self-supervised video representation learning, which is a challenging task due to 1) lack of labels for explicit supervision; 2) unstructured and noisy visual information. Existing methods mainly use contrastive loss with video clips as the instances and learn visual representation by discriminating instances from each other, but they need a careful treatment of negative pairs by either relying on large batch sizes, memory banks, extra modalities or customized mining strategies, which inevitably includes noisy data. In this paper, we observe that the consistency between positive samples is the key to learn robust video representation. Specifically, we propose two tasks to learn the appearance and speed consistency, respectively. The appearance consistency task aims to maximize the similarity between two clips of the same video with different playback speeds. The speed consistency task aims to maximize the similarity between two clips with the same playback speed but different appearance information. We show that optimizing the two tasks jointly consistently improves the performance on downstream tasks, e.g., action recognition and video retrieval. Remarkably, for action recognition on the UCF-101 dataset, we achieve 90.8\% accuracy without using any extra modalities or negative pairs for unsupervised pretraining, which outperforms the ImageNet supervised pretrained model. Codes and models will be available.

Wei Jing, Feng Tian, Jizhong Zhang et al.

Facial Expressions Recognition(FER) on low-resolution images is necessary for applications like group expression recognition in crowd scenarios(station, classroom etc.). Classifying a small size facial image into the right expression category is still a challenging task. The main cause of this problem is the loss of discriminative feature due to reduced resolution. Super-resolution method is often used to enhance low-resolution images, but the performance on FER task is limited when on images of very low resolution. In this work, inspired by feature super-resolution methods for object detection, we proposed a novel generative adversary network-based feature level super-resolution method for robust facial expression recognition(FSR-FER). In particular, a pre-trained FER model was employed as feature extractor, and a generator network G and a discriminator network D are trained with features extracted from images of low resolution and original high resolution. Generator network G tries to transform features of low-resolution images to more discriminative ones by making them closer to the ones of corresponding high-resolution images. For better classification performance, we also proposed an effective classification-aware loss re-weighting strategy based on the classification probability calculated by a fixed FER model to make our model focus more on samples that are easily misclassified. Experiment results on Real-World Affective Faces (RAF) Database demonstrate that our method achieves satisfying results on various down-sample factors with a single model and has better performance on low-resolution images compared with methods using image super-resolution and expression recognition separately.

Ke Zhan, Shimiao Jiang, Yu Bai et al.

Eltwise layer is a commonly used structure in the multi-branch deep learning network. In a filter-wise pruning procedure, due to the specific operation of the eltwise layer, all its previous convolutional layers should vote for which filters by index should be pruned. Since only an intersection of the voted filters is pruned, the compression rate is limited. This work proposes a method called Directed-Weighting Group Lasso (DWGL), which enforces an index-wise incremental (directed) coefficient on the filterlevel group lasso items, so that the low index filters getting high activation tend to be kept while the high index ones tend to be pruned. When using DWGL, much fewer filters are retained during the voting process and the compression rate can be boosted. The paper test the proposed method on the ResNet series networks. On CIFAR-10, it achieved a 75.34% compression rate on ResNet-56 with a 0.94% error increment, and a 52.06% compression rate on ResNet-20 with a 0.72% error increment. On ImageNet, it achieved a 53% compression rate with ResNet-50 with a 0.6% error increment, speeding up the network by 2.23 times. Furthermore, it achieved a 75% compression rate on ResNet-50 with a 1.2% error increment, speeding up the network by 4 times.

Xu Liu, Licheng Jiao, Dan Zhang et al.

POLSAR image has an advantage over optical image because it can be acquired independently of cloud cover and solar illumination. PolSAR image classification is a hot and valuable topic for the interpretation of POLSAR image. In this paper, a novel POLSAR image classification method is proposed based on polarimetric scattering coding and sparse support matrix machine. First, we transform the original POLSAR data to get a real value matrix by the polarimetric scattering coding, which is called polarimetric scattering matrix and is a sparse matrix. Second, the sparse support matrix machine is used to classify the sparse polarimetric scattering matrix and get the classification map. The combination of these two steps takes full account of the characteristics of POLSAR. The experimental results show that the proposed method can get better results and is an effective classification method.

Qigong Sun, Xiufang Li, Lingling Li et al.

Polarimetric synthetic aperture radar (PolSAR) images are widely used in disaster detection and military reconnaissance and so on. However, their interpretation faces some challenges, e.g., deficiency of labeled data, inadequate utilization of data information and so on. In this paper, a complex-valued generative adversarial network (GAN) is proposed for the first time to address these issues. The complex number form of model complies with the physical mechanism of PolSAR data and in favor of utilizing and retaining amplitude and phase information of PolSAR data. GAN architecture and semi-supervised learning are combined to handle deficiency of labeled data. GAN expands training data and semi-supervised learning is used to train network with generated, labeled and unlabeled data. Experimental results on two benchmark data sets show that our model outperforms existing state-of-the-art models, especially for conditions with fewer labeled data.

Lin Cheng, Xu Liu, Lingling Li et al.

Object detection is a fundamental and challenging problem in aerial and satellite image analysis. More recently, a two-stage detector Faster R-CNN is proposed and demonstrated to be a promising tool for object detection in optical remote sensing images, while the sparse and dense characteristic of objects in remote sensing images is complexity. It is unreasonable to treat all images with the same region proposal strategy, and this treatment limits the performance of two-stage detectors. In this paper, we propose a novel and effective approach, named deep adaptive proposal network (DAPNet), address this complexity characteristic of object by learning a new category prior network (CPN) on the basis of the existing Faster R-CNN architecture. Moreover, the candidate regions produced by DAPNet model are different from the traditional region proposal network (RPN), DAPNet predicts the detail category of each candidate region. And these candidate regions combine the object number, which generated by the category prior network to achieve a suitable number of candidate boxes for each image. These candidate boxes can satisfy detection tasks in sparse and dense scenes. The performance of the proposed framework has been evaluated on the challenging NWPU VHR-10 data set. Experimental results demonstrate the superiority of the proposed framework to the state-of-the-art.

Xu Liu, Steven W. Chen, Shreyas Aditya et al.

We present a novel fruit counting pipeline that combines deep segmentation, frame to frame tracking, and 3D localization to accurately count visible fruits across a sequence of images. Our pipeline works on image streams from a monocular camera, both in natural light, as well as with controlled illumination at night. We first train a Fully Convolutional Network (FCN) and segment video frame images into fruit and non-fruit pixels. We then track fruits across frames using the Hungarian Algorithm where the objective cost is determined from a Kalman Filter corrected Kanade-Lucas-Tomasi (KLT) Tracker. In order to correct the estimated count from tracking process, we combine tracking results with a Structure from Motion (SfM) algorithm to calculate relative 3D locations and size estimates to reject outliers and double counted fruit tracks. We evaluate our algorithm by comparing with ground-truth human-annotated visual counts. Our results demonstrate that our pipeline is able to accurately and reliably count fruits across image sequences, and the correction step can significantly improve the counting accuracy and robustness. Although discussed in the context of fruit counting, our work can extend to detection, tracking, and counting of a variety of other stationary features of interest such as leaf-spots, wilt, and blossom.

Xu Liu, Lili Zhao, Dajun Ding et al.

This paper proposes an end-to-end deep hashing framework with category mask for fast video retrieval. We train our network in a supervised way by fully exploiting inter-class diversity and intra-class identity. Classification loss is optimized to maximize inter-class diversity, while intra-pair is introduced to learn representative intra-class identity. We investigate the binary bits distribution related to categories and find out that the effectiveness of binary bits is highly correlated with data categories, and some bits may degrade classification performance of some categories. We then design hash code generation scheme with category mask to filter out bits with negative contribution. Experimental results demonstrate the proposed method outperforms several state-of-the-arts under various evaluation metrics on public datasets.

Zheng Tang, Gaoang Wang, Tao Liu et al.

Tracking of multiple objects is an important application in AI City geared towards solving salient problems related to safety and congestion in an urban environment. Frequent occlusion in traffic surveillance has been a major problem in this research field. In this challenge, we propose a model-based vehicle localization method, which builds a kernel at each patch of the 3D deformable vehicle model and associates them with constraints in 3D space. The proposed method utilizes shape fitness evaluation besides color information to track vehicle objects robustly and efficiently. To build 3D car models in a fully unsupervised manner, we also implement evolutionary camera self-calibration from tracking of walking humans to automatically compute camera parameters. Additionally, the segmented foreground masks which are crucial to 3D modeling and camera self-calibration are adaptively refined by multiple-kernel feedback from tracking. For object detection/classification, the state-of-the-art single shot multibox detector (SSD) is adopted to train and test on the NVIDIA AI City Dataset. To improve the accuracy on categories with only few objects, like bus, bicycle and motorcycle, we also employ the pretrained model from YOLO9000 with multi-scale testing. We combine the results from SSD and YOLO9000 based on ensemble learning. Experiments show that our proposed tracking system outperforms both state-of-the-art of tracking by segmentation and tracking by detection.