Fast pixel-matching for video object segmentation

Video object segmentation, aiming to segment the foreground objects given the annotation of the first frame, has been attracting increasing attentions. Many state-of-the-art approaches have achieved great performance by relying on online model updating or mask-propagation techniques. However, most online models require high computational cost due to model fine-tuning during inference. Most mask-propagation based models are faster but with relatively low performance due to failure to adapt to object appearance variation. In this paper, we are aiming to design a new model to make a good balance between speed and performance. We propose a model, called NPMCA-net, which directly localizes foreground objects based on mask-propagation and non-local technique by matching pixels in reference and target frames. Since we bring in information of both first and previous frames, our network is robust to large object appearance variation, and can better adapt to occlusions. Extensive experiments show that our approach can achieve a new state-of-the-art performance with a fast speed at the same time (86.5% IoU on DAVIS-2016 and 72.2% IoU on DAVIS-2017, with speed of 0.11s per frame) under the same level comparison. Source code is available at https://github.com/siyueyu/NPMCA-net.     

SCPNet: Self-constrained parallelism network for keypoint-based lightweight object detection

Keypoint-based object detection achieves better performance without positioning calculations and extensive prediction. However, they have heavy backbone, and high-resolution is restored using upsampling that obtain unreliable features. We propose a self-constrained parallelism keypoint-based lightweight object detection network (SCPNet), which speeds inference, drops parameters, widens receptive fields, and makes prediction accurate. Specifically, the parallel multi-scale fusion module (PMFM) with parallel shuffle blocks (PSB) adopts parallel structure to obtain reliable features and reduce depth, adopts repeated multi-scale fusion to avoid too many parallel branches. The self-constrained detection module (SCDM) has a two-branch structure, with one branch predicting corners, and employing entad offset to match high-quality corner pairs, and the other branch predicting center keypoints. The distances between the paired corners’ geometric centers and the center keypoints are used for self-constrained detection. On MS-COCO 2017 and PASCAL VOC, SCPNet’s results are competitive with the state-of-the-art lightweight object detection. https://github.com/mengdie-wang/SCPNet.git.     

Unified Chinese License Plate detection and recognition with high efficiency

Recently, deep learning-based methods have reached an excellent performance on License Plate (LP) detection and recognition tasks. However, it is still challenging to build a robust model for Chinese LPs since there are not enough large and representative datasets. In this work, we propose a new dataset named Chinese Road Plate Dataset (CRPD) that contains multi-objective Chinese LP images as a supplement to the existing public benchmarks. The images are mainly captured with electronic monitoring systems with detailed annotations. To our knowledge, CRPD is the largest public multi-objective Chinese LP dataset with annotations of vertices. With CRPD, a unified detection and recognition network with high efficiency is presented as the baseline. The network is end-to-end trainable with totally real-time inference efficiency (30 fps with 640 p). The experiments on several public benchmarks demonstrate that our method has reached competitive performance. The code and dataset will be publicly available at https://github.com/yxgong0/CRPD.     

No-Reference Video Quality Assessment using novel hybrid features and two-stage hybrid regression for score level fusion

This paper presents a novel No-Reference Video Quality Assessment (NR-VQA) model that utilizes proposed 3D steerable wavelet transform-based Natural Video Statistics (NVS) features as well as human perceptual features. Additionally, we proposed a novel two-stage regression scheme that significantly improves the overall performance of quality estimation. In the first stage, transform-based NVS and human perceptual features are separately passed through the proposed hybrid regression scheme: Support Vector Regression (SVR) followed by Polynomial curve fitting. The two visual quality scores predicted from the first stage are then used as features for the similar second stage. This predicts the final quality scores of distorted videos by achieving score level fusion. Extensive experiments were conducted using five authentic and four synthetic distortion databases. Experimental results demonstrate that the proposed method outperforms other published state-of-the-art benchmark methods on synthetic distortion databases and is among the top performers on authentic distortion databases. The source code is available at https://github.com/anishVNIT/two-stage-vqa.     

R2RNet: Low-light image enhancement via Real-low to Real-normal Network

Images captured in weak illumination conditions could seriously degrade the image quality. Solving a series of degradation of low-light images can effectively improve the visual quality of images and the performance of high-level visual tasks. In this study, a novel Retinex-based Real-low to Real-normal Network (R2RNet) is proposed for low-light image enhancement, which includes three subnets: a Decom-Net, a Denoise-Net, and a Relight-Net. These three subnets are used for decomposing, denoising, contrast enhancement and detail preservation, respectively. Our R2RNet not only uses the spatial information of the image to improve the contrast but also uses the frequency information to preserve the details. Therefore, our model achieved more robust results for all degraded images. Unlike most previous methods that were trained on synthetic images, we collected the first Large-Scale Real-World paired low/normal-light images dataset (LSRW dataset) to satisfy the training requirements and make our model have better generalization performance in real-world scenes. Extensive experiments on publicly available datasets demonstrated that our method outperforms the existing state-of-the-art methods both quantitatively and visually. In addition, our results showed that the performance of the high-level visual task (i.e., face detection) can be effectively improved by using the enhanced results obtained by our method in low-light conditions. Our codes and the LSRW dataset are available at: https://github.com/JianghaiSCU/R2RNet.     

Edge-aware object pixel-level representation tracking

Recently, there has been a trend in tracking to use more refined segmentation mask instead of coarse bounding box to represent the target object. Some trackers proposed segmentation branches based on the tracking framework and maintain real-time speed. However, those trackers use a simple FCNs structure and lack of the edge information modeling. This makes performance quite unsatisfactory. In this paper, we propose an edge-aware segmentation network, which uses the complementarity between target information and edge information to provide a more refined representation of the target. Firstly, We use the high-level features of the tracking backbone network and the correlation features of the classification branch of the tracking framework to fuse, and use the target edge and target segmentation mask for simultaneous supervision to obtain an optimized high-level feature with rough edge information and target information. Secondly, we use the optimized high-level features to guide the low-level features of the tracking backbone network to generate more refined edge features. Finally, we use the refined edge features to fuse with the target features of each layer to generate the final mask. Our approach has achieved leading performance on recent pixel-wise object tracking benchmark VOT2020 and segmentation datasets DAVIS2016 and DAVIS2017 while running on 47 fps. Code is available at https://github.com/TJUMMG/EATtracker.     

Boosting semantic segmentation via feature enhancement

Semantic segmentation aims to map each pixel of an image into its corresponding semantic label. Most existing methods either mainly concentrate on high-level features or simple combination of low-level and high-level features from backbone convolutional networks, which may weaken or even ignore the compensation between different levels. To effectively take advantages from both shallow (textural) and deep (semantic) features, this paper proposes a novel plug-and-play module, namely feature enhancement module (FEM). The proposed FEM first uses an information extractor to extract the desired details or semantics from different stages, and then enhances target features by taking in the extracted message. Two types of FEM, i.e., detail FEM and semantic FEM, can be customized. Concretely, the former type strengthens textural information to protect key but tiny/low-contrast details from suppression/removal, while the other one highlights structural information to boost segmentation performance. By equipping a given backbone network with FEMs, there might contain two information flows, i.e., detail flow and semantic flow. Extensive experiments on the Cityscapes, ADE20K and PASCAL Context datasets are conducted to validate the effectiveness of our design. The code has been released at https://github.com/SuperZ-Liu/FENet.     

Adaptive weight multi-channel center similar deep hashing

To increase the richness of the extracted text modality feature information and deeply explore the semantic similarity between the modalities. In this paper, we propose a novel method, named adaptive weight multi-channel center similar deep hashing (AMCDH). The algorithm first utilizes three channels with different configurations to extract feature information from the text modality; and then adds them according to the learned weight ratio to increase the richness of the information. We also introduce the Jaccard coefficient to measure the semantic similarity level between modalities from 0 to 1, and utilize it as the penalty coefficient of the cross-entropy loss function to increase its role in backpropagation. Besides, we propose a method of constructing center similarity, which makes the hash codes of similar data pairs close to the same center point, and dissimilar data pairs are scattered at different center points to generate high-quality hash codes. Extensive experimental evaluations on four benchmark datasets show that the performance of our proposed model AMCDH is significantly better than other competing baselines. The code can be obtained from https://github.com/DaveLiu6/AMCDH.git.     

Part-attentive kinematic chain-based regressor for 3D human modeling

As the demand for realistic representation and its applications increases rapidly, 3D human modeling via a single RGB image has become the essential technique. Owing to the great success of deep neural networks, various learning-based approaches have been introduced for this task. However, partial occlusions still give the difficulty to accurately estimate the 3D human model. In this letter, we propose the part-attentive kinematic regressor for 3D human modeling. The key idea of the proposed method is to predict body part attentions based on each body center position and estimate parameters of the 3D human model via corresponding attentive features through the kinematic chain-based decoder in a one-stage fashion. One important advantage is that the proposed method has a good ability to yield natural shapes and poses even with severe occlusions. Experimental results on benchmark datasets show that the proposed method is effective for 3D human modeling under complicated real-world environments. The code and model are publicly available at: https://github.com/DCVL-3D/PKCN_release     

Convolutional neural network with adaptive inferential framework for skeleton-based action recognition

In the task of skeleton-based action recognition, CNN-based methods represent the skeleton data as a pseudo image for processing. However, it still remains as a critical issue of how to construct the pseudo image to model the spatial dependencies of the skeletal data. To address this issue, we propose a novel convolutional neural network with adaptive inferential framework (AIF-CNN) to exploit the dependencies among the skeleton joints. We particularly investigate several initialization strategies to make the AIF effective with each strategy introducing the different prior knowledge. Extensive experiments on the dataset of NTU RGB+D and Kinetics-Skeleton demonstrate that the performance is improved significantly by integrating the different prior information. The source code is available at: https://github.com/hhe-distance/AIF-CNN.     

Infrared dim and small target detection based on U-Transformer

Infrared dim and small target detection is a key technology for space-based infrared search and tracking systems. Traditional detection methods have a high false alarm rate and fail to handle complex background and high-noise scenarios. Also, the methods cannot effectively detect targets on a small scale. In this paper, a U-Transformer method is proposed, and a transformer is introduced into the infrared dim and small target detection. First, a U-shaped network is constructed. In the encoder part, the self-attention mechanism is used for infrared dim and small target feature extraction, which helps to solve the problems of losing dim and small target features of deep networks. Meanwhile, by using the encoding and decoding structure, infrared dim and small target features are filtered from the complex background while the shallow features and semantic information of the target are retained. Experiments show that anchor-free and transformer have great potential for infrared dim and small target detection. On the datasets with a complex background, our method outperforms the state-of-the-art detectors and meets the real-time requirement. The code is publicly available at https://github.com/Linaom1214/U-Transformer.     

Global-guided weakly-supervised learning for multi-label image classification

Multi-label classification with region-free labels is attracting increasing attention compared to that with region-based labels due to the time-consuming manual region-labeling process. Existing methods usually employ attention-based technology to discover the conspicuous label-related regions in a weakly-supervised manner with only image-level region-free labels, while the region covering is not precise without exploring global clues of multi-level features. To address this issue, a novel Global-guided Weakly-Supervised Learning (GWSL) method for multi-label classification is proposed. The GWSL first extracts the multi-level features to estimate their global correlation map which is further utilized to guide feature disentanglement in the proposed Feature Disentanglement and Localization (FDL) networks. Specifically, the FDL networks then adaptively combine the different correlated features and localize the fine-grained features for identifying multiple labels. The proposed method is optimized in an end-to-end manner under weakly supervision with only image-level labels. Experimental results demonstrate that the proposed method outperforms the state-of-the-arts for multi-label learning problems on several publicly available image datasets. To facilitate similar researches in the future, the codes are directly available online at https://github.com/Yong-DAI/GWSL.     

Self-Balanced R-CNN for instance segmentation

Current state-of-the-art two-stage models on instance segmentation task suffer from several types of imbalances. In this paper, we address the Intersection over the Union (IoU) distribution imbalance of positive input Regions of Interest (RoIs) during the training of the second stage. Our Self-Balanced R-CNN (SBR-CNN), an evolved version of the Hybrid Task Cascade (HTC) model, brings brand new loop mechanisms of bounding box and mask refinements. With an improved Generic RoI Extraction (GRoIE), we also address the feature-level imbalance at the Feature Pyramid Network (FPN) level, originated by a non-uniform integration between low- and high-level features from the backbone layers. In addition, the redesign of the architecture heads toward a fully convolutional approach with FCC further reduces the number of parameters and obtains more clues to the connection between the task to solve and the layers used. Moreover, our SBR-CNN model shows the same or even better improvements if adopted in conjunction with other state-of-the-art models. In fact, with a lightweight ResNet-50 as backbone, evaluated on COCO minival 2017 dataset, our model reaches 45.3% and 41.5% AP for object detection and instance segmentation, with 12 epochs and without extra tricks. The code is available at https://github.com/IMPLabUniPr/mmdetection/tree/sbr_cnn.     

Multi-stage feature-fusion dense network for motion deblurring

Although convolutional neural networks (CNNs) have recently shown considerable progress in motion deblurring, most existing methods that adopt multi-scale input schemes are still challenging in accurately restoring the heavily-blurred regions in blurry images. Several recent methods aim to further improve the deblurring effect using larger and more complex models, but these methods inevitably result in huge computing costs. To address the performance-complexity trade-off, we propose a multi-stage feature-fusion dense network (MFFDNet) for motion deblurring. Each sub-network of our MFFDNet has the similar structure and the same scale of input. Meanwhile, we propose a feature-fusion dense connection structure to reuse the extracted features, thereby improving the deblurring effect. Moreover, instead of using the multi-scale loss function, we only calculate the loss function at the output of the last stage since the input scale of our sub-network is invariant. Experimental results show that MFFDNet maintains a relatively small computing cost while outperforming state-of-the-art motion-deblurring methods. The source code is publicly available at: https://github.com/CaiGuoHS/MFFDNet_release.     

Hierarchical attention vision transformer for fine-grained visual classification

Recently, vision transformer has gained a breakthrough in image recognition. Its self-attention mechanism (MSA) can extract discriminative tokens information from different patches to improve image classification accuracy. However, the classification token in its deep layer ignore the local features between layers. In addition, the patch embedding layer feeds fixed-size patches into the network, which inevitably introduces additional image noise. Therefore, we propose a hierarchical attention vision transformer (HAVT) based on the transformer framework. We present a data augmentation method for attention cropping to crop and drop image noise and force the network to learn key features. Second, the hierarchical attention selection (HAS) module is proposed, which improves the network's ability to learn discriminative tokens between layers by filtering and fusing tokens between layers. Experimental results show that the proposed HAVT outperforms state-of-the-art approaches and significantly improves the accuracy to 91.8% and 91.0% on CUB-200–2011 and Stanford Dogs, respectively. We have released our source code on GitHub https://github.com/OhJackHu/HAVT.git.     

A super-resolution-based license plate recognition method for remote surveillance

With the continuous development of deep learning, neural networks have made great progress in license plate recognition (LPR). Nevertheless, there is still room to improve the performance of license plate recognition for low-resolution and relatively blurry images in remote surveillance scenarios. When it is difficult to enhance the recognition algorithm, we choose super-resolution (SR) to improve the quality of license plate images and thereby provide clearer input for the subsequent recognition stage. In this paper, we propose an automatic super-resolution license plate recognition (SRLPR) network which consists of four parts separately: license plate detection, character detection, single character super-resolution, and recognition. In the training stage, firstly, LP detection model needs to be trained alone and then its detection results will be used to successively train the three subsequent modules. During the test phase, for each input image, the network can get its LP number automatically. We also collect an applicable and challenging LPR dataset called SRLP, which is collected from real remote traffic surveillance. The experimental results demonstrate that our method achieves comprehensive quality of SR images and higher recognition accuracy compared with state-of-the-art methods. The SRLP dataset and the code for training and testing SRLPR network are available at https://pan.baidu.com/s/1vnhRa-c-dBj6jlfBZV5w4g.     

A new challenging image dataset with simple background for evaluating and developing co-segmentation algorithms

Many image co-segmentation algorithms have been proposed over the last decade. In this paper, we present a new dataset for evaluating co-segmentation algorithms, which contains 889 image groups with 18 images in each and the pixel-wise hand-annotated ground truths. The dataset is characterized by simple background produced from nearly a single color. It looks simple but is actually very challenging for current co-segmentation algorithms, because of four difficult cases in it: easy-confused foreground with background, transparent regions in objects, minor holes in objects, and shadows. In order to test the usefulness of our dataset, we review the state-of-the-art co-segmentation algorithms and evaluate seven algorithms on our dataset. The obtained performance of each algorithm is compared with those previously reported in the datasets with complex background. The results prove that our dataset is valuable for the development of co-segmentation techniques. It is more feasible to solve the four difficulties above on the simple background and then extend the solutions to the complex background problems. Our dataset can be freely downloaded from: http://www.iscbit.org/source/MLMR-COS.zip.     

TDFSSD: Top-Down Feature Fusion Single Shot MultiBox Detector

Object detection across different scales is challenging as the variances of object scales. Thus, a novel detection network, Top-Down Feature Fusion Single Shot MultiBox Detector (TDFSSD), is proposed. The proposed network is based on Single Shot MultiBox Detector (SSD) using VGG-16 as backbone with a novel, simple yet efficient feature fusion module, namely, the Top-Down Feature Fusion Module. The proposed module fuses features from higher-level features, containing semantic information, to lower-level features, containing boundary information, iteratively. Extensive experiments have been conducted on PASCAL VOC2007, PASCAL VOC2012, and MS COCO datasets to demonstrate the efficiency of the proposed method. The proposed TDFSSD network is trained end to end and outperforms the state-of-the-art methods across the three datasets. The TDFSSD network achieves 81.7% and 80.1% mAPs on VOC2007 and 2012 respectively, which outperforms the reported best results of both one-stage and two-stage frameworks. In the meantime, it achieves 33.4% mAP on MS COCO test-dev, especially 17.2% average precision (AP) on small objects. Thus all the results show the efficiency of the proposed method on object detection. Code and model are available at: https://github.com/dongfengxijian/TDFSSD.