Deep neural networks have been demonstrated to be vulnerable to adversarial attacks: sutle perturbations can completely change the classification results. Their vulnerability has led to a surge of research in this direction. However, most works dedicated to attacking anchor-based object detection models. In this work, we aim to present an effective and efficient algorithm to generate adversarial examples to attack anchor-free object models based on two approaches. First, we conduct category-wise instead of instance-wise attacks on the object detectors. Second, we leverage the high-level semantic information to generate the adversarial examples. Surprisingly, the generated adversarial examples it not only able to effectively attack the targeted anchor-free object detector but also to be transferred to attack other object detectors, even anchor-based detectors such as Faster R-CNN.
Prior knowledge of face shape and location plays an important role in face inpainting. However, traditional facing inpainting methods mainly focus on the generated image resolution of the missing portion but without consideration of the special particularities of the human face explicitly and generally produce discordant facial parts. To solve this problem, we present a stable variational latent generative model for large inpainting of face images. We firstly represent only face regions with the latent variable space but simultaneously constraint the random vectors to offer control over the distribution of latent variables, and combine with the non-face parts textures to generate a face image with plausible contents. Two adversarial discriminators are finally used to judge whether the generated distribution is close to the real distribution or not. It can not only synthesize novel image structures but also explicitly utilize the latent space with Eigenfaces to make better predictions. Furthermore, our work better evaluates the side face impainting problem. Experiments on both CelebA and CelebA-HQ face datasets demonstrate that our proposed approach generates higher quality inpainting results than existing ones.
The majority of existing human parsing methods formulate the task as semantic segmentation, which regard each semantic category equally and fail to exploit the intrinsic physiological structure of human body, resulting in inaccurate results. In this paper, we design a novel semantic neural tree for human parsing, which uses a tree architecture to encode physiological structure of human body, and designs a coarse to fine process in a cascade manner to generate accurate results. Specifically, the semantic neural tree is designed to segment human regions into multiple semantic subregions (e.g., face, arms, and legs) in a hierarchical way using a new designed attention routing module. Meanwhile, we introduce the semantic aggregation module to combine multiple hierarchical features to exploit more context information for better performance. Our semantic neural tree can be trained in an end-to-end fashion by standard stochastic gradient descent (SGD) with back-propagation. Several experiments conducted on four challenging datasets for both single and multiple human parsing, i.e., LIP, PASCAL-Person-Part, CIHP and MHP-v2, demonstrate the effectiveness of the proposed method. Code can be found at https://isrc.iscas.ac.cn/gitlab/research/sematree.
This paper proposes a space-time multi-scale attention network (STANet) to solve density map estimation, localization and tracking in dense crowds of video clips captured by drones with arbitrary crowd density, perspective, and flight altitude. Our STANet method aggregates multi-scale feature maps in sequential frames to exploit the temporal coherency, and then predict the density maps, localize the targets, and associate them in crowds simultaneously. A coarse-to-fine process is designed to gradually apply the attention module on the aggregated multi-scale feature maps to enforce the network to exploit the discriminative space-time features for better performance. The whole network is trained in an end-to-end manner with the multi-task loss, formed by three terms, i.e., the density map loss, localization loss and association loss. The non-maximal suppression followed by the min-cost flow framework is used to generate the trajectories of targets' in scenarios. Since existing crowd counting datasets merely focus on crowd counting in static cameras rather than density map estimation, counting and tracking in crowds on drones, we have collected a new large-scale drone-based dataset, DroneCrowd, formed by 112 video clips with 33,600 high resolution frames (i.e., 1920x1080) captured in 70 different scenarios. With intensive amount of effort, our dataset provides 20,800 people trajectories with 4.8 million head annotations and several video-level attributes in sequences. Extensive experiments are conducted on two challenging public datasets, i.e., Shanghaitech and UCF-QNRF, and our DroneCrowd, to demonstrate that STANet achieves favorable performance against the state-of-the-arts. The datasets and codes can be found at https://github.com/VisDrone.
In this paper, we describe a fast and light-weight portrait segmentation method based on a new {\em extremely light-weight backbone} (ELB) architecture. The core element of ELB is a {\em bottleneck-based factorized block} (BFB) that has much fewer parameters than existing alternatives while keeping good learning capacity. Consequently, the ELB-based portrait segmentation method can run faster (263.2FPS) than the existing methods yet retaining the competitive accuracy performance with state-of-the-arts. Experiments conducted on two benchmark datasets demonstrate the effectiveness and efficiency of our method.
Improving the efficiency of portrait segmentation is of great importance for the deployment on mobile devices. In this paper, we achieve the fast and light-weight portrait segmentation by introducing a new extremely light-weight backbone (ELB) architecture. The core element of ELB is a bottleneck-based factorized block (BFB), which can greatly reduce the number of parameters while keeping good learning capacity. Based on the proposed ELB architecture, we only use a single convolution layer as decoder to generate results. The ELB-based portrait segmentation method can run faster (263.2FPS) than existing methods yet retaining the competitive accuracy performance with state-of-the-arts. Experiments are conducted on two datasets, which demonstrates the efficacy of our method.
AI-synthesized face swapping videos, commonly known as the DeepFakes, have become an emerging problem recently. Correspondingly, there is an increasing interest in developing algorithms that can detect them. However, existing dataset of DeepFake videos suffer from low visual quality and abundant artifacts that do not reflect the reality of DeepFake videos circulated on the Internet. In this work, we present a new DeepFake dataset, Celeb-DF, for the development and evaluation of DeepFake detection algorithms. The Celeb-DF dataset is generated using a refined synthesis algorithm that reduces the visual artifacts observed in existing datasets. Based on the Celeb-DF dataset, we also benchmark existing DeepFake detection algorithms.
Object detection and counting are related but challenging problems, especially for drone based scenes with small objects and cluttered background. In this paper, we propose a new Guided Attention Network (GANet) to deal with both object detection and counting tasks based on the feature pyramid. Different from the previous methods relying on unsupervised attention modules, we fuse different scales of feature maps by using the proposed weakly-supervised Background Attention (BA) between the background and objects for more semantic feature representation. Then, the Foreground Attention (FA) module is developed to consider both global and local appearance of the object to facilitate accurate localization. Moreover, the new data argumentation strategy is designed to train a robust model in various complex scenes. Extensive experiments on three challenging benchmarks (i.e., UAVDT, CARPK and PUCPR+) show the state-of-the-art detection and counting performance of the proposed method compared with existing methods.