Search

Oriented object detection in aerial images is a crucial link in earth observation. As a special parameter in oriented object representation, the angle is the key to achieving high-precision detection. However, the widely used regression-based methods suffer from boundary discontinuity problems due to the periodicity of the angle. To address this issue, we proposed a novel angle prediction method called fixed step trigonometric coder (FSTC). Exploiting the innate periodicity of trigonometric functions, FSTC can encode angles cyclically in a succinct, continuous, and uniform manner. Based on FSTC, we designed a single-shot oriented object detector, namely, a trigonometric-coded refined detector (TRDet), for high-precision object detection in real-time. TRDet consists of two modules: the anchor optimization module (AOM) and the object detection module (ODM). AOM employs FSTC to generate high-quality rotated anchors. In ODM, a dynamically weighted loss (DWL) was proposed to make the model focus on hard samples with higher angle deviation. Extensive experiments on DOTA and HRSC2016 show that both FSTC and TRDet can achieve competitive performance compared with peer works. [ABSTRACT FROM AUTHOR]

In this article, we propose BNAS-v2 to further improve the efficiency of broad neural architecture search (BNAS), which employs a broad convolutional neural network (BCNN) as the search space. In BNAS, the single-path sampling-updating strategy of an overparameterized BCNN leads to terrible unfair training issue, which restricts the efficiency improvement. To mitigate the unfair training issue, we employ a continuous relaxation strategy to optimize all paths of the overparameterized BCNN simultaneously. However, continuous relaxation leads to a performance collapse issue that leads to the unsatisfactory performance of the learned BCNN. For that, we propose the confident learning rate (CLR) and introduce the combination of partial channel connections and edge normalization. Experimental results show that 1) BNAS-v2 delivers state-of-the-art search efficiency on both CIFAR-10 (0.05 GPU days, which is $4\times $ faster than BNAS) and ImageNet (0.19 GPU days) with better or competitive performance; 2) the above two solutions are effectively alleviating the performance collapse issue; and 3) BNAS-v2 achieves powerful generalization ability on multiple transfer tasks, e.g., MNIST, FashionMNIST, NORB, and SVHN. The code is available at https://github.com/zixiangding/BNASv2 . [ABSTRACT FROM AUTHOR]

For a typical Scene Graph Generation (SGG) method in image understanding, there usually exists a large gap in the performance of the predicates’ head classes and tail classes. This phenomenon is mainly caused by the semantic overlap between different predicates as well as the long-tailed data distribution. In this paper, a Predicate Correlation Learning (PCL) method for SGG is proposed to address the above problems by taking the correlation between predicates into consideration. To measure the semantic overlap between highly correlated predicate classes, a Predicate Correlation Matrix (PCM) is defined to quantify the relationship between predicate pairs, which is dynamically updated to remove the matrix’s long-tailed bias. In addition, PCM is integrated into a predicate correlation loss function ($L_{PC}$) to reduce discouraging gradients of unannotated classes. The proposed method is evaluated on several benchmarks, where the performance of the tail classes is significantly improved when built on existing methods. [ABSTRACT FROM AUTHOR]

Constructing adversarial examples in a black-box threat model injures the original images by introducing visual distortion. In this paper, we propose a novel black-box attack approach that can directly minimize the induced distortion by learning the noise distribution of the adversarial example, assuming only loss-oracle access to the black-box network. To quantify visual distortion, the perceptual distance between the adversarial example and the original image, is introduced in our loss. We first approximate the gradient of the corresponding non-differentiable loss function by sampling noise from the learned noise distribution. Then the distribution is updated using the estimated gradient to reduce visual distortion. The learning continues until an adversarial example is found. We validate the effectiveness of our attack on ImageNet. Our attack results in much lower distortion when compared to the state-of-the-art black-box attacks and achieves 100% success rate on InceptionV3, ResNet50 and VGG16bn. Furthermore, we theoretically prove the convergence of our model. The code is publicly available at https://github.com/Alina-1997/visual-distortion-in-attack. [ABSTRACT FROM AUTHOR]

Spatial–temporal action detection in videos is a challenging problem that has attracted considerable attention in recent years. Most current approaches address action detection as an object detection problem, which utilizes successful object detection frameworks such as Faster R-CNN to operate action detection at every single frame first, and then generates action tubes by linking bounding boxes across the whole video in an offline fashion. However, unlike object detection in static images, temporal context information is vital for action detection in videos. Therefore, we propose an online action detection model that leverages the spatial–temporal context information existing in videos to perform action inference and localization. More specifically, we try to depict the spatial–temporal context pattern of actions via an encoder–decoder model that is based on a convolutional recurrent neural network. The model accepts a video snippet as input and encodes the dynamic information inside the snippet in the forward pass. During the backward pass, the decoder resolves the information for action detection with the current appearance or motion cue at each time stamp. In addition, we devise an incremental action-tube construction algorithm that enables our model to accomplish action prediction ahead of time and performs action detection in an online fashion. To evaluate the performance of our method, we conduct experiments on three popular public datasets UCF-101, UCF-Sports, and J-HMDB-21. The experimental results demonstrate that our method can achieve competitive or superior performance when compared to the state-of-the-art methods. To encourage further research, we release our project on “ https://github.com.hjjpku.OATD.” [ABSTRACT FROM AUTHOR]