Search

In computer vision, an important challenge to deep neural networks comes from adjusting the varying properties of different image domains. To study this problem, researchers have been investigating a practical setting in which the deep neural networks are trained on a labeled source domain and then transferred to an unlabeled or even unseen target domain. The major difficulty lies in the potential domain gap, which essentially arises from the overfitting in the source domain. Hence, it is important to introduce generalized priors to alleviate the issue. From this perspective, this paper presents a novel framework that forces visual features to align with domain-agnostic priors (DAP). Specifically, we study two kinds of priors, (i) language-guided embedding and (ii) class-level relationship, and we believe that more such priors can be constructed. Our framework, referred to as DAP, is evaluated on both unsupervised domain adaptation (UDA) and domain generalization (DG) where the target domain is unlabeled and even unseen, respectively. We use the standard benchmark that performs transfer semantic segmentation on synthesized datasets (i.e., GTAv and SYNTHIA) and a real dataset (i.e., Cityscapes). Experiments validate the effectiveness of DAP with competitive accuracy in all tasks. In particular, language-guided priors work sufficiently well for UDA, while class-level priors serve as useful complements for DG. The proposed frameworks shed light that domain transfer benefits from better proxies, possibly from other modalities. [ABSTRACT FROM AUTHOR]

With the increasing popularity of Unmanned Aerial Vehicles (UAVs) in computer vision-related applications, intelligent UAV video analysis has recently attracted the attention of an increasing number of researchers. To facilitate research in the UAV field, this paper presents a UAV dataset with 100 videos featuring approximately 2700 vehicles recorded under unconstrained conditions and 840k manually annotated bounding boxes. These UAV videos were recorded in complex real-world scenarios and pose significant new challenges, such as complex scenes, high density, small objects, and large camera motion, to the existing object detection and tracking methods. These challenges have encouraged us to define a benchmark for three fundamental computer vision tasks, namely, object detection, single object tracking (SOT) and multiple object tracking (MOT), on our UAV dataset. Specifically, our UAV benchmark facilitates evaluation and detailed analysis of state-of-the-art detection and tracking methods on the proposed UAV dataset. Furthermore, we propose a novel approach based on the so-called Context-aware Multi-task Siamese Network (CMSN) model that explores new cues in UAV videos by judging the consistency degree between objects and contexts and that can be used for SOT and MOT. The experimental results demonstrate that our model could make tracking results more robust in both SOT and MOT, showing that the current tracking and detection methods have limitations in dealing with the proposed UAV benchmark and that further research is indeed needed. [ABSTRACT FROM AUTHOR]

Fluidization of non-spherical particles is very common in petroleum engineering. Understanding the complex phenomenon of non-spherical particle flow is of great significance. In this paper, coupled with two-fluid model, the drag coefficient correlation based on artificial neural network was applied in the simulations of a bubbling fluidized bed filled with non-spherical particles. The simulation results were compared with the experimental data from the literature. Good agreement between the experimental data and the simulation results reveals that the modified drag model can accurately capture the interaction between the gas phase and solid phase. Then, several cases of different particles, including tetrahedron, cube, and sphere, together with the nylon beads used in the model validation, were employed in the simulations to study the effect of particle shape on the flow behaviors in the bubbling fluidized bed. Particle shape affects the hydrodynamics of non-spherical particles mainly on microscale. This work can be a basis and reference for the utilization of artificial neural network in the investigation of drag coefficient correlation in the dense gas–solid two-phase flow. Moreover, the proposed drag coefficient correlation provides one more option when investigating the hydrodynamics of non-spherical particles in the gas–solid fluidized bed. [ABSTRACT FROM AUTHOR]

An intrinsic challenge of person re-identification (re-ID) is the annotation difficulty. This typically means (1) few training samples per identity and (2) thus the lack of diversity among the training samples. Consequently, we face high risk of over-fitting when training the convolutional neural network (CNN), a state-of-the-art method in person re-ID. To reduce the risk of over-fitting, this paper proposes a Pseudo-Positive Regularization method to enrich the diversity of the training data. Specifically, unlabeled data from an independent pedestrian database are retrieved using the target training data as query. A small proportion of these retrieved samples are randomly selected as the Pseudo-Positive samples and added to the target training set for the supervised CNN training. The addition of Pseudo-Positive samples is therefore a Data Augmentation method to reduce the risk of over-fitting during CNN training. We implement our idea in the identification CNN models (i.e., CaffeNet, VGGNet-16 and ResNet-50). On CUHK03 and Market-1501 datasets, experimental results demonstrate that the proposed method consistently improves the baseline and yields competitive performance to the state-of-the-art person re-ID methods. [ABSTRACT FROM AUTHOR]

State-of-the-art image classification approaches are mainly based on robust image representation, such as the bag-of-features (BoF) model or the convolutional neural network (CNN) architecture. In real applications, the orientation (left/right) of an image or an object might vary from sample to sample, whereas some handcrafted descriptors (e.g., SIFT) and network operations (e.g., convolution) are not reversal-invariant, leading to the unsatisfied stability of image features extracted from these models. To deal with, a popular solution is to augment the dataset by adding a left-right reversed copy for each image. This strategy improves the recognition accuracy to some extent, but also brings the price of almost doubled time and memory consumptions on both the training and testing stages. In this paper, we present an alternative solution based on designing reversal-invariant representation of local patterns, so that we can obtain the identical representation for an image and its left-right reversed copy. For the BoF model, we design a reversal-invariant version of SIFT descriptor named Max-SIFT, a generalized RIDE algorithm which can be applied to a large family of local descriptors. For the CNN architecture, we present a simple idea of generating reversal-invariant deep features ( RI-Deep), and, inspired by which, design reversal-invariant convolution ( RI-Conv) layers to increase the CNN capacity without increasing the model complexity. Experiments reveal consistent accuracy gain on various image classification tasks, including scene understanding, fine-grained object recognition, and large-scale visual recognition. [ABSTRACT FROM AUTHOR]

This paper considers the task of image search using the Bag-of-Words (BoW) model. In this model, the precision of visual matching plays a critical role. Conventionally, local cues of a keypoint, e.g., SIFT, are employed. However, such strategy does not consider the contextual evidences of a keypoint, a problem which would lead to the prevalence of false matches. To address this problem and enable accurate visual matching, this paper proposes to integrate discriminative cues from multiple contextual levels, i.e., local, regional, and global, via probabilistic analysis. 'True match' is defined as a pair of keypoints corresponding to the same scene location on all three levels (Fig. 1). Specifically, the Convolutional Neural Network (CNN) is employed to extract features from regional and global patches. We show that CNN feature is complementary to SIFT due to its semantic awareness and compares favorably to several other descriptors such as GIST, HSV, etc. To reduce memory usage, we propose to index CNN features outside the inverted file, communicated by memory-efficient pointers. Experiments on three benchmark datasets demonstrate that our method greatly promotes the search accuracy when CNN feature is integrated. We show that our method is efficient in terms of time cost compared with the BoW baseline, and yields competitive accuracy with the state-of-the-arts. [ABSTRACT FROM AUTHOR]