Search

Weather classification from single images is significant for many outdoor computer vision applications, while it has not been thoroughly studied. Existing methods view it as a supervised task under the guidance of weather labels. Though these methods have made great success, they are not applicable to real-world applications because of their reliance on massive human-annotated weather images. In this paper, we take the initial attempt to treat weather classification as an unsupervised task, i.e. to classify weather conditions from unlabeled outdoor images. Specifically, we propose a three-step unsupervised approach to automatically group images into weather clusters. In the first step, i.e. weather feature learning, semantically meaningful weather features are learned by employing a self-supervised task. Furthermore, we also introduce online triplet mining into the self-supervised task to extract discriminative weather features. In the second step, i.e. weather clustering, we design a learnable clustering method via mining the nearest neighbors and enforcing consistency between each sample and its nearest neighbors. To alleviate the uncertainty of weather clustering due to noisy nearest neighbors, we propose a self-labeling method as the third step to employ the already well-classified samples for fine-tuning. Experimental results on two publicly available weather image datasets demonstrate that the proposed approach achieves promising performance. [ABSTRACT FROM AUTHOR]

Forecasting the ocean dynamics is a critical issue for a wide array of climate extremes and environmental crisis. The dynamic variations are traditionally approached by relying on numerical models with all the related physical processes identified beforehand. An efficient alternative forecasting approach is based on the data-driven models. Despite their potential ability in modeling spatio-temporal ocean data, they ignore the fact that the ocean variables in different spatial regions and time periods typically have ever changing influences on each other, thus cannot yield satisfactory prediction results. In this paper, we develop a novel attention based dynamic graph for the ocean variable forecasting problem, which captures both the spatial and temporal dependencies. Specifically, we employ joint self-attention to incorporate information from the spatial graph over the target region, and model the graph evolution across long-range time steps. The performance of the proposed prediction model has been examined in the Indian Ocean based on ocean grid data products datasets. Experimental results demonstrate that this model has significant forecasting capability within 12 months, compared with the numerical methods and the state-of-the-art spatio-temporal embedding baselines. [ABSTRACT FROM AUTHOR]

Learning subtle and discriminative regions plays an important role in fine-grained image recognition, and attention mechanisms have shown great potential in such tasks. Recent research mainly focuses on employing the attention mechanism to locate key discriminative regions and learn salient features, whilst ignoring imperceptible complementary features and the causal relationship between prediction results and attention. To address the above issues, we propose an Attention Interaction and Counterfactual Attention Network (AICA-Net). Specifically, we propose an Attention Interaction Fusion Module (AIFM) to model the negative correlation between the attention map channels to locate the complementary features, and fuse the complementary features and key discriminative features to generate richer fine-grained features. Simultaneously, an Enhanced Counterfactual Attention Module (ECAM) is proposed to generate a counterfactual attention map. By comparing the impact of the learned attention map and the counterfactual attention map on the final prediction results, quantifying the quality of attention drives the network to learn more effective attention. Extensive experiments on CUB-200-2011, FGVC-Aircraft and Stanford Cars datasets have shown that our AICA-Net can get outstanding results. In particular, it achieves 90.83% and 95.87% accuracy on two open competitive benchmark datasets CUB-200-2011 and Stanford Cars, respectively. Experiments demonstrate that our method outperforms state-of-the-art solutions. [ABSTRACT FROM AUTHOR]

Discriminative correlation filter (DCF) based tracking algorithms have recently achieved excellent performance in challenging factors such as rotations and distractors. However, in case with fast motions and full occlusion, these trackers are not always effective and easily drift. In contrast, Siamese matching networks are insensitive to fast motions, but suffer from distractors. In this work, we propose an efficient real-time parallel framework for robust visual tracking. By incorporating DCF and Siamese network into the tracking framework to complement each other and better distinguish target objects from background clutters. Additionally, to improve tracking results and prevent target drift, we introduce an effective tracker switch method to select suitable tracker in each frame by considering the confidence estimation as well as motion smoothness, and examines the impact among all trackers over time. To validate the effectiveness of our method, we perform comprehensive experiments on three popular benchmark datasets, namely OTB2013, OTB2015, VOT2016, and TC128. The experimental results demonstrate that the proposed algorithm exhibits favorably results and real-time tracking speed against state-of-art trackers. [ABSTRACT FROM AUTHOR]