دانلود رایگان مقاله انگلیسی یادگیری برنامه درسی خوشه های بصری برای طبقه بندی چند کاره - الزویر 2018

abstract

Visual attributes, from simple objects (e.g., backpacks, hats) to soft-biometrics (e.g., gender, height, clothing) have proven to be a powerful representational approach for many applications such as image description and human identification. In this paper, we introduce a novel method to combine the advantages of both multi-task and curriculum learning in a visual attribute classification framework. Individual tasks are grouped after performing hierarchical clustering based on their correlation. The clusters of tasks are learned in a curriculum learning setup by transferring knowledge between clusters. The learning process within each cluster is performed in a multi-task classification setup. By leveraging the acquired knowledge, we speed-up the process and improve performance. We demonstrate the effectiveness of our method via ablation studies and a detailed analysis of the covariates, on a variety of publicly available datasets of humans standing with their full-body visible. Extensive experimentation has proven that the proposed approach boosts the performance by 4%–10%.

6. Conclusion

Given a set of tasks that need to be learned we sought to find an answer to how we can learn them effectively and what would be the optimal way in terms of performance, speed, and simplicity. Learning each task separately, although very simple, lacks in terms of performance since it does not exploit the information from other tasks. Learning all tasks at the same time in a multitask classification scenario is relatively fast, easy to implement, and employs knowledge from other tasks to boost the classification performance. Curriculum learning is a learning scheme in which samples or tasks are not treated as equally easy or hard, but are instead presented to the model in a meaningful way so as to increase generalization and performance. Since learning a large number of tasks one at a time is computationally expensive, we opted for learning clusters of tasks in a curriculum. In each cluster of visual attributes, we proposed to learn the corresponding tasks in a multi-task classification setup.

Our proposed method, CILICIA, finds the sequence in which clusters of visual attributes are learned very efficiently, and classifies them with high performance. Given images of standing humans as an input, we performed end-to-end learning by solving multiple binary classification problems simultaneously. Tasks were grouped into clusters by employing hierarchical agglomerative clustering based on their correlation. The sequence (i.e., curriculum) in which clusters were learned was found by computing the average cross-correlation within each cluster and sorting the obtained values in a descending order. During training of weakly correlated clusters of tasks, we leveraged the knowledge already learned from clusters which demonstrated stronger correlation. By these means, we combined the advantages of both multi-task and curriculum learning paradigms; since our method converges fast, it is effective and employs prior knowledge. We evaluated our method in three datasets and outperformed the state-of-the-art by 9.9% on the VIPeR dataset and by a recall rate of almost 4% (when the false positive rate is fixed and equal to 10%) on the PETA dataset despite the fact that no body part-specific information was employed. The obtained results demonstrate the effectiveness and, at the same time, the great potential of multi-task curriculum learning.