Recent studies have revealed that, beyond conventional accuracy, calibration should also be considered for training modern deep neural networks. To address miscalibration during learning, some methods have explored different penalty functions as part …
In spite of the dominant performances of deep neural networks, recent works have shown that they are poorly calibrated, resulting in over-confident predictions. Miscalibration can be exacerbated by overfitting due to the minimization of the …
Deep learning models have gained significant interest as a way of building hierarchical image representation. However, current models still perform far behind human vision system because of the lack of selective property, the lack of high-level …
How to build a suitable image representation remains a critical problem in computer vision. Traditional Bag-of-Feature (BoF) based models build image representation by the pipeline of local feature extraction, feature coding and spatial pooling. …
The bag of feature model is one of the most successful model to represent an image for classification task. However, the discrimination loss in the local appearance coding and the lack of spatial information hinder its performance. To address these …
The discovery of key and distinctive parts is critical for scene parsing and understanding. However, it is a challenging problem due to the weakly supervised condition, i.e., no annotation for parts is available. To address above issues, we propose a …
Recently, many deep networks are proposed to learn hierarchical image representation to replace traditional hand-designed features. To enhance the ability of the generative model to tackle discriminative computer vision tasks (e.g. image …