Mining deep features for accurate diagnosis of congenital abnormalities of retinal lens defects – We present the first ever study of the effect of the camera on the object detection. We study the effect of the camera in both the task of object detection and recognition. To this end, we present a new dataset that includes camera-detached objects and a novel object detection task. We use RGB-D image patches to detect objects with different shape, texture and appearance features and then exploit this information by projecting them onto camera-detached objects. We evaluate our approach using the PASCAL VOC dataset with and without features and show that our approach outperforms state-of-the-art methods.

In this paper we propose a novel, efficient method for supervised prediction of large-scale image retrieval. Firstly, we first learn a novel dataset with a large domain of labels and an efficient classifier model to predict future examples. Then, we train the classifier model with a weighted sum of the label weights of past examples. We also propose a novel deep learning based method for learning the label-preserving feature representations, to reduce the memory cost of the classifier. The proposed algorithm requires only $n$ samples in $n$ deep learning models. We evaluate our method on a large-scale set of data.

On the convergence of the gradient of the Hessian

An Empirical Comparison of the Accuracy of DPMM and BPM Ensembles at SimplotQL

Mining deep features for accurate diagnosis of congenital abnormalities of retinal lens defects

Online Voting for Social Good

High quality structured output learning using single-step gradient discriminant analysisIn this paper we propose a novel, efficient method for supervised prediction of large-scale image retrieval. Firstly, we first learn a novel dataset with a large domain of labels and an efficient classifier model to predict future examples. Then, we train the classifier model with a weighted sum of the label weights of past examples. We also propose a novel deep learning based method for learning the label-preserving feature representations, to reduce the memory cost of the classifier. The proposed algorithm requires only $n$ samples in $n$ deep learning models. We evaluate our method on a large-scale set of data.