Recently the deep learning has shown its advantage in representation and clustering for time series data. Despite considerable progress, existing approaches mostly seek to train neural network by some instance reconstruction based or cluster distribution objective, which, however, lack ability exploit sample-wise (or augmentation-wise) contrastive information even higher-level (e.g., cluster-le...

Multiple instance learning (MIL) can reduce the need for costly annotation in tasks such as semantic segmentation by weakening the required degree of supervision. We propose a novel MIL formulation of multi-class semantic segmentation learning by a fully convolutional network. In this setting, we seek to learn a semantic segmentation model from just weak image-level labels. The model is trained...

When supervising an object detector with weakly labeled data, most existing approaches are prone to trapping in the discriminative object parts, e.g., finding the face of a cat instead of the full body, due to lacking the supervision on the extent of full objects. To address this challenge, we incorporate object segmentation into the detector training, which guides the model to correctly locali...

In many cases, human actions can be identified not only by the singular observation of the human body in motion, but also properties of the surrounding scene and the related objects. In this paper, we look into this problem and propose an approach for human action recognition that integrates multiple feature channels from several entities such as objects, scenes and people. We formulate the pro...

Statistical spam filters are known to be vulnerable to adversarial attacks. One of the more common adversarial attacks, known as the good word attack, thwarts spam filters by appending to spam messages sets of “good” words, which are words that are common in legitimate email but rare in spam. We present a counterattack strategy that attempts to differentiate spam from legitimate email in the in...

Most existing deep image clustering methods use only class-level representations for clustering. However, the representation alone is not sufficient to describe differences between images belonging same cluster. This may lead high intra-class differences, which will harm performance. To address this problem, paper proposes a model named Deep Image Clustering based on Label Similarity and Maximi...