Multi-modal clustering aims to cluster data into different groups by exploring complementary information from multiple modalities or views. Little work learns the deep fused representations and simutaneously discovers the cluster structure with a discriminative loss. In this paper, we present an End-to-end Adversarial-attention network for Multi-modal Clustering (EAMC), where adversarial learning and attention mechanism are leveraged to align the latent feature distributions and quantify the importance of modalities respectively. To benefit from the joint training, we introducea divergence-based clustering objective that not only encourages the separation and compactness of the clusters but also enjoy a clear cluster structure by embedding the simplex geometry of the output space into the loss. The proposed network consists of modality-specific feature learning, modality fusion and cluster assignment three modules. It can be trained from scratch with batch-mode based optimization and avoid an autoencoder pretraining stage. Comprehensive experiments conducted on five real-world datasets show the superiority and effectiveness of the proposed clustering method.

The goal of person reidentification (Re-ID) is to identify a given pedestrian from a network of nonoverlapping surveillance cameras. Most existing works follow the supervised learning paradigm which requires pairwise labeled training data for each pair of cameras. However, this limits their scalability to real-world applications where abundant unlabeled data are available. To address this issue, we propose a multi-feature fusion with adaptive graph learning model for unsupervised Re-ID. Our model aims to negotiate comprehensive assessment on the consistent graph structure of pedestrians with the help of special information of feature descriptors. Specifically, we incorporate multi-feature dictionary learning and adaptive multi-feature graph learning into a unified learning model such that the learned dictionaries are discriminative and the subsequent graph structure learning is accurate. An alternating optimization algorithm with proved convergence is developed to solve the final optimization objective. Extensive experiments on four benchmark data sets demonstrate the superiority and effectiveness of the proposed method.

The success of batch mode active learning (BMAL) methods lies in selecting both representative and uncertain samples. Representative samples quickly capture the global structure of the whole dataset, while the uncertain ones refine the decision boundary. There are two principles, namely the direct approach and the screening approach, to make a trade-off between representativeness and uncertainty. Although widely used in literature, little is known about the relationship between these two principles. In this paper, we discover that the two approaches both have shortcomings in the initial stage of BMAL. To alleviate the shortcomings, we bound the certainty scores of unlabeled samples from below and directly combine this lower-bounded certainty with representativeness in the objective function. Additionally, we show that the two aforementioned approaches are mathematically equivalent to two special cases of our approach. To the best of our knowledge, this is the first work that tries to generalize the direct and screening approaches. The objective function is then solved by super-modularity optimization. Extensive experiments on fifteen datasets indicate that our method has significantly higher classification accuracy on testing data than the latest state-of-the-art BMAL methods, and also scales better even when the size of the unlabeled pool reaches 106.