Fine-grained text-to-image retrieval aims to retrieve a fine-grained target image with a given text query. Existing methods typically assume that each training image is accurately depicted by its textual descriptions. However, textual descriptions can be ambiguous and fail to depict discriminative visual details in images, leading to inaccurate representation learning. To alleviate the effects of text ambiguity, we propose a Multi-Modal Reference learning framework to learn robust representations. We first propose a multi-modal reference construction module to aggregate all visual and textual details of the same object into a comprehensive multi-modal reference. The multi-modal reference hence facilitates the subsequent representation learning and retrieval similarity computation. Specifically, a reference-guided representation learning module is proposed to use multi-modal references to learn more accurate visual and textual representations. Additionally, we introduce a reference-based refinement method that employs the object references to compute a reference-based similarity that refines the initial retrieval results. Extensive experiments are conducted on five fine-grained text-to-image retrieval datasets for different text-to-image retrieval tasks. The proposed method has achieved superior performance over state-of-the-art methods. For instance, on the text-to-person image retrieval dataset RSTPReid, our method achieves the Rank1 accuracy of 56.2%, surpassing the recent CFine by 5.6%.

Deep domain adaptation methods have achieved appealing performance by learning transferable representations from a well-labeled source domain to a different but related unlabeled target domain. Most existing works assume source and target data share the identical label space, which is often difficult to be satisfied in many real-world applications. With the emergence of big data, there is a more practical scenario called partial domain adaptation, where we are always accessible to a more large-scale source domain while working on a relative small-scale target domain. In this case, the conventional domain adaptation assumption should be relaxed, and the target label space tends to be a subset of the source label space. Intuitively, reinforcing the positive effects of the most relevant source subclasses and reducing the negative impacts of irrelevant source subclasses are of vital importance to address partial domain adaptation challenge. This paper proposes an efficiently-implemented Deep Residual Correction Network (DRCN) by plugging one residual block into the source network along with the task-specific feature layer, which effectively enhances the adaptation from source to target and explicitly weakens the influence from the irrelevant source classes. Specifically, the plugged residual block, which consists of several fully-connected layers, could deepen basic network and boost its feature representation capability correspondingly. Moreover, we design a weighted class-wise domain alignment loss to couple two domains by matching the feature distributions of shared classes between source and target. Comprehensive experiments on partial, traditional and fine-grained cross-domain visual recognition demonstrate that DRCN is superior to the competitive deep domain adaptation approaches.

Visual domain adaptation aims to seek an effective transferable model for unlabeled target images by benefiting from the well-labeled source images following different distributions. Many recent efforts focus on extracting domain-invariant image representations via exploring target pseudo labels, predicted by the source classifier, to further mitigate the conditional distribution shift across domains. However, two essential factors are overlooked by most existing methods: 1) the learned transferable features should be not only domain invariant but also category discriminative; and 2) the target pseudo label is a two-edged sword to cross-domain alignment. In other words, the wrongly predicted target labels may hinder the class-wise domain matching. In this article, to address these two issues simultaneously, we propose a discriminative transfer feature and label consistency (DTLC) approach for visual domain adaptation problems, which can naturally unify cross-domain alignment with discriminative information preserved and label consistency of source and target data into one framework. To be specific, DTLC first incorporates class discriminative information by penalizing the maximum distance of data pair in the same class and the minimum distance of data pair sharing the different labels for each data into the distribution alignment of both domains. The target pseudo labels are then refined based on the label consistency within the domains. Thus, the transfer feature learning and coarse-to-fine target labels would be coupled to benefit each other in an iterative way. Comprehensive experiments on several visual cross-domain benchmarks verify that DTLC can gain remarkable margins over state-of-the-art (SOTA) nondeep visual domain adaptation methods and even be comparable to competitive deep domain adaptation ones.

Domain adaptation aims to transfer the enriched label knowledge from large amounts of source data to unlabeled target data. It has raised significant interest in multimedia analysis. Existing researches mainly focus on learning domain-wise transferable representations via statistical moment matching or adversarial adaptation techniques, while ignoring the class-wise mismatch across domains, resulting in inaccurate distribution alignment. To address this issue, we propose a Joint Adversarial Domain Adaptation (JADA) approach to simultaneously align domain-wise and class-wise distributions across source and target in a unified adversarial learning process. Specifically, JADA attempts to solve two complementary minimax problems jointly. The feature generator aims to not only fool the well-trained domain discriminator to learn domain-invariant features, but also minimize the disagreement between two distinct task-specific classifiers' predictions to synthesize target features near the support of source class-wisely. As a result, the learned transferable features will be equipped with more discriminative structures, and effectively avoid mode collapse. Additionally, JADA enables an efficient end-to-end training manner via a simple back-propagation scheme. Extensive experiments on several real-world cross-domain benchmarks, including VisDA-2017, ImageCLEF, Office-31 and digits, verify that JADA can gain remarkable improvements over other state-of-the-art deep domain adaptation approaches.

Automatic multi-document abstractive summarization system is used to summarize several documents into a short one with generated new sentences. Many of them are based on word-graph and ILP method, and lots of sentences are ignored because of the heavy computation load. To reduce computation and generate readable and informative summaries, we propose a novel abstractive multi-document summarization system based on chunk-graph (CG) and recurrent neural network language model (RNNLM). In our approach, A CG which is based on word-graph is constructed to organize all information in a sentence cluster, CG can reduce the size of graph and keep more semantic information than word-graph. We use beam search and character-level RNNLM to generate readable and informative summaries from the CG for each sentence cluster, RNNLM is a better model to evaluate sentence linguistic quality than n-gram language model. Experimental results show that our proposed system outperforms all baseline systems and reach the state-of-art systems, and the system with CG can generate better summaries than that with ordinary word-graph.