MHTN: Modal-adversarial Hybrid Transfer Network for Cross-modal Retrieval

Cross-modal retrieval has drawn wide interest for retrieval across different modalities of data. However, existing methods based on DNN face the challenge of insufficient cross-modal training data, which limits the training effectiveness and easily leads to overfitting. Transfer learning is for relieving the problem of insufficient training data, but it mainly focuses on knowledge transfer only from large-scale datasets as single-modal source domain to single-modal target domain. Such large-scale single-modal datasets also contain rich modal-independent semantic knowledge that can be shared across different modalities. Besides, large-scale cross-modal datasets are very labor-consuming to collect and label, so it is significant to fully exploit the knowledge in single-modal datasets for boosting cross-modal retrieval. This paper proposes modal-adversarial hybrid transfer network (MHTN), which to the best of our knowledge is the first work to realize knowledge transfer from single-modal source domain to cross-modal target domain, and learn cross-modal common representation. It is an end-to-end architecture with two subnetworks: (1) Modal-sharing knowledge transfer subnetwork is proposed to jointly transfer knowledge from a large-scale single-modal dataset in source domain to all modalities in target domain with a star network structure, which distills modal-independent supplementary knowledge for promoting cross-modal common representation learning. (2) Modal-adversarial semantic learning subnetwork is proposed to construct an adversarial training mechanism between common representation generator and modality discriminator, making the common representation discriminative for semantics but indiscriminative for modalities to enhance cross-modal semantic consistency during transfer process. Comprehensive experiments on 4 widely-used datasets show its effectiveness and generality.

Cross-modal Common Representation Learning by Hybrid Transfer Network

DNN-based cross-modal retrieval is a research hotspot to retrieve across different modalities as image and text, but existing methods often face the challenge of insufficient cross-modal training data. In single-modal scenario, similar problem is usually relieved by transferring knowledge from large-scale auxiliary datasets (as ImageNet). Knowledge from such single-modal datasets is also very useful for cross-modal retrieval, which can provide rich general semantic information that can be shared across different modalities. However, it is challenging to transfer useful knowledge from single-modal (as image) source domain to cross-modal (as image/text) target domain. Knowledge in source domain cannot be directly transferred to both two different modalities in target domain, and the inherent cross-modal correlation contained in target domain provides key hints for cross-modal retrieval which should be preserved during transfer process. This paper proposes Cross-modal Hybrid Transfer Network (CHTN) with two subnetworks: Modal-sharing transfer subnetwork utilizes the modality in both source and target domains as a bridge, for transferring knowledge to both two modalities simultaneously; Layer-sharing correlation subnetwork preserves the inherent cross-modal semantic correlation to further adapt to cross-modal retrieval task. Cross-modal data can be converted to common representation by CHTN for retrieval, and comprehensive experiment on 3 datasets shows its effectiveness.

Query-adaptive Image Retrieval by Deep Weighted Hashing

Hashing methods have attracted much attention for large scale image retrieval. Some deep hashing methods have achieved promising results by taking advantage of the strong representation power of deep networks recently. However, existing deep hashing methods treat all hash bits equally. On one hand, a large number of images share the same distance to a query image due to the discrete Hamming distance, which raises a critical issue of image retrieval where fine-grained rankings are very important. On the other hand, different hash bits actually contribute to the image retrieval differently, and treating them equally greatly affects the retrieval accuracy of image. To address the above two problems, we propose the query-adaptive deep weighted hashing (QaDWH) approach, which can perform fine-grained ranking for different queries by weighted Hamming distance. First, a novel deep hashing network is proposed to learn the hash codes and corresponding class-wise weights jointly, so that the learned weights can reflect the importance of different hash bits for different image classes. Second, a query-adaptive image retrieval method is proposed, which rapidly generates hash bit weights for different query images by fusing its semantic probability and the learned class-wise weights. Fine-grained image retrieval is then performed by the weighted Hamming distance, which can provide more accurate ranking than the traditional Hamming distance. Experiments on four widely used datasets show that the proposed approach outperforms eight state-of-the-art hashing methods.

Fine-graind Image Classification via Combining Vision and Language

Fine-grained image classification is a challenging task due to the large intra-class variance and small inter-class variance, aiming at recognizing hundreds of sub-categories belonging to the same basic-level category. Most existing fine-grained image classification methods generally learn part detection models to obtain the semantic parts for better classification accuracy. Despite achieving promising results, these methods mainly have two limitations: (1) not all the parts which obtained through the part detection models are beneficial and indispensable for classification, and (2) fine-grained image classification requires more detailed visual descriptions which could not be provided by the part locations or attribute annotations. For addressing the above two limitations, this paper proposes the two-stream model combining vision and language (CVL) for learning latent semantic representations. The vision stream learns deep representations from the original visual information via deep convolutional neural network. The language stream utilizes the natural language descriptions which could point out the discriminative parts or characteristics for each image, and provides a flexible and compact way of encoding the salient visual aspects for distinguishing sub-categories. Since the two streams are complementary, combining the two streams can further achieves better classification accuracy. Comparing with 12 state-of-the-art methods on the widely used CUB-200-2011 dataset for fine-grained image classification, the experimental results demonstrate our CVL approach achieves the best performance.

Cross-media Similarity Metric Learning with Unified Deep Networks

As a highlighting research topic in the multimedia area, cross-media retrieval aims to capture the complex correlations among multiple media types. Learning better shared representation and distance metric for multimedia data is important to boost the cross-media retrieval. Motivated by the strong ability of deep neural network in feature representation and comparison functions learning, we propose the Unified Network for Cross-media Similarity Metric (UNCSM) to associate cross-media shared representation learning with distance metric in a unified framework. First, we design a two-pathway deep network pretrained with contrastive loss, and employ double triplet similarity loss for fine-tuning to learn the shared representation for each media type by modeling the relative semantic similarity. Second, the metric network is designed for effectively calculating the cross-media similarity of the shared representation, by modeling the pairwise similar and dissimilar constraints. Compared to the existing methods which mostly ignore the dissimilar constraints and only use sample distance metric as Euclidean distance separately, our UNCSM approach unifies the representation learning and distance metric to preserve the relative similarity as well as embrace more complex similarity functions for further improving the cross-media retrieval accuracy. The experimental results show that our UNCSM approach outperforms 8 state-of-the-art methods on 4 widely-used cross-media datasets.

Cross-modal Deep Metric Learning with Multi-task Regularization

DNN-based cross-modal retrieval has become a research hotspot, by which users can search results across various modalities like image and text. However, existing methods mainly focus on the pairwise correlation and reconstruction error of labeled data. They ignore the semantically similar and dissimilar constraints between different modalities, and cannot take advantage of unlabeled data. This paper proposes Cross-modal Deep Metric Learning with Multi-task Regularization (CDMLMR), which integrates quadruplet ranking loss and semi-supervised contrastive loss for modeling cross-modal semantic similarity in a unified multi-task learning architecture. The quadruplet ranking loss can model the semantically similar and dissimilar constraints to preserve cross-modal relative similarity ranking information. The semi-supervised contrastive loss is able to maximize the semantic similarity on both labeled and unlabeled data. Compared to the existing methods, CDMLMR exploits not only the similarity ranking information but also unlabeled cross-modal data, and thus boosts cross-modal retrieval accuracy.

Saliency-guided video classification via adaptively weighted learning

Video classification is productive in many practical applications, and the recent deep learning has greatly improved its accuracy. However, existing works often model video frames indiscriminately, but from the view of motion, video frames can be decomposed into salient and non-salient areas naturally. Salient and non-salient areas should be modeled with different networks, for the former present both appearance and motion information, and the latter present static background information. To address this problem, in this paper, video saliency is predicted by optical flow without supervision firstly. Then two streams of 3D CNN are trained individually for raw frames and optical flow on salient areas, and another 2D CNN is trained for raw frames on non-salient areas. For the reason that these three streams play different roles for each class, the weights of each stream are adaptively learned for each class. Experimental results show that saliency-guided modeling and adaptively weighted learning can reinforce each other, and we achieve the state-of-the-art results.

The Application of Two-level Attention Models in Deep Convolutional Neural Network for Fine-grained Image Classification

Fine-grained classification is challenging because categories can only be discriminated by subtle and local differences. Variances in the pose, scale or rotation usually make the problem more difficult. Most fine-grained classification systems follow the pipeline of finding foreground object or object parts (where) to extract discriminative features (what). In this paper, we propose to apply visual attention to fine-grained classification task using deep neural network. Our pipeline integrates three types of attention: the bottom-up attention that propose candidate patches, the object-level top-down attention that selects relevant patches to a certain object, and the part-level top-down attention that localizes discriminative parts. We combine these attentions to train domain-specific deep nets, then use it to improve both the what and where aspects. Importantly, we avoid using expensive annotations like bounding box or part information from end-to-end. The weak supervision constraint makes our work easier to generalize. We have verified the effectiveness of the method on the subsets of ILSVRC2012 dataset and CUB200_2011 dataset. Our pipeline delivered significant improvements and achieved the best accuracy under the weakest supervision condition. The performance is competitive against other methods that rely on additional annotations.

Robust Image Analysis by L1-Norm Semi-supervised Learning

This paper presents a novel L1-norm semi-supervised learning algorithm for robust image analysis by giving new L1-norm formulation of Laplacian regularization which is the key step of graph-based semi-supervised learning. Since our L1-norm Laplacian regularization is defined directly over the eigenvectors of the normalized Laplacian matrix, we successfully formulate semi-supervised learning as an L1-norm linear reconstruction problem which can be effectively solved with sparse coding. By working with only a small subset of eigenvectors, we further develop a fast sparse coding algorithm for our L1-norm semi-supervised learning. Due to the sparsity induced by sparse coding, the proposed algorithm can deal with the noise in the data to some extent and thus has important applications to robust image analysis, such as noise-robust image classification and noise reduction for visual and textual bag-of-words (BOW) models. In particular, this paper is the first attempt to obtain robust image representation by sparse co-refinement of visual and textual BOW models. The experimental results have shown the promising performance of the proposed algorithm.

Latent Semantic Learning with Structured Sparse Representation for Human Action Recognition

This paper proposes a novel latent semantic learning method for extracting high-level features (i.e. latent semantics) from a large vocabulary of abundant mid-level features (i.e. visual keywords) with structured sparse representation, which can help to bridge the semantic gap in the challenging task of human action recognition. To discover the manifold structure of midlevel features, we develop a spectral embedding approach to latent semantic learning based on L1-graph, without the need to tune any parameter for graph construction as a key step of manifold learning. More importantly, we construct the L1-graph with structured sparse representation, which can be obtained by structured sparse coding with its structured sparsity ensured by novel L1-norm hypergraph regularization over mid-level features. In the new embedding space, we learn latent semantics automatically from abundant mid-level features through spectral clustering. The learnt latent semantics can be readily used for human action recognition with SVM by defining a histogram intersection kernel. Different from the traditional latent semantic analysis based on topic models, our latent semantic learning method can explore the manifold structure of mid-level features in both L1-graph construction and spectral embedding, which results in compact but discriminative high-level features. The experimental results on the commonly used KTH action dataset and unconstrained YouTube action dataset show the superior performance of our method.