Search

Accurately matching visual and textual data in cross-modal retrieval has been widely studied in the multimedia community. To address these challenges posited by the heterogeneity gap and the semantic gap, we propose integrating Shannon information theory and adversarial learning. In terms of the heterogeneity gap, we integrate modality classification and information entropy maximization adversarially. For this purpose, a modality classifier (as a discriminator) is built to distinguish the text and image modalities according to their different statistical properties. This discriminator uses its output probabilities to compute Shannon information entropy, which measures the uncertainty of the modality classification it performs. Moreover, feature encoders (as a generator) project uni-modal features into a commonly shared space and attempt to fool the discriminator by maximizing its output information entropy. Thus, maximizing information entropy gradually reduces the distribution discrepancy of cross-modal features, thereby achieving a domain confusion state where the discriminator cannot classify two modalities confidently. To reduce the semantic gap, Kullback-Leibler (KL) divergence and bi-directional triplet loss are used to associate the intra- and inter-modality similarity between features in the shared space. Furthermore, a regularization term based on KL-divergence with temperature scaling is used to calibrate the biased label classifier caused by the data imbalance issue. Extensive experiments with four deep models on four benchmarks are conducted to demonstrate the effectiveness of the proposed approach., Accepted by Pattern Recognition

Deep learning for fine-grained image retrieval in an incremental context is less investigated. In this paper, we explore this task to realize the model's continuous retrieval ability. That means, the model enables to perform well on new incoming data and reduce forgetting of the knowledge learned on preceding old tasks. For this purpose, we distill semantic correlations knowledge among the representations extracted from the new data only so as to regularize the parameters updates using the teacher-student framework. In particular, for the case of learning multiple tasks sequentially, aside from the correlations distilled from the penultimate model, we estimate the representations for all prior models and further their semantic correlations by using the representations extracted from the new data. To this end, the estimated correlations are used as an additional regularization and further prevent catastrophic forgetting over all previous tasks, and it is unnecessary to save the stream of models trained on these tasks. Extensive experiments demonstrate that the proposed method performs favorably for retaining performance on the already-trained old tasks and achieving good accuracy on the current task when new data are added at once or sequentially.

Convolutional neural network training can suffer from diverse issues like exploding or vanishing gradients, scaling-based weight space symmetry and covariant-shift. In order to address these issues, researchers develop weight regularization methods and activation normalization methods. In this work we propose a weight soft-regularization method based on the Oblique manifold. The proposed method uses a loss function which pushes each weight vector to have a norm close to one, i.e. the weight matrix is smoothly steered toward the so-called Oblique manifold. We evaluate our method on the very popular CIFAR-10, CIFAR-100 and ImageNet 2012 datasets using two state-of-the-art architectures, namely the ResNet and wide-ResNet. Our method introduces negligible computational overhead and the results show that it is competitive to the state-of-the-art and in some cases superior to it. Additionally, the results are less sensitive to hyperparameter settings such as batch size and regularization factor.

The focus of this survey is on the analysis of two modalities of multimodal deep learning: image and text. Unlike classic reviews of deep learning where monomodal image classifiers such as VGG, ResNet and Inception module are central topics, this paper will examine recent multimodal deep models and structures, including auto-encoders, generative adversarial nets and their variants. These models go beyond the simple image classifiers in which they can do uni-directional (e.g. image captioning, image generation) and bi-directional (e.g. cross-modal retrieval, visual question answering) multimodal tasks. Besides, we analyze two aspects of the challenge in terms of better content understanding in deep multimodal applications. We then introduce current ideas and trends in deep multimodal feature learning, such as feature embedding approaches and objective function design, which are crucial in overcoming the aforementioned challenges. Finally, we include several promising directions for future research., Accepted by Neurocomputing

During the long history of computer vision, one of the grand challenges has been semantic segmentation which is the ability to segment an unknown image into different parts and objects (e.g., beach, ocean, sun, dog, swimmer). Furthermore, segmentation is even deeper than object recognition because recognition is not necessary for segmentation. Specifically, humans can perform image segmentation without even knowing what the objects are (for example, in satellite imagery or medical X-ray scans, there may be several objects which are unknown, but they can still be segmented within the image typically for further investigation). Performing segmentation without knowing the exact identity of all objects in the scene is an important part of our visual understanding process which can give us a powerful model to understand the world and also be used to improve or augment existing computer vision techniques. Herein this work, we review the field of semantic segmentation as pertaining to deep convolutional neural networks. We provide comprehensive coverage of the top approaches and summarize the strengths, weaknesses and major challenges.

Recent studies have shown that image representations built upon deep convolutional layers in Convolutional Neural Networks (CNNs) have strong discriminative characteristics. In this paper, we present a novel and effective method to create compact binary codes (deep binary codes) based on deep convolutional features for image retrieval. Deep binary codes are generated by comparing the response from each feature map and the average response across all the feature maps on the deep convolutional layers. Additionally, a spatial cross-summing strategy is proposed to directly generate bit-scalable binary codes. As the deep binary codes on different deep layers can be obtained by passing the image through the CNN and each of them makes a different contribution to the search accuracy, we then present a dynamic, on-the-fly late fusion approach where the top N high quality search scores from deep binary codes are automatically determined online and fused to further enhance the retrieval precision. Two strengths of the proposed methods are that the generation of deep binary codes is based on a generic model, which does not require additional training for new image domains, and that the dynamic late fusion scheme is query adaptive. Extensive experimental results on well known benchmarks show that the performance of deep binary codes are competitive with state-of-the-art approaches for large scale image retrieval. Moreover, it is shown that the dynamic late fusion scheme significantly enhances the search accuracy.

Cross-modal hash retrieval has received considerable interest in the area of deep learning. Here hash codes of data of different modalities are learned where pair-wise loss functions control feature similarity in a shared embedding space. In this paper we improve on feature similarity by using Shannon's information entropy with respect to the modality information that is left in learning superior hash codes. We introduce a novel network for predicting the domain from the learned features while the protagonist network uses a loss function based on Shannon's information entropy to learn to maximize the domain uncertainty and therefore the information content. Additionally, according to the number of common labels between each similar image-text pair, we define a multi-level similarity matrix as supervisory information, which constrains all similar pairs with different weights. We show with extensive experiments that our novel approach to domain uncertainty leads to a cross-modal hash retrieval that outperforms the state-of-the-art.

Person re-identification (Re-ID) aims at matching images of the same person where images are captured by non-overlapping camera views distributed at different locations. To solve this problem, most recent works require a large pre-labeled dataset for training a deep model. These methods are not always suitable for real-world applications, because the latter often lack labeled data. In order to tackle this drawback, we proposed a novel Domain-Invariant Embedding Network (DIEN) to learn a domain-invariant embedding (DIE) feature by introducing a multi-loss joint learning with Recurrent Top- Down Attention (RTDA) mechanism. Due to the improvement in traditional triplet loss, our proposed model can benefit from both source-domain (labeled) data and target-domain (unlabeled) data. Furthermore, the resulting DIE feature not only has improved class discrimination but also robustness to domain shift. We compared our method with recent competitive algorithms and also evaluated the effectiveness of the proposed modules.

Fashion style transfer has attracted significant attention because it both has interesting scientific challenges and it is also important to the fashion industry. This paper focuses on addressing a practical problem in fashion style transfer, person-to-person clothing swapping, which aims to visualize what the person would look like with the target clothes worn on another person instead of dressing them physically. This problem remains challenging due to varying pose deformations between different person images. In contrast to traditional nonparametric methods that blend or warp the target clothes for the reference person, in this paper we propose a multistage deep generative approach named SwapGAN that exploits three generators and one discriminator in a unified framework to fulfill the task end-to-end. The first and second generators are conditioned on a human pose map and a segmentation map, respectively, so that we can simultaneously transfer the pose style and the clothes style. In addition, the third generator is used to preserve the human body shape during the image synthesis process. The discriminator needs to distinguish two fake image pairs from the real image pair. The entire SwapGAN is trained by integrating the adversarial loss and the mask-consistency loss. The experimental results on the DeepFashion dataset demonstrate the improvements of SwapGAN over other existing approaches through both quantitative and qualitative evaluations. Moreover, we conduct ablation studies on SwapGAN and provide a detailed analysis about its effectiveness.

In numerous multimedia and multi-modal tasks from image and video retrieval to zero-shot recognition to multimedia question and answering, bridging image and text representations plays an important and in some cases an indispensable role. To narrow the modality gap between vision and language, prior approaches attempt to discover their correlated semantics in a common feature space. However, these approaches omit the intra-modal semantic consistency when learning the inter-modal correlations. To address this problem, we propose cycle-consistent embeddings in a deep neural network for matching visual and textual representations. Our approach named as CycleMatch can maintain both inter-modal correlations and intra-modal consistency by cascading dual mappings and reconstructed mappings in a cyclic fashion. Moreover, in order to achieve a robust inference, we propose to employ two late-fusion approaches: average fusion and adaptive fusion. Both of them can effectively integrate the matching scores of different embedding features, without increasing the network complexity and training time. In the experiments on cross-modal retrieval, we demonstrate comprehensive results to verify the effectiveness of the proposed approach. Our approach achieves state-of-the-art performance on two well-known multi-modal datasets, Flickr30K and MSCOCO.

Feature detectors and descriptors have been successfully used for various computer vision tasks, such as video object tracking and content-based image retrieval. Many methods use image gradients in different stages of the detection-description pipeline to describe local image structures. Recently, some, or all, of these stages have been replaced by convolutional neural networks (CNNs), in order to increase their performance. A detector is defined as a selection problem, which makes it more challenging to implement as a CNN. They are therefore generally defined as regressors, converting input images to score maps and keypoints can be selected with non-maximum suppression. This paper discusses and compares several recent methods that use CNNs for keypoint detection. Experiments are performed both on the CNN based approaches, as well as a selection of conventional methods. In addition to qualitative measures defined on keypoints and descriptors, the bag-of-words (BoW) model is used to implement an image retrieval application, in order to determine how the methods perform in practice. The results show that each type of features are best in different contexts., Comment: 5 pages, 3 figures, 3 tables, CBMI 2019