Device-to-device (D2D) communication underlay cellular networks is a promising technique to improve spectrum efficiency. In this situation, D2D transmission may cause severe interference to both the cellular and other D2D links, which imposes a great technical challenge to spectrum allocation. Existing centralized schemes require global information, which causes a large signaling overhead. While existing distributed schemes requires frequent information exchange among D2D users and cannot achieve global optimization. In this paper, a distributed spectrum allocation framework based on multi-agent deep reinforcement learning is proposed, named multi-agent actor critic (MAAC). MAAC shares global historical states, actions and policies during centralized training, requires no signal interaction during execution and utilizes cooperation among users to further optimize system performance. Moreover, in order to decrease the computing complexity of the training, we further propose the neighbor-agent actor critic (NAAC) based on the neighbor users' historical information for centralized training. The simulation results show that the proposed MAAC and NAAC can effectively reduce the outage probability of cellular links, greatly improve the sum rate of D2D links and converge quickly.

Visual Semantic Embedding (VSE) is a dominant method for cross-modal vision-language retrieval. Its purpose is to learn an embedding space so that visual data can be embedded in a position close to the corresponding text description. However, there are large intra-class variations in the vision-language data. For example, multiple texts describing the same image may be described from different views, and the descriptions of different views are often dissimilar. The mainstream VSE method embeds samples from the same class in similar positions, which will suppress intra-class variations and lead to inferior generalization performance. This paper proposes a Multi-View Visual Semantic Embedding (MV-VSE) framework, which learns multiple embeddings for one visual data and explicitly models intra-class variations. To optimize MV-VSE, a multi-view upper bound loss is proposed, and the multi-view embeddings are jointly optimized while retaining intra-class variations. MV-VSE is plug-and-play and can be applied to various VSE models and loss functions without excessively increasing model complexity. Experimental results on the Flickr30K and MS-COCO datasets demonstrate the superior performance of our framework.

Image-Text Matching (ITM) aims to establish the correspondence between images and sentences. ITM is fundamental to various vision and language understanding tasks. However, there are limitations in the way existing ITM benchmarks are constructed. The ITM benchmark collects pairs of images and sentences during construction. Therefore, only samples that are paired at collection are annotated as positive. All other samples are annotated as negative. Many correlations are missed in these samples that are annotated as negative. For example, a sentence matches only one image at the time of collection. Only this image is annotated as positive for the sentence. All other images are annotated as negative. However, these negative images may contain images that correspond to the sentences. These mislabeled samples are called false negatives . Existing ITM models are optimized based on annotations containing mislabels, which can introduce noise during training. In this paper, we propose an ITM framework integrating Language Guidance ( LG ) for correcting false negatives. A language pre-training model is introduced into the ITM framework to identify false negatives. To correct false negatives, we propose language guidance loss, which adaptively corrects the locations of false negatives in the visual-semantic embedding space. Extensive experiments on two ITM benchmarks show that our method can improve the performance of existing ITM models. To verify the performance of correcting false negatives, we conduct further experiments on ECCV Caption. ECCV Caption is a verified dataset where false negatives in annotations have been corrected. The experimental results show that our method can recall more relevant false negatives. The code is available at https://github.com/AAA-Zheng/LG_ITM .

Video-text retrieval is a crucial task that has been a powerful application for multi-media data analysis and attracted tremendous interest in the research area. The core steps are feature representations and alignment to overcome the heterogeneous gap between videos and texts. Existing methods not only take advantage of multi-modal information in videos but also explore local alignment to enhance retrieval accuracy. Although performing well, these methods seem deficient at three perspectives: a) The semantic correlations between different modal features are not considered, which introduces irrelevant noise in feature representations. b) The cross-modal relations and temporal associations are ambiguously learned by a single self-attention manipulation. c) The training signal to optimize the semantic topic assignment for local alignment is missing. In this paper, we proposed a novel Temporal Multi-modal Graph Transformer with Global-Local Alignment (TMMGT-GLA) for video-text retrieval. We model the input video as a sequence of semantic correlation graphs to exploit the structural information between multi-modal features. Graph and temporal self-attention layers are leveraged on the semantic correlation graphs to effectively learn cross-modal relations and temporal associations respectively. For local alignment, the encoded video and text features are assigned to a set of shared semantic topics, and the distances between residuals from the same ones are minimized. To optimize the assignments, a minimum entropy-based regularization term is proposed for training the overall framework. Experimental results are carried out on the MSR-VTT, LSMDC, and ActivityNet Captions datasets. Our method outperforms previous approaches by a large margin and achieves state-of-the-art performance.

Device-to-device (D2D) communication has been recognized as a promising technique to improve spectrum efficiency. However, D2D transmission as an underlay causes severe interference, which imposes a technical challenge to spectrum allocation. Existing centralized schemes require global information, which can cause serious signaling overhead. While existing distributed solution requires frequent information exchange between users and cannot achieve global optimization. In this paper, a distributed spectrum allocation framework based on multi-agent deep reinforcement learning is proposed, named Neighbor-Agent Actor Critic (NAAC). NAAC uses neighbor users' historical information for centralized training but is executed distributedly without that information, which not only has no signal interaction during execution, but also utilizes cooperation between users to further optimize system performance. The simulation results show that the proposed framework can effectively reduce the outage probability of cellular links, improve the sum rate of D2D links and have good convergence.

Due to high labeling cost, it is inevitable to introduce a certain proportion of noisy correspondence into visual-text datasets, resulting in poor model robustness for cross-modal matching. Although recent methods divide the datasets into clean and noisy pair subsets to yield promising achievements, they still suffer from deep neural networks over-fitting on noisy correspondence. In particular, the similar positive pairs with partially relevant semantic correspondence are easily partitioned into noisy pair subset by mistake without carefully selection, which brings harmful impact on robust learning. Meanwhile, the similar negative pairs with partially relevant semantic correspondence lead to ambiguous distance relations in common space learning, which also damages the stability of performance. To solve the coarse-grained dataset division problem, we propose Correspondence Tri-Partition Rectifier (CTPR) to partition the training set into clean, hard, and noisy pair subsets based on the memorization effect of neural networks and prediction inconsistency. Then, we refine the correspondence labels for each subset to indicate the real semantic correspondence between visual-text pairs. The differences between rectified labels of anchors and hard negatives are recast as the adaptive margin in the improved triplet loss for robust training in a co-teaching manner. To verify the effectiveness and robustness of our method, we conduct experiments by implementing image-text and video-text matching as two showcases. Extensive experiments on Flickr30 K, MS-COCO, MSR-VTT, and LSMDC datasets verify that our method successfully partitions the visual-text pairs according to their semantic correspondence and improves performance under noisy data training.