Improving the performance of semantic segmentation models using multispectral information is crucial, especially for environments with low-light and adverse conditions. Multi-modal fusion techniques pursue either the learning of cross-modality features to generate a fused image or engage in knowledge distillation but address multimodal and missing modality scenarios as distinct issues, which is not an optimal approach for multi-sensor models. To address this, a novel multi-modal fusion approach called CSK-Net is proposed, which uses a contrastive learning-based spectral knowledge distillation technique along with an automatic mixed feature exchange mechanism for semantic segmentation in optical (EO) and infrared (IR) images. The distillation scheme extracts detailed textures from the optical images and distills them into the optical branch of CSK-Net. The model encoder consists of shared convolution weights with separate batch norm (BN) layers for both modalities, to capture the multi-spectral information from different modalities of the same objects. A Novel Gated Spectral Unit (GSU) and mixed feature exchange strategy are proposed to increase the correlation of modality-shared information and decrease the modality-specific information during the distillation process. Comprehensive experiments show that CSK-Net surpasses state-of-the-art models in multi-modal tasks and for missing modalities when exclusively utilizing IR data for inference across three public benchmarking datasets. For missing modality scenarios, the performance increase is achieved without additional computational costs compared to the baseline segmentation models.
Temporal knowledge graphs (TKGs) have been identified as a promising approach to represent the dynamics of facts along the timeline. The extrapolation of TKG is to predict unknowable facts happening in the future, holding significant practical value across diverse fields. Most extrapolation studies in TKGs focus on modeling global historical fact repeating and cyclic patterns, as well as local historical adjacent fact evolution patterns, showing promising performance in predicting future unknown facts. Yet, existing methods still face two major challenges: (1) They usually neglect the importance of historical information in KG snapshots related to the queries when encoding the local and global historical information; (2) They exhibit weak anti-noise capabilities, which hinders their performance when the inputs are contaminated with noise.To this end, we propose a novel \blue{Lo}cal-\blue{g}lobal history-aware \blue{C}ontrastive \blue{L}earning model (\blue{LogCL}) for TKG reasoning, which adopts contrastive learning to better guide the fusion of local and global historical information and enhance the ability to resist interference. Specifically, for the first challenge, LogCL proposes an entity-aware attention mechanism applied to the local and global historical facts encoder, which captures the key historical information related to queries. For the latter issue, LogCL designs four historical query contrast patterns, effectively improving the robustness of the model. The experimental results on four benchmark datasets demonstrate that LogCL delivers better and more robust performance than the state-of-the-art baselines.
The task of multimodal relation extraction has attracted significant research attention, but progress is constrained by the scarcity of available training data. One natural thought is to extend existing datasets with cross-modal generative models. In this paper, we consider a novel problem setting, where only unimodal data, either text or image, are available during training. We aim to train a multimodal classifier from synthetic data that perform well on real multimodal test data. However, training with synthetic data suffers from two obstacles: lack of data diversity and label information loss. To alleviate the issues, we propose Mutual Information-aware Multimodal Iterated Relational dAta GEneration (MI2RAGE), which applies Chained Cross-modal Generation (CCG) to promote diversity in the generated data and exploits a teacher network to select valuable training samples with high mutual information with the ground-truth labels. Comparing our method to direct training on synthetic data, we observed a significant improvement of 24.06% F1 with synthetic text and 26.42% F1 with synthetic images. Notably, our best model trained on completely synthetic images outperforms prior state-of-the-art models trained on real multimodal data by a margin of 3.76% in F1. Our codebase will be made available upon acceptance.
Early weakly supervised video grounding (WSVG) methods often struggle with incomplete boundary detection due to the absence of temporal boundary annotations. To bridge the gap between video-level and boundary-level annotation, explicit-supervision methods, i.e., generating pseudo-temporal boundaries for training, have achieved great success. However, data augmentations in these methods might disrupt critical temporal information, yielding poor pseudo boundaries. In this paper, we propose a new perspective that maintains the integrity of the original temporal content while introducing more valuable information for expanding the incomplete boundaries. To this end, we propose EtC (Expand then Clarify), first use the additional information to expand the initial incomplete pseudo boundaries, and subsequently refine these expanded ones to achieve precise boundaries. Motivated by video continuity, i.e., visual similarity across adjacent frames, we use powerful multimodal large language models (MLLMs) to annotate each frame within initial pseudo boundaries, yielding more comprehensive descriptions for expanded boundaries. To further clarify the noise of expanded boundaries, we combine mutual learning with a tailored proposal-level contrastive objective to use a learnable approach to harmonize a balance between incomplete yet clean (initial) and comprehensive yet noisy (expanded) boundaries for more precise ones. Experiments demonstrate the superiority of our method on two challenging WSVG datasets.
Reasoning with knowledge graphs (KGs) has primarily focused on triple-shaped facts. Recent advancements have been explored to enhance the semantics of these facts by incorporating more potent representations, such as hyper-relational facts. However, these approaches are limited to \emph{atomic facts}, which describe a single piece of information. This paper extends beyond \emph{atomic facts} and delves into \emph{nested facts}, represented by quoted triples where subjects and objects are triples themselves (e.g., ((\emph{BarackObama}, \emph{holds\_position}, \emph{President}), \emph{succeed\_by}, (\emph{DonaldTrump}, \emph{holds\_position}, \emph{President}))). These nested facts enable the expression of complex semantics like \emph{situations} over time and \emph{logical patterns} over entities and relations. In response, we introduce NestE, a novel KG embedding approach that captures the semantics of both atomic and nested factual knowledge. NestE represents each atomic fact as a $1\times3$ matrix, and each nested relation is modeled as a $3\times3$ matrix that rotates the $1\times3$ atomic fact matrix through matrix multiplication. Each element of the matrix is represented as a complex number in the generalized 4D hypercomplex space, including (spherical) quaternions, hyperbolic quaternions, and split-quaternions. Through thorough analysis, we demonstrate the embedding's efficacy in capturing diverse logical patterns over nested facts, surpassing the confines of first-order logic-like expressions. Our experimental results showcase NestE's significant performance gains over current baselines in triple prediction and conditional link prediction. The code and pre-trained models are open available at https://github.com/xiongbo010/NestE.
E-commerce search and recommendation usually operate on structured data such as product catalogs and taxonomies. However, creating better search and recommendation systems often requires a large variety of unstructured data including customer reviews and articles on the web. Traditionally, the solution has always been converting unstructured data into structured data through information extraction, and conducting search over the structured data. However, this is a costly approach that often has low quality. In this paper, we envision a solution that does entirely the opposite. Instead of converting unstructured data (web pages, customer reviews, etc) to structured data, we instead convert structured data (product inventory, catalogs, taxonomies, etc) into textual data, which can be easily integrated into the text corpus that trains LLMs. Then, search and recommendation can be performed through a Q/A mechanism through an LLM instead of using traditional information retrieval methods over structured data.
Our research addresses class imbalance issues in heterogeneous graphs using graph neural networks (GNNs). We propose a novel method combining the strengths of Generative Adversarial Networks (GANs) with GNNs, creating synthetic nodes and edges that effectively balance the dataset. This approach directly targets and rectifies imbalances at the data level. The proposed framework resolves issues such as neglecting graph structures during data generation and creating synthetic structures usable with GNN-based classifiers in downstream tasks. It processes node and edge information concurrently, improving edge balance through node augmentation and subgraph sampling. Additionally, our framework integrates a threshold strategy, aiding in determining optimal edge thresholds during training without time-consuming parameter adjustments. Experiments on the Amazon and Yelp Review datasets highlight the effectiveness of the framework we proposed, especially in minority node identification, where it consistently outperforms baseline models across key performance metrics, demonstrating its potential in the field.
End-to-end neural diarization with encoder-decoder based attractors (EEND-EDA) is a method to perform diarization in a single neural network. EDA handles the diarization of a flexible number of speakers by using an LSTM-based encoder-decoder that generates a set of speaker-wise attractors in an autoregressive manner. In this paper, we propose to replace EDA with a transformer-based attractor calculation (TA) module. TA is composed of a Combiner block and a Transformer decoder. The main function of the combiner block is to generate conversational dependent (CD) embeddings by incorporating learned conversational information into a global set of embeddings. These CD embeddings will then serve as the input for the transformer decoder. Results on public datasets show that EEND-TA achieves 2.68% absolute DER improvement over EEND-EDA. EEND-TA inference is 1.28 times faster than that of EEND-EDA.
In recent years, there have been studies to further improve the end-to-end neural speaker diarization (EEND) systems. This letter proposes the EEND-DEMUX model, a novel framework utilizing demultiplexed speaker embeddings. In this work, we focus on disentangling speaker-relevant information in the latent space and then transform each separated latent variable into its corresponding speech activity. EEND-DEMUX can directly obtain separated speaker embeddings through the demultiplexing operation in the inference phase without an external speaker diarization system, an embedding extractor, or a heuristic decoding technique. Furthermore, we employ a multi-head cross-attention mechanism to capture the correlation between mixture and separated speaker embeddings effectively. We formulate three loss functions based on matching, orthogonality, and sparsity constraints to learn robust demultiplexed speaker embeddings. The experimental results on the LibriMix dataset show consistently improved performance in both a fixed and flexible number of speakers scenarios.
Due to the scarcity and specific imaging characteristics in medical images, light-weighting Vision Transformers (ViTs) for efficient medical image segmentation is a significant challenge, and current studies have not yet paid attention to this issue. This work revisits the relationship between CNNs and Transformers in lightweight universal networks for medical image segmentation, aiming to integrate the advantages of both worlds at the infrastructure design level. In order to leverage the inductive bias inherent in CNNs, we abstract a Transformer-like lightweight CNNs block (ConvUtr) as the patch embeddings of ViTs, feeding Transformer with denoised, non-redundant and highly condensed semantic information. Moreover, an adaptive Local-Global-Local (LGL) block is introduced to facilitate efficient local-to-global information flow exchange, maximizing Transformer's global context information extraction capabilities. Finally, we build an efficient medical image segmentation model (MobileUtr) based on CNN and Transformer. Extensive experiments on five public medical image datasets with three different modalities demonstrate the superiority of MobileUtr over the state-of-the-art methods, while boasting lighter weights and lower computational cost. Code is available at https://github.com/FengheTan9/MobileUtr.