United States

Open-vocabulary Scene Graph Generation (OV-SGG) overcomes the limitations of the closed-set assumption by aligning visual relationship representations with open-vocabulary textual representations. This enables the identification of novel visual relationships, making it applicable to real-world scenarios with diverse relationships.  However, existing OV-SGG methods are constrained by fixed text representations, limiting diversity and accuracy in image-text alignment.  To address these challenges, we propose the Relation-Aware Hierarchical Prompting (RAHP) framework, which enhances text representation by integrating subject-object and region-specific relation information.  Our approach employs entity clustering to manage the complexity of the relation triplet category space, ensuring the practicality of incorporating subject-object information.  Additionally, we utilize a large language model (LLM) to generate detailed region-aware prompts, capturing fine-grained visual interactions and improving alignment between visual and textual modalities.  RAHP also introduces a dynamic selection mechanism within Vision-Language Models (VLMs), which adaptively selects relevant text prompts based on the visual content, reducing noise from irrelevant prompts.  Extensive experiments on the Visual Genome and Open Images v6 datasets demonstrate that our framework consistently achieves state-of-the-art performance, demonstrating its effectiveness in addressing the challenges of open-vocabulary scene graph generation.

AAAI 2025

Relation-aware Hierarchical Prompt for Open-vocabulary Scene Graph Generation

scene analysis understanding

We are pleased to announce the Thirty-Ninth AAAI Conference on Artificial Intelligence (AAAI-25), which will be held in Philadelphia, Pennsylvania at the Pennsylvania Convention Center from February 25 to March 4, 2025.

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines. AAAI-25 will feature technical paper presentations, special tracks, invited speakers, workshops, tutorials, poster sessions, senior member presentations, competitions, and exhibit programs, and a range of other activities to be announced.

### [Invited Speakers](https://aaai.org/conference/aaai/aaai-25/aaai-25-invited-speakers/)

Register [here](https://aaai.org/conference/aaai/aaai-25/registration/)

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines. AAAI-25 will feature technical paper presentations, special tracks, invited speakers, workshops, tutorials, poster sessions, senior member presentations, competitions, and exhibit programs, and a range of other activities to be announced.



poster

Blind face video restoration aims to restore high-fidelity details from videos subjected to complex and unknown degradations. This task poses a significant challenge of managing temporal heterogeneity while at the same time maintaining stable face attributes. In this paper, we introduce a Discrete Prior-based Temporal-Coherent content prediction transformer to address the challenge, and our model is referred to as DP-TempCoh. Specifically, we incorporate a spatial-temporal-aware content prediction module to synthesize high-quality content from discrete visual priors, conditioned on degraded video tokens. To further enhance the temporal coherence of the predicted content, a motion statistics modulation module is designed to adjust the content, based on discrete motion priors in terms of cross-frame mean and variance. As a result, the statistics of the predicted content can match with that of real videos over time. By performing extensive experiments, we verify the effectiveness of the design elements and demonstrate the superior performance of our DP-TempCoh in both synthetically and naturally degraded video restoration.

Discrete Prior-based Temporal-coherent Content Prediction for Blind Face Video Restoration

Federated learning (FL) is a promising technology for data privacy and distributed optimization, but it suffers from data imbalance and heterogeneity among clients. Existing FL methods try to solve the problems by aligning client with server model or by correcting client model with control variables. These methods excel on IID and general Non-IID data but perform mediocrely in Simpson's Paradox scenarios. Simpson's Paradox refers to the phenomenon that the trend observed on the global dataset disappears or reverses on a subset, which may lead to the fact that global model obtained through aggregation in FL does not accurately reflect the distribution of global data. Thus, we propose FedCFA, an novel FL framework employing counterfactual learning to generate counterfactual samples by replacing local data critical factors with global average data, aligning local data distributions with the global and mitigating Simpson's Paradox effects.In addition, to improve the counterfactual samples quality, we introduce factor decorrelation (FDC) loss to reduce the correlation among features and thus improve the independence of extracted factors.We conduct extensive experiments on six datasets and verify that our method outperforms other FL methods in terms of efficiency and global model accuracy under limited communication rounds.

FedCFA: Alleviating Simpson's Paradox in Model Aggregation with Counterfactual Federated Learning

If unaligned multimodal medical images can be simultaneously aligned and fused using a single-stage approach within a unified processing framework, it will not only achieve mutual promotion of dual tasks but also help reduce the complexity of the model. However, the design of this model faces the challenge of incompatible requirements for feature fusion and alignment; specifically, feature alignment requires consistency among corresponding features, whereas feature fusion requires the features to be complementary to each other. To address this challenge, this paper proposes an unaligned medical image fusion method called Bidirectional Stepwise Feature Alignment and Fusion (BSFA-F) strategy. To reduce the negative impact of modality differences on cross-modal feature matching, we incorporate the Modal Discrepancy-Free Feature Representation (MDF-FR) method into BSFA-F. MDF-FR utilizes a Modality Feature Representation Head (MFRH) to integrate the global information of the input image. By injecting the information contained in MFRH of the current image into other modality images, it effectively reduces the impact of modality differences on feature alignment while preserving the complementary information carried by different images. In terms of feature alignment, BSFA-F employs a bidirectional stepwise alignment deformation field prediction strategy based on the path independence of vector displacement between two points. This strategy solves the problem of large spans and inaccurate deformation field prediction in single-step alignment. Finally, Multi-Modal Feature Fusion block achieves the fusion of aligned features. The experimental results across multiple datasets demonstrate the effectiveness of our method.

BSAFusion: A Bidirectional Stepwise Feature Alignment Network for Unaligned Medical Image Fusion

Word definition is the most fundamental and crucial linguistic concept. Any changes in word definition lead to changes in the theoretical system of the respective language. Traditionally, researchers in Natural Language Processing (NLP) for Vietnamese texts believe Vietnamese words are constructed from syllables. However, their works did not explicitly mention which linguistic theory they followed for this assumption. Although there are no theoretical guarantees, most NLP studies in Vietnamese accept this assumption. Consequently, word segmentation is recognized as one of the essential stages in NLP for Vietnamese texts. In this study, we address the role of word segmentation for Vietnamese texts from the linguistic perspective. Through our extensive experiments, we show that, based on linguistic theories, performing word segmentation in Vietnamese is not required. Moreover, we present a novel method, \textbf{Vi}etnamese \textbf{Word} Trans\textbf{Former} (ViWordFormer), for modeling Vietnamese word formation. Experimental results indicate that our method is appropriate for modeling Vietnamese word formation from both theoretical and experimental aspects and embark a novel approach to Vietnamese word representation. The implementation of our proposed method is available at this link\footnote{The implementation will be publicly available upon the acceptance of this paper.}.

Vietnamese Words Are Not Constructed from Syllables: Rethinking the Role of Word Segmentation in Natural Language Processing for Vietnamese Texts

Recently segment anything model (SAM) has shown powerful segmentation capability and has drawn great attention in computer vision fields. Massive following works have developed various applications based on the pretrained SAM and achieved impressive performance on downstream vision tasks. However, SAM consists of heavy architectures and requires massive computational capacity, which hinders the further application of SAM on computation constrained edge devices. To this end, in this paper we propose a framework to obtain a tiny segment anything model (TinySAM) while maintaining the strong zero-shot performance. We first propose a full-stage knowledge distillation method with hard prompt sampling and hard mask weighting strategy to distill a lightweight student model. We also adapt the post-training quantization to the promptable segmentation task and further reduce the computational cost. Moreover, a hierarchical segmenting everything strategy is proposed to accelerate the everything inference by $2\times$ with almost no performance degradation. With all these proposed methods, our TinySAM leads to orders of magnitude computational reduction and pushes the envelope for efficient segment anything task. Extensive experiments on various zero-shot transfer tasks demonstrate the significantly advantageous performance of our TinySAM against counterpart methods.

TinySAM: Pushing the Envelope for Efficient Segment Anything Model

Spherical Sliced-Wasserstein (SSW) has recently been proposed to measure the discrepancy between spherical data distributions in various fields, such as geology, medical domains, computer vision, and deep representation learning. However, in the original SSW, all projection directions are treated equally, which is too idealistic and cannot accurately reflect the importance of different projection directions for various data distributions. To address this issue, we propose a novel data-adaptive Discriminative Spherical Sliced-Wasserstein (DSSW) distance, which utilizes a projected energy function to determine the discriminative projection direction for SSW. In our new DSSW, we introduce two types of projected energy functions to generate the weights for projection directions with complete theoretical guarantees. The first type employs a non-parametric deterministic function that transforms the projected Wasserstein distance into its corresponding weight in each projection direction. This improves the performance of the original SSW distance with negligible additional computational overhead. The second type utilizes a neural network-induced function that learns the projection direction weight through a parameterized neural network based on data projections. This further enhances the performance of the original SSW distance with less extra computational overhead. Finally, we evaluate the performance of our proposed DSSW by comparing it with several state-of-the-art methods across a variety of machine learning tasks, including gradient flows, density estimation on real earth data, and self-supervised learning.

Towards Better Spherical Sliced-Wasserstein Distance Learning with Data-Adaptive Discriminative Projection Direction

Learning concept prerequisite relations helps better master and build a logically coherent knowledge structure. Many studies use graph neural networks to create heterogeneous knowledge networks that enhance concept representations. However, different types of relations in these networks can influence each other. Existing research often focuses solely on concept relations, neglecting other types of knowledge connections. To address this issue, this paper proposes a novel concept prerequisite relation learning model, named the Global Knowledge Relation Optimization Model(GKROM). Specifically, we capture the impact of different knowledge relation types on document and concept semantic representations separately, integrating the document and concept semantic representations. Then, we introduce multi-objective learning to optimize the knowledge relation network from a global perspective. Through the above optimization, GKROM learns richer semantic representations for concepts and documents, improving the accuracy of concept prerequisite relation learning. Extensive experiments on public datasets confirm the method's effectiveness, achieving state-of-the-art performance in concept prerequisite relation learning. Our code is available at https://anonymous.4open.science/r/GKROM.

Learning Concept Prerequisite Relation via Global Knowledge Relation Optimization

Decoupling domain-variant information (DVI) from domain-invariant information (DII) serves as a prominent strategy for mitigating domain shifts in the practical implementation of deep learning algorithms. However, in medical settings, concerns surrounding data collection and privacy often restrict access to both training and test data, hindering the empirical decoupling of information by existing methods. To tackle this issue, we propose an Autonomous Information Filter-driven Source-free Domain Adaptation (AIF-SFDA) algorithm, which leverages a frequency-based learnable information filter to autonomously decouple DVI and DII. Information Bottleneck (IB) and Self-supervision (SS) are incorporated to optimize the learnable frequency filter. The IB governs the information flow within the filter to diminish redundant DVI, while SS preserves DII in alignment with the specific task and image modality. Thus, the autonomous information filter can overcome domain shifts relying solely on target data. A series of experiments covering various medical image modalities and segmentation tasks were conducted to demonstrate the benefits of AIF-SFDA through comparisons with leading algorithms and ablation studies.

AIF-SFDA: Autonomous Information Filter driven Source-Free Domain Adaptation for Medical Image Segmentation

Graph Neural Networks (GNNs) are widely used in graph data mining tasks. Traditional GNNs follow a message passing scheme that can effectively utilize local and structural information. However, the phenomena of over-smoothing and over-squashing limit the receptive field in message passing processes. Graph Transformers were introduced to address these issues, achieving a global receptive field but suffering from the noise of irrelevant nodes and loss of structural information. Therefore, drawing inspiration from fine-grained token-based representation learning in Natural Language Processing (NLP), we propose the Structure-aware Multi-token Graph Transformer (Tokenphormer), which generates multiple tokens to effectively capture local and structural information and explore global information at different levels of granularity. Specifically, we first introduce the walk-token generated by mixed walks consisting of four walk types to explore the graph and capture structure and contextual information flexibly. To ensure local and global information coverage, we also introduce the SGPM-token (obtained through the Self-supervised Graph Pre-train Model, SGPM) and the hop-token, extending the length and density limit of the walk-token, respectively. Finally, these expressive tokens are fed into the Transformer model to learn node representations collaboratively. Experimental results demonstrate that the capability of the proposed Tokenphormer can achieve state-of-the-art performance on node classification tasks.

Tokenphormer: Structure-aware Multi-token Graph Transformer for Node Classification

Recent studies have shown that neighborhood aggregation (NA) and contrastive learning (CL) exacerbate the impact of fake users, making GNN-based RSs more vulnerable to shilling attacks. However, existing defense mechanisms predominantly focus on white-box scenarios, overlooking the compounded vulnerabilities introduced by NA and CL architectures. Therefore, we propose a novel black-box universal training framework for GNN-based RSs, specifically designed to address two critical research questions: (i) How can we accurately identify fake interaction data under strict black-box settings? (ii) How to effectively mitigate the impact of residual malicious samples when complete detection is infeasible?

Downloads

Next from AAAI 2025

Discrete Prior-based Temporal-coherent Content Prediction for Blind Face Video Restoration

Similar lecture

Scene Graph-Grounded Image Generation

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from AAAI 2025

Discrete Prior-based Temporal-coherent Content Prediction for Blind Face Video Restoration

Similar lecture

Scene Graph-Grounded Image Generation

Downloads