Canada

With the ability to collect vast amounts of image and natural language data from the web, there has been a remarkable advancement in Large-scale Language Models (LLMs). This progress has led to the emergence of chatbots and dialogue systems capable of fluent conversations with humans. As the variety of devices enabling interactions between humans and agents expands, and the performance of text-based dialogue systems improves, there has been recently proposed research on visual dialog. However, visual dialog requires understanding sequences of pairs consisting of images and sentences, making it challenging to gather sufficient data for training large-scale models from the web. In this paper, we propose a new multimodal learning method leveraging existing large-scale models designed for each modality, to enable model training for visual dialog with small visual dialog datasets. The key ideas of our approach are: 1) storing the history or context during the progression of visual dialog in the form of spatiotemporal graphs, and 2) introducing small modulation blocks between modality-specific models and the graphs to align the semantic spaces. For implementation, we introduce a novel structure-aware cross-attention method, which retrieves relevant image and text knowledge for utterance generation from the pretrained models. For experiments, we achieved a new state-of-the-art performance on three visual dialog datasets, including the most challenging one COMET.

AAAI 2024

Structure-Aware Multimodal Sequential Learning for Visual Dialog | VIDEO

multimodal learning

representation learning

language grounding

technical paper

We are pleased to announce the Thirty-Eighth AAAI Conference on Artificial Intelligence (AAAI-24), which will be held in Vancouver, British Columbia at the Vancouver Convention Centre – West Building from 20-27 February, 2024.

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-24 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.

We expect for AAAI-24 to be an in-person conference – one author of all accepted papers will be expected to present work in person unless there are exceptional circumstances that prevent this.<br><br><br><br>

In order to access the AAAI-24 event page you need to register [here](https://aaai.org/aaai-conference/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. 

Description-based person search aims to retrieve images of the target identity via textual descriptions. One of the challenges for this task is to extract discriminative representation from images and descriptions. Most existing methods apply the part-based split method or external models to explore the fine-grained details of local features, which ignore the global relationship between partial information and cause network instability. To overcome these issues, we propose a Multi-modal Disordered Representation Learning Network (MDRL) for description-based person search to fully extract the visual and textual representations. Specifically, we design a Cross-modality Global Feature Learning Architecture to learn the global features from the two modalities and meet the demand of the task. Based on our global network, we introduce a Disorder Local Learning Module to explore local features by a disordered reorganization strategy from both visual and textual aspects and enhance the robustness of the whole network. Besides, we introduce a Cross-modality Interaction Module to guide the two streams to extract visual or textual representations considering the correlation between modalities. Extensive experiments are conducted on two public datasets, and the results show that our method outperforms the state-of-the-art methods on CUHK-PEDES and ICFG-PEDES datasets and achieves superior performance.

Multi-Modal Disordered Representation Learning Network for Description-Based Person Search

The current neuron reconstruction pipeline for electron microscopy (EM) data usually includes automatic image segmentation followed by extensive human expert proofreading. In this work, we aim to reduce human workload by predicting connectivity between over-segmented neuron pieces, taking both microscopy image and 3D morphology features into account, similar to human proofreading workflow. To this end, we first construct a dataset, named FlyTracing, that contains millions of pairwise connections of segments expanding the whole fly brain, which is three orders of magnitude larger than existing datasets for neuron segment connection. To learn sophisticated biological imaging features from the connectivity annotations, we propose a novel connectivity-aware contrastive learning method to generate dense volumetric EM image embedding. The learned embeddings can be easily incorporated with any point or voxel-based morphological representations for automatic neuron tracing. Extensive comparisons of different combination schemes of image and morphological representation in identifying split errors across the whole fly brain demonstrate the superiority of the proposed approach, especially for the locations that contain severe imaging artifacts, such as section missing and misalignment. The dataset and code are available at https://github.com/Levishery/Flywire-Neuron-Tracing.

Learning Multimodal Volumetric Features for Large-Scale Neuron Tracing

Modern subgraph-finding algorithm implementations consist of thousands of lines of highly optimized code, and this complexity raises questions about their trustworthiness.  Recently, some state-of-the-art subgraph solvers have been enhanced to output machine-verifiable proofs that their results are correct.  While this significantly improves reliability, it is not a fully satisfactory solution,  since end-users have to trust both the proof checking algorithms and the translation of the high-level graph problem into a low-level 0-1 integer linear program (ILP) used for the proofs.
    
In this work, we present the first formally verified toolchain capable of full end-to-end verification for subgraph solving, which closes both of these trust gaps.  We have built encoder frontends for various graph problems together with a 0-1 ILP (a.k.a. pseudo-Boolean) proof checker, all implemented and formally verified in the CakeML ecosystem.  This toolchain is flexible and extensible, and we use it to build verified proof checkers for both decision and optimization graph problems, namely, subgraph isomorphism, maximum clique, and maximum common (connected) induced subgraph.  Our experimental evaluation shows that end-to-end formal verification is now feasible for a wide range of hard graph problems.

End-to-End Verification for Subgraph Solving

The watch time is a significant indicator of user satisfaction in video recommender systems. However, the prediction of watch time as a target variable is often hindered by its highly imbalanced distribution with a scarcity of observations for larger target values and over-populated samples for small values. State-of-the-art watch time prediction models discretize the continuous watch time into a set of buckets in order to consider the distribution of watch time. However, it is highly uninvestigated how these discrete buckets should be created from the continuous watch time distribution, and existing discretization approaches suffer from either a large learning error or a large restoration error. To address this challenge, we propose a Classification-Restoration framework with Error-Adaptive-Discretization (CREAD) to accurately predict the watch time. The proposed framework contains a discretization module, a classification module, and a restoration module. It predicts the watch time through multiple classification problems. The discretization process is a key contribution of the CREAD framework. We theoretically analyze the impacts of the discretization on the learning error and the restoration error, and then propose the error-adaptive discretization (EAD) technique to better balance the two errors, which achieves better performance over traditional discretization approaches. We conduct detailed offline evaluations on a public dataset and an industrial dataset, both showing performance gains through the proposed approach. Moreover, We have fully launched our framework to an online video platform, which resulted in a significant increase in users' video watch time by 0.29$\%$ through A/B testing. These results highlight the effectiveness of the CREAD framework in watch time prediction in video recommender systems.

CREAD: A Classification-Restoration Framework with Error Adaptive Discretization for Watch Time Prediction in Video Recommender Systems

Learning to collaborate has witnessed significant progress in multi-agent reinforcement learning (MARL). However, promoting coordination among agents and enhancing exploration capabilities remain challenges. In multi-agent environments, interactions between agents are limited in specific situations. Effective collaboration between agents thus requires a nuanced understanding of when and how agents' actions influence others.To this end, in this paper, we propose a novel MARL algorithm named Situation-Dependent Causal Influence-Based Cooperative Multi-agent Reinforcement Learning (SCIC), which incorporates a novel Intrinsic reward mechanism based on a new cooperation criterion measured by situation-dependent causal influence among agents.Our approach aims to detect inter-agent causal influences in specific situations based on the criterion using causal intervention and conditional mutual information. This effectively assists agents in exploring states that can positively impact other agents, thus promoting cooperation between agents.The resulting update links coordinated exploration and intrinsic reward distribution, which enhance overall collaboration and performance.Experimental results on various MARL benchmarks demonstrate the superiority of our method compared to state-of-the-art approaches.

Situation-Dependent Causal Influence-Based Cooperative Multi-Agent Reinforcement Learning

For generative learning tasks, there are three crucial criteria for generating samples from the models: quality,  coverage/diversity, and sampling speed. Among the existing generative models, Generative adversarial networks (GANs) and diffusion models demonstrate outstanding quality performance while suffering from notable limitations. GANs can generate high-quality results and enable fast sampling, their drawbacks, however, lie in the limited diversity of the generated samples. On the other hand, diffusion models excel at generating high-quality results with a commendable diversity. Yet, its iterative generation process necessitates hundreds to thousands of sampling steps, leading to slow speeds that are impractical for real-time scenarios. To address the aforementioned problem, this paper proposes a novel Consistency-GAN model. In particular, to aid in the training of the GAN, we introduce instance noise, which employs consistency models using only a few steps compared to the conventional diffusion process. Our evaluations on various datasets indicate that our approach significantly accelerates sampling speeds compared to traditional diffusion models, while preserving sample quality and diversity. Furthermore, our approach also has better model coverage than traditional adversarial training methods.

Consistency-GAN: Training GANs with Consistency Model

Neural Radiance Fields (NeRF) have garnered remarkable success in novel view synthesis. Nonetheless, the task of generating high-quality images for novel views persists as a critical challenge. While the existing efforts have exhibited commendable progress, capturing intricate details, enhancing textures, and achieving superior Peak Signal-to-Noise Ratio (PSNR) metrics warrant further focused attention and advancement. In this work, we propose NeRF-VPT, an innovative method for novel view synthesis to address these challenges. Our proposed NeRF-VPT employs a cascading view prompt tuning paradigm, wherein RGB information gained from preceding rendering outcomes serves as instructive visual prompts for subsequent rendering stages, with the aspiration that the prior knowledge embedded in the prompts can facilitate the gradual enhancement of rendered image quality. NeRF-VPT only requires sampling RGB data from previous stage renderings as priors at each training stage, without relying on extra guidance or complex techniques. Thus, our NeRF-VPT is plug-and-play and can be readily integrated into existing methods. By conducting comparative analyses of our NeRF-VPT against several NeRF-based approaches on demanding real-scene benchmarks, such as Realistic Synthetic 360, Real Forward-Facing, Replica dataset, and a user-captured dataset, we substantiate that our NeRF-VPT significantly elevates baseline performance and proficiently generates more high-quality novel view images than all the compared state-of-the-art methods. Furthermore, the cascading learning of NeRF-VPT introduces adaptability to scenarios with sparse inputs, resulting in a significant enhancement of accuracy for sparse-view novel view synthesis. The source code and dataset are available at https://github.com/Freedomcls/NeRF-VPT.

NeRF-VPT: Learning Novel View Representations with Neural Radiance Fields via View Prompt Tuning

Protein structure-based property prediction has emerged as a promising approach for various biological tasks, such as protein function prediction and sub-cellular location estimation. The existing methods highly rely on experimental protein structure data and fail in scenarios where these data are unavailable. Predicted protein structures from AI tools (e.g., AlphaFold2) were utilized as alternatives. However, we observed that current practices, which simply employ accurately predicted structures during inference, suffer from notable degradation in prediction accuracy. While similar phenomena have been extensively studied in general fields (e.g., Computer Vision) as model robustness, their impact on protein property prediction remains unexplored. In this paper, we first investigate the reason behind the performance decrease when utilizing predicted structures, attributing it to the structure embedding bias from the perspective of structure representation learning. To study this problem, we identify a Protein 3D Graph Structure Learning Problem for Robust Protein Property Prediction (PGSL-RP3), collect benchmark datasets, and present a protein Structure embedding Alignment Optimization framework (SAO) to mitigate the problem of structure embedding bias between the predicted and experimental protein structures. Extensive experiments have shown that our framework is model-agnostic and effective in improving the property prediction of both predicted structures and experimental structures.

Protein 3D Graph Structure Learning for Robust Structure-Based Protein Property Prediction

This study introduces a new method for detecting and localizing image forgery by focusing on manipulation traces within the noise domain. We posit that nearly invisible noise in RGB images carries tampering traces, useful for distinguishing and locating forgeries. However, the advancement of tampering technology complicates the direct application of noise for forgery detection, as the noise inconsistency between forged and authentic regions is not fully exploited. To tackle this, we develop a two-step discriminative noise-guided approach to explicitly enhance the representation and use of noise inconsistencies, thereby fully exploiting noise information to improve the accuracy and robustness of forgery detection. Specifically, we first enhance the noise discriminability of forged regions compared to authentic ones using a de-noising network and a statistics-based constraint. Then, we merge a model-driven guided filtering mechanism with a data-driven attention mechanism to create a learnable and differentiable noise-guided filter. This sophisticated filter allows us to maintain the edges of forged regions learned from the noise. Comprehensive experiments on multiple datasets demonstrate that our method can reliably detect and localize forgeries, surpassing existing state-of-the-art methods.

Learning Discriminative Noise Guidance for Image Forgery Detection and Localization

The Entity Set Expansion (ESE) task aims to expand a handful of seed entities with new entities belonging to the same semantic class. Conventional ESE methods are based on mono-modality (i.e., literal modality), which struggle to deal with complex entities in the real world such as: (1) Negative entities with fine-grained semantic differences. (2) Synonymous entities. (3) Polysemous entities. (4) Long-tailed entities. These challenges prompt us to propose Multi-modal Entity Set Expansion (MESE), where models integrate information from multiple modalities to represent entities. Intuitively, the benefits of multi-modal information for ESE are threefold: (1) Different modalities can provide complementary information. (2) Multi-modal information provides a unified signal via common visual properties for the same semantic class or entity. (3) Multi-modal information offers robust alignment signal for synonymous entities. To assess the performance of model in MESE and facilitate further research, we constructed the MESED dataset which is the first multi-modal dataset for ESE with large-scale and elaborate manual calibration. A powerful multi-modal model MultiExpan is proposed which is pre-trained on four multimodal pre-training tasks. The extensive experiments and analyses on MESED demonstrate the high quality of the dataset and the effectiveness of our MultiExpan, as well as pointing the direction for future research.

Structure-Aware Multimodal Sequential Learning for Visual Dialog | VIDEO

Downloads

Next from AAAI 2024

Multi-Modal Disordered Representation Learning Network for Description-Based Person Search

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES