Searcharxiv⌕ Search

arXiv subjects

Di Hu

Publications and source records attributed to Di Hu.

At least 73 records · Page 4Linked to original sources
arXiv2024

MMPareto: Boosting Multimodal Learning with Innocent Unimodal Assistance

Multimodal learning methods with targeted unimodal learning objectives have exhibited their superior efficacy in alleviating the imbalanced multimodal learning problem. However, in this paper, we identify the previously ignored gradient conflict between multimodal and unimodal learning objectives, potentially misleading the unimodal encoder optimization. To well diminish these conflicts, we observe the discrepancy between multimodal loss and unimodal loss, where both gradient magnitude and covariance of the easier-to-learn multimodal loss are smaller than the unimodal one. With this property, we analyze Pareto integration under our multimodal scenario and propose MMPareto algorithm, which could ensure a final gradient with direction that is common to all learning objectives and enhanced magnitude to improve generalization, providing innocent unimodal assistance. Finally, experiments across multiple types of modalities and frameworks with dense cross-modal interaction indicate our superior and extendable method performance. Our method is also expected to facilitate multi-task cases with a clear discrepancy in task difficulty, demonstrating its ideal scalability. The source code and dataset are available at https://github.com/GeWu-Lab/MMPareto_ICML2024.

cs.CV↗
arXiv2024

Quantifying and Enhancing Multi-modal Robustness with Modality Preference

Multi-modal models have shown a promising capability to effectively integrate information from various sources, yet meanwhile, they are found vulnerable to pervasive perturbations, such as uni-modal attacks and missing conditions. To counter these perturbations, robust multi-modal representations are highly expected, which are positioned well away from the discriminative multi-modal decision boundary. In this paper, different from conventional empirical studies, we focus on a commonly used joint multi-modal framework and theoretically discover that larger uni-modal representation margins and more reliable integration for modalities are essential components for achieving higher robustness. This discovery can further explain the limitation of multi-modal robustness and the phenomenon that multi-modal models are often vulnerable to attacks on the specific modality. Moreover, our analysis reveals how the widespread issue, that the model has different preferences for modalities, limits the multi-modal robustness by influencing the essential components and could lead to attacks on the specific modality highly effective. Inspired by our theoretical finding, we introduce a training procedure called Certifiable Robust Multi-modal Training (CRMT), which can alleviate this influence from modality preference and explicitly regulate essential components to significantly improve robustness in a certifiable manner. Our method demonstrates substantial improvements in performance and robustness compared with existing methods. Furthermore, our training procedure can be easily extended to enhance other robust training strategies, highlighting its credibility and flexibility.

cs.CV↗
arXiv2024

Highly dispersed Ru nanoparticles anchored on NiAl layered double oxides catalyst for selective hydrodeoxygenation of vanillin

The hydrodeoxygenation (HDO) of lignin-derived feedstocks into value-added chemicals with high efficiency and selectivity is desirable for the utilization of biomass resource. The complex oxygen-containing groups of lignin-derived substance result in the challenge of the low selectivity toward the required product. In this work, highly dispersed Ru nanoparticles anchored on Ni3Al1 layered double oxides (LDOs) catalyst derived from NiAl layered double hydroxides (LDHs) with flower-shaped morphology was constructed by a simple deposition-reduction method. The introduction of LDHs-derived support can significantly impact the catalytic activity for the HDO of lignin-derived vanillin (VL) into 2-methoxy-4-methylphenol (MMP). The Ru/Ni3Al1-400 catalyst obtained complete conversion of VL and 94.2% yield of MMP at 130 °C in methanol solvent, much better than the catalysts without LDHs-derived support. The methanol solvent is beneficial for the conversion of reaction intermediate of vanillin alcohol (VA). Detailed characterization reveals that the existence of the enhanced metal-support interaction over Ru/Ni3Al1-400 and the easily accessible acid sites facilitate the production of MMP.

physics.chem-ph↗
arXiv2024

Facile synthesis of fine-grained CoFe$_2$O$_4$ anchored on porous carbon for simultaneous removal of tetracycline and arsenite

The coexistence of tetracycline (TC) and arsenite (As(III)) in livestock wastewater threatens public health, and the heterogeneous Fenton-like system is a practical approach for the simultaneous removal of TC and As(III). In this work, fine CoFe$_2$O$_4$ nanoparticles are facilely anchored on heretically porous carbon (CoFe$_2$O$_4$@PC) via a microwave-assisted calcination method and used for eliminating TC and As(III) via peroxymonosulfate (PMS) activation.

physics.app-ph↗
arXiv2024

SphereDiffusion: Spherical Geometry-Aware Distortion Resilient Diffusion Model

Controllable spherical panoramic image generation holds substantial applicative potential across a variety of domains.However, it remains a challenging task due to the inherent spherical distortion and geometry characteristics, resulting in low-quality content generation.In this paper, we introduce a novel framework of SphereDiffusion to address these unique challenges, for better generating high-quality and precisely controllable spherical panoramic images.For the spherical distortion characteristic, we embed the semantics of the distorted object with text encoding, then explicitly construct the relationship with text-object correspondence to better use the pre-trained knowledge of the planar images.Meanwhile, we employ a deformable technique to mitigate the semantic deviation in latent space caused by spherical distortion.For the spherical geometry characteristic, in virtue of spherical rotation invariance, we improve the data diversity and optimization objectives in the training process, enabling the model to better learn the spherical geometry characteristic.Furthermore, we enhance the denoising process of the diffusion model, enabling it to effectively use the learned geometric characteristic to ensure the boundary continuity of the generated images.With these specific techniques, experiments on Structured3D dataset show that SphereDiffusion significantly improves the quality of controllable spherical image generation and relatively reduces around 35% FID on average.

cs.CV↗
arXiv2024

Kinematic-aware Prompting for Generalizable Articulated Object Manipulation with LLMs

Generalizable articulated object manipulation is essential for home-assistant robots. Recent efforts focus on imitation learning from demonstrations or reinforcement learning in simulation, however, due to the prohibitive costs of real-world data collection and precise object simulation, it still remains challenging for these works to achieve broad adaptability across diverse articulated objects. Recently, many works have tried to utilize the strong in-context learning ability of Large Language Models (LLMs) to achieve generalizable robotic manipulation, but most of these researches focus on high-level task planning, sidelining low-level robotic control. In this work, building on the idea that the kinematic structure of the object determines how we can manipulate it, we propose a kinematic-aware prompting framework that prompts LLMs with kinematic knowledge of objects to generate low-level motion trajectory waypoints, supporting various object manipulation. To effectively prompt LLMs with the kinematic structure of different objects, we design a unified kinematic knowledge parser, which represents various articulated objects as a unified textual description containing kinematic joints and contact location. Building upon this unified description, a kinematic-aware planner model is proposed to generate precise 3D manipulation waypoints via a designed kinematic-aware chain-of-thoughts prompting method. Our evaluation spanned 48 instances across 16 distinct categories, revealing that our framework not only outperforms traditional methods on 8 seen categories but also shows a powerful zero-shot capability for 8 unseen articulated object categories. Moreover, the real-world experiments on 7 different object categories prove our framework's adaptability in practical scenarios. Code is released at https://github.com/GeWu-Lab/LLM_articulated_object_manipulation/tree/main.

cs.RO↗
arXiv2024

Prompting Segmentation with Sound Is Generalizable Audio-Visual Source Localizer

Never having seen an object and heard its sound simultaneously, can the model still accurately localize its visual position from the input audio? In this work, we concentrate on the Audio-Visual Localization and Segmentation tasks but under the demanding zero-shot and few-shot scenarios. To achieve this goal, different from existing approaches that mostly employ the encoder-fusion-decoder paradigm to decode localization information from the fused audio-visual feature, we introduce the encoder-prompt-decoder paradigm, aiming to better fit the data scarcity and varying data distribution dilemmas with the help of abundant knowledge from pre-trained models. Specifically, we first propose to construct Semantic-aware Audio Prompt (SAP) to help the visual foundation model focus on sounding objects, meanwhile, the semantic gap between the visual and audio modalities is also encouraged to shrink. Then, we develop a Correlation Adapter (ColA) to keep minimal training efforts as well as maintain adequate knowledge of the visual foundation model. By equipping with these means, extensive experiments demonstrate that this new paradigm outperforms other fusion-based methods in both the unseen class and cross-dataset settings. We hope that our work can further promote the generalization study of Audio-Visual Localization and Segmentation in practical application scenarios.

cs.CV↗
arXiv2024

Two-dimensional 5d multiferroic W3Cl8: breathing Kagome lattice and tunable magneto-optical Kerr effect

Owing to the strong spin-orbit coupling and the related fascinating physical properties, heavy 5d transition-metals exhibit desirable application prospects. However, up to now, the 5d magnetic materials are still very limited, especially very rare for tungsten. In this work, we theoretically predict a two-dimensional multiferroic W3Cl8 monolayer. Intrinsic 5d magnetism of tungsten is activated by the W ions' fractional valence in a breathing Kagome lattice of reduced effective dimension. A coplanar Y-type antiferromagnetism composed by ferromagnetic W3 trimers is confirmed as the magnetic ground state. The spontaneous ferroelectric polarization mainly originates from the ion displacement induced by the breathing distortion of Kagome lattice. An intrinsic magneto-optical Kerr effect with sizable Kerr angle can be observed to detect this trimeric Y-type antiferromagnetism, and it depends strongly on the detailed magnetic order. Thereby, we propose a general scheme for realizing more 5d magnetism in two-dimensional multiferroic systems.

cond-mat.mes-hall↗
arXiv2023

TikTalk: A Video-Based Dialogue Dataset for Multi-Modal Chitchat in Real World

To facilitate the research on intelligent and human-like chatbots with multi-modal context, we introduce a new video-based multi-modal dialogue dataset, called TikTalk. We collect 38K videos from a popular video-sharing platform, along with 367K conversations posted by users beneath them. Users engage in spontaneous conversations based on their multi-modal experiences from watching videos, which helps recreate real-world chitchat context. Compared to previous multi-modal dialogue datasets, the richer context types in TikTalk lead to more diverse conversations, but also increase the difficulty in capturing human interests from intricate multi-modal information to generate personalized responses. Moreover, external knowledge is more frequently evoked in our dataset. These facts reveal new challenges for multi-modal dialogue models. We quantitatively demonstrate the characteristics of TikTalk, propose a video-based multi-modal chitchat task, and evaluate several dialogue baselines. Experimental results indicate that the models incorporating large language models (LLM) can generate more diverse responses, while the model utilizing knowledge graphs to introduce external knowledge performs the best overall. Furthermore, no existing model can solve all the above challenges well. There is still a large room for future improvements, even for LLM with visual extensions. Our dataset is available at \url{https://ruc-aimind.github.io/projects/TikTalk/}.

cs.CL↗
arXiv2023

Two-orbital spin-fermion model study of ferromagnetism in honeycomb lattice

The spin-fermion model was previously successful to describe the complex phase diagrams of colossal magnetoresistive manganites and iron-based superconductors. In recent years, two-dimensional magnets have rapidly raised up as a new attractive branch of quantum materials, which are theoretically described based on classical spin models in most studies. Alternatively, here the two-orbital spin-fermion model is established as a uniform scenario to describe the ferromagnetism in a two-dimensional honeycomb lattice. This model connects the magnetic interactions with the electronic structures. Then the continuous tuning of magnetism in these honeycomb lattices can be predicted, based on a general phase diagram. The electron/hole doping, from the empty $e_{g}$ to half-filled $e_{g}$ limit, is studied as a benchmark. Our Monte Carlo result finds that the ferromagnetic $T_{C}$ reaches the maximum at the quarter-filled case. In other regions, the linear relationship between $T_{C}$ and doping concentration provides a theoretical guideline for the experimental modulations of two-dimensional ferromagnetism tuned by ionic liquid or electrical gating.

cond-mat.str-el↗
arXiv2023

Towards Inadequately Pre-trained Models in Transfer Learning

Pre-training has been a popular learning paradigm in deep learning era, especially in annotation-insufficient scenario. Better ImageNet pre-trained models have been demonstrated, from the perspective of architecture, by previous research to have better transferability to downstream tasks. However, in this paper, we found that during the same pre-training process, models at middle epochs, which is inadequately pre-trained, can outperform fully trained models when used as feature extractors (FE), while the fine-tuning (FT) performance still grows with the source performance. This reveals that there is not a solid positive correlation between top-1 accuracy on ImageNet and the transferring result on target data. Based on the contradictory phenomenon between FE and FT that better feature extractor fails to be fine-tuned better accordingly, we conduct comprehensive analyses on features before softmax layer to provide insightful explanations. Our discoveries suggest that, during pre-training, models tend to first learn spectral components corresponding to large singular values and the residual components contribute more when fine-tuning.

cs.CV↗
arXiv2023

Progressive Spatio-temporal Perception for Audio-Visual Question Answering

Audio-Visual Question Answering (AVQA) task aims to answer questions about different visual objects, sounds, and their associations in videos. Such naturally multi-modal videos are composed of rich and complex dynamic audio-visual components, where most of which could be unrelated to the given questions, or even play as interference in answering the content of interest. Oppositely, only focusing on the question-aware audio-visual content could get rid of influence, meanwhile enabling the model to answer more efficiently. In this paper, we propose a Progressive Spatio-Temporal Perception Network (PSTP-Net), which contains three modules that progressively identify key spatio-temporal regions w.r.t. questions. Specifically, a temporal segment selection module is first introduced to select the most relevant audio-visual segments related to the given question. Then, a spatial region selection module is utilized to choose the most relevant regions associated with the question from the selected temporal segments. To further refine the selection of features, an audio-guided visual attention module is employed to perceive the association between auido and selected spatial regions. Finally, the spatio-temporal features from these modules are integrated for answering the question. Extensive experimental results on the public MUSIC-AVQA and AVQA datasets provide compelling evidence of the effectiveness and efficiency of PSTP-Net. Code is available at: \href{https://github.com/GeWu-Lab/PSTP-Net}{https://github.com/GeWu-Lab/PSTP-Net}

cs.CV↗
arXiv2023

Towards Long Form Audio-visual Video Understanding

We live in a world filled with never-ending streams of multimodal information. As a more natural recording of the real scenario, long form audio-visual videos are expected as an important bridge for better exploring and understanding the world. In this paper, we propose the multisensory temporal event localization task in long form videos and strive to tackle the associated challenges. To facilitate this study, we first collect a large-scale Long Form Audio-visual Video (LFAV) dataset with 5,175 videos and an average video length of 210 seconds. Each of the collected videos is elaborately annotated with diversified modality-aware events, in a long-range temporal sequence. We then propose an event-centric framework for localizing multisensory events as well as understanding their relations in long form videos. It includes three phases in different levels: snippet prediction phase to learn snippet features, event extraction phase to extract event-level features, and event interaction phase to study event relations. Experiments demonstrate that the proposed method, utilizing the new LFAV dataset, exhibits considerable effectiveness in localizing multiple modality-aware events within long form videos. Project website: http://gewu-lab.github.io/LFAV/

cs.MM↗
arXiv2023

Balanced Audiovisual Dataset for Imbalance Analysis

The imbalance problem is widespread in the field of machine learning, which also exists in multimodal learning areas caused by the intrinsic discrepancy between modalities of samples. Recent works have attempted to solve the modality imbalance problem from algorithm perspective, however, they do not fully analyze the influence of modality bias in datasets. Concretely, existing multimodal datasets are usually collected under specific tasks, where one modality tends to perform better than other ones in most conditions. In this work, to comprehensively explore the influence of modality bias, we first split existing datasets into different subsets by estimating sample-wise modality discrepancy. We surprisingly find that: the multimodal models with existing imbalance algorithms consistently perform worse than the unimodal one on specific subsets, in accordance with the modality bias. To further explore the influence of modality bias and analyze the effectiveness of existing imbalance algorithms, we build a balanced audiovisual dataset, with uniformly distributed modality discrepancy over the whole dataset. We then conduct extensive experiments to re-evaluate existing imbalance algorithms and draw some interesting findings: existing algorithms only provide a compromise between modalities and suffer from the large modality discrepancy of samples. We hope that these findings could facilitate future research on the modality imbalance problem.

cs.LG↗
arXiv2023

Supervised Knowledge May Hurt Novel Class Discovery Performance

Novel class discovery (NCD) aims to infer novel categories in an unlabeled dataset by leveraging prior knowledge of a labeled set comprising disjoint but related classes. Given that most existing literature focuses primarily on utilizing supervised knowledge from a labeled set at the methodology level, this paper considers the question: Is supervised knowledge always helpful at different levels of semantic relevance? To proceed, we first establish a novel metric, so-called transfer flow, to measure the semantic similarity between labeled/unlabeled datasets. To show the validity of the proposed metric, we build up a large-scale benchmark with various degrees of semantic similarities between labeled/unlabeled datasets on ImageNet by leveraging its hierarchical class structure. The results based on the proposed benchmark show that the proposed transfer flow is in line with the hierarchical class structure; and that NCD performance is consistent with the semantic similarities (measured by the proposed metric). Next, by using the proposed transfer flow, we conduct various empirical experiments with different levels of semantic similarity, yielding that supervised knowledge may hurt NCD performance. Specifically, using supervised information from a low-similarity labeled set may lead to a suboptimal result as compared to using pure self-supervised knowledge. These results reveal the inadequacy of the existing NCD literature which usually assumes that supervised knowledge is beneficial. Finally, we develop a pseudo-version of the transfer flow as a practical reference to decide if supervised knowledge should be used in NCD. Its effectiveness is supported by our empirical studies, which show that the pseudo transfer flow (with or without supervised knowledge) is consistent with the corresponding accuracy based on various datasets. Code is released at https://github.com/J-L-O/SK-Hurt-NCD

cs.LG↗
arXiv2023

Multi-Scale Attention for Audio Question Answering

Audio question answering (AQA), acting as a widely used proxy task to explore scene understanding, has got more attention. The AQA is challenging for it requires comprehensive temporal reasoning from different scales' events of an audio scene. However, existing methods mostly extend the structures of visual question answering task to audio ones in a simple pattern but may not perform well when perceiving a fine-grained audio scene. To this end, we present a Multi-scale Window Attention Fusion Model (MWAFM) consisting of an asynchronous hybrid attention module and a multi-scale window attention module. The former is designed to aggregate unimodal and cross-modal temporal contexts, while the latter captures sound events of varying lengths and their temporal dependencies for a more comprehensive understanding. Extensive experiments are conducted to demonstrate that the proposed MWAFM can effectively explore temporal information to facilitate AQA in the fine-grained scene.Code: https://github.com/GeWu-Lab/MWAFM

cs.SD↗
arXiv2023

Robust Cross-Modal Knowledge Distillation for Unconstrained Videos

Cross-modal distillation has been widely used to transfer knowledge across different modalities, enriching the representation of the target unimodal one. Recent studies highly relate the temporal synchronization between vision and sound to the semantic consistency for cross-modal distillation. However, such semantic consistency from the synchronization is hard to guarantee in unconstrained videos, due to the irrelevant modality noise and differentiated semantic correlation. To this end, we first propose a \textit{Modality Noise Filter} (MNF) module to erase the irrelevant noise in teacher modality with cross-modal context. After this purification, we then design a \textit{Contrastive Semantic Calibration} (CSC) module to adaptively distill useful knowledge for target modality, by referring to the differentiated sample-wise semantic correlation in a contrastive fashion. Extensive experiments show that our method could bring a performance boost compared with other distillation methods in both visual action recognition and video retrieval task. We also extend to the audio tagging task to prove the generalization of our method. The source code is available at \href{https://github.com/GeWu-Lab/cross-modal-distillation}{https://github.com/GeWu-Lab/cross-modal-distillation}.

cs.CV↗
arXiv2023

Modulation of skyrmionic magnetic textures in two-dimensional vdW materials and their heterostructures

The intrinsic magnetism observed in two-dimensional (2D) van der Waals (vdW) materials provides a unique opportunity for exploring the 2D topological magnetic textures, in particular skyrmionic magnetic textures (SMTs) including skyrmion and its topological equivalents. Since the experimental discovery of skyrmions in the 2D vdW materials and their heterostructures, a critical challenge lies in the control of these SMTs to translate their intriguing features into spintronic applications. Here, we review the recent experimental and theoretical progresses on the modulations of SMTs in 2D vdW monolayer materials and their heterostructures. Besides well-established basic modulation factors including temperature, magnetic field and sample thickness, we present the experimental realization of mobility and transition driven by electric current, and the theoretical prediction of diverse magnetoelectric modulations by electric field. Considering the 2D character of vdW layered materials, strain and stacking style are also efficient approaches to tune the magnetic textures.

cond-mat.mes-hall↗