Shuai Wang

Haochen Wang, Cilin Yan, Shuai Wang et al.

Video Instance Segmentation (VIS) aims at segmenting and categorizing objects in videos from a closed set of training categories, lacking the generalization ability to handle novel categories in real-world videos. To address this limitation, we make the following three contributions. First, we introduce the novel task of Open-Vocabulary Video Instance Segmentation, which aims to simultaneously segment, track, and classify objects in videos from open-set categories, including novel categories unseen during training. Second, to benchmark Open-Vocabulary VIS, we collect a Large-Vocabulary Video Instance Segmentation dataset (LV-VIS), that contains well-annotated objects from 1,196 diverse categories, significantly surpassing the category size of existing datasets by more than one order of magnitude. Third, we propose an efficient Memory-Induced Transformer architecture, OV2Seg, to first achieve Open-Vocabulary VIS in an end-to-end manner with near real-time inference speed. Extensive experiments on LV-VIS and four existing VIS datasets demonstrate the strong zero-shot generalization ability of OV2Seg on novel categories. The dataset and code are released here https://github.com/haochenheheda/LVVIS.

Muhammad Khalifa, Yogarshi Vyas, Shuai Wang et al. · amazon-science

We investigate semi-structured document classification in a zero-shot setting. Classification of semi-structured documents is more challenging than that of standard unstructured documents, as positional, layout, and style information play a vital role in interpreting such documents. The standard classification setting where categories are fixed during both training and testing falls short in dynamic environments where new document categories could potentially emerge. We focus exclusively on the zero-shot setting where inference is done on new unseen classes. To address this task, we propose a matching-based approach that relies on a pairwise contrastive objective for both pretraining and fine-tuning. Our results show a significant boost in Macro F$_1$ from the proposed pretraining step in both supervised and unsupervised zero-shot settings.

Yuxiang Zhang, Zhenbo Liu, Shuai Wang

Objects in a scene are not always related. The execution efficiency of the one-stage scene graph generation approaches are quite high, which infer the effective relation between entity pairs using sparse proposal sets and a few queries. However, they only focus on the relation between subject and object in triplet set subject entity, predicate entity, object entity, ignoring the relation between subject and predicate or predicate and object, and the model lacks self-reasoning ability. In addition, linguistic modality has been neglected in the one-stage method. It is necessary to mine linguistic modality knowledge to improve model reasoning ability. To address the above-mentioned shortcomings, a Self-reasoning Transformer with Visual-linguistic Knowledge (SrTR) is proposed to add flexible self-reasoning ability to the model. An encoder-decoder architecture is adopted in SrTR, and a self-reasoning decoder is developed to complete three inferences of the triplet set, s+o-p, s+p-o and p+o-s. Inspired by the large-scale pre-training image-text foundation models, visual-linguistic prior knowledge is introduced and a visual-linguistic alignment strategy is designed to project visual representations into semantic spaces with prior knowledge to aid relational reasoning. Experiments on the Visual Genome dataset demonstrate the superiority and fast inference ability of the proposed method.

Xinwei Li, Li Lin, Shuai Wang et al.

Recently, multi-modal content generation has attracted lots of attention from researchers by investigating the utilization of visual instruction tuning based on large language models (LLMs). To enhance the performance and generalization ability of such LLMs, the practice of distilling knowledge from pretrained multi-modal models (a.k.a. teachers) to more compact multi-modal LLMs (students) has gained considerable interest. However, the prevailing paradigm of instructiontuning in multi-modal LLMs knowledge distillation is resource-intensive and unidirectional, neglecting the potential for mutual feedback between the student and teacher models. Thus, we propose an innovative Competitive Multi-modal Distillation framework (CoMD), which captures bidirectional feedback between teacher and student models and continually updates the multi-modal capabilities that the student model has learned. It comprises two stages: multi-modal pre-training and multi-modal competitive distillation. The first stage pre-trains the student model on a large number of filtered multi-modal datasets. The second stage facilitates a bidirectional knowledge transfer between the student and teacher models. Our experimental analysis of diverse datasets shows that our knowledge transfer method consistently improves the capabilities of the student model. Finally, the 7B-sized student model after four distillations surpassed the current state-of-the-art model LLaVA-13B on the ScienceQA and LLaVA Test dataset, also outperforms other strong baselines in the zero-shot setting.

Zongjie Li, Chaozheng Wang, Chaowei Liu et al.

With recent advancements in Large Multimodal Models (LMMs) across various domains, a novel prompting method called visual referring prompting has emerged, showing significant potential in enhancing human-computer interaction within multimodal systems. This method offers a more natural and flexible approach to human interaction with these systems compared to traditional text descriptions or coordinates. However, the categorization of visual referring prompting remains undefined, and its impact on the performance of LMMs has yet to be formally examined. In this study, we conduct the first comprehensive analysis of LMMs using a variety of visual referring prompting strategies. We introduce a benchmark dataset called VRPTEST, comprising 3 different visual tasks and 2,275 images, spanning diverse combinations of prompt strategies. Using VRPTEST, we conduct a comprehensive evaluation of eight versions of prominent open-source and proprietary foundation models, including two early versions of GPT-4V. We develop an automated assessment framework based on software metamorphic testing techniques to evaluate the accuracy of LMMs without the need for human intervention or manual labeling. We find that the current proprietary models generally outperform the open-source ones, showing an average accuracy improvement of 22.70%; however, there is still potential for improvement. Moreover, our quantitative analysis shows that the choice of prompt strategy significantly affects the accuracy of LMMs, with variations ranging from -17.5% to +7.3%. Further case studies indicate that an appropriate visual referring prompting strategy can improve LMMs' understanding of context and location information, while an unsuitable one might lead to answer rejection. We also provide insights on minimizing the negative impact of visual referring prompting on LMMs.

Dan Li, Shuai Wang, Jie Zou et al.

In this work we propose a new task: artistic visualization of classical Chinese poems, where the goal is to generatepaintings of a certain artistic style for classical Chinese poems. For this purpose, we construct a new dataset called Paint4Poem. Thefirst part of Paint4Poem consists of 301 high-quality poem-painting pairs collected manually from an influential modern Chinese artistFeng Zikai. As its small scale poses challenges for effectively training poem-to-painting generation models, we introduce the secondpart of Paint4Poem, which consists of 3,648 caption-painting pairs collected manually from Feng Zikai's paintings and 89,204 poem-painting pairs collected automatically from the web. We expect the former to help learning the artist painting style as it containshis most paintings, and the latter to help learning the semantic relevance between poems and paintings. Further, we analyze Paint4Poem regarding poem diversity, painting style, and the semantic relevance between poems and paintings. We create abenchmark for Paint4Poem: we train two representative text-to-image generation models: AttnGAN and MirrorGAN, and evaluate theirperformance regarding painting pictorial quality, painting stylistic relevance, and semantic relevance between poems and paintings.The results indicate that the models are able to generate paintings that have good pictorial quality and mimic Feng Zikai's style, but thereflection of poem semantics is limited. The dataset also poses many interesting research directions on this task, including transferlearning, few-shot learning, text-to-image generation for low-resource data etc. The dataset is publicly available.(https://github.com/paint4poem/paint4poem)

Ben Zhou, Sarthak Jain, Yi Zhang et al.

Large language models have been shown to suffer from reasoning inconsistency issues. That is, they fail more in situations unfamiliar to the training data, even though exact or very similar reasoning paths exist in more common cases that they can successfully solve. Such observations motivate us to propose methods that encourage models to understand the high-level and abstract reasoning processes during training instead of only the final answer. This way, models can transfer the exact solution to similar cases, regardless of their relevance to the pre-training data distribution. In this work, we propose SAL, a self-supervised analogical learning framework. SAL mimics the human analogy process and trains models to explicitly transfer high-quality symbolic solutions from cases that they know how to solve to other rare cases in which they tend to fail more. We show that the resulting models after SAL learning outperform base language models on a wide range of reasoning benchmarks, such as StrategyQA, GSM8K, and HotpotQA, by 2% to 20%. At the same time, we show that our model is more generalizable and controllable through analytical studies.

Shuai Wang, Ivona Najdenkoska, Hongyi Zhu et al.

Understanding visual art requires reasoning across multiple perspectives -- cultural, historical, and stylistic -- beyond mere object recognition. While recent multimodal large language models (MLLMs) perform well on general image captioning, they often fail to capture the nuanced interpretations that fine art demands. We propose ArtRAG, a novel, training-free framework that combines structured knowledge with retrieval-augmented generation (RAG) for multi-perspective artwork explanation. ArtRAG automatically constructs an Art Context Knowledge Graph (ACKG) from domain-specific textual sources, organizing entities such as artists, movements, themes, and historical events into a rich, interpretable graph. At inference time, a multi-granular structured retriever selects semantically and topologically relevant subgraphs to guide generation. This enables MLLMs to produce contextually grounded, culturally informed art descriptions. Experiments on the SemArt and Artpedia datasets show that ArtRAG outperforms several heavily trained baselines. Human evaluations further confirm that ArtRAG generates coherent, insightful, and culturally enriched interpretations.

Zhengyang Chen, Shuai Wang, Yanmin Qian

Large performance degradation is often observed for speaker ver-ification systems when applied to a new domain dataset. Givenan unlabeled target-domain dataset, unsupervised domain adaptation(UDA) methods, which usually leverage adversarial training strate-gies, are commonly used to bridge the performance gap caused bythe domain mismatch. However, such adversarial training strategyonly uses the distribution information of target domain data and cannot ensure the performance improvement on the target domain. Inthis paper, we incorporate self-supervised learning strategy to the un-supervised domain adaptation system and proposed a self-supervisedlearning based domain adaptation approach (SSDA). Compared tothe traditional UDA method, the new SSDA training strategy canfully leverage the potential label information from target domainand adapt the speaker discrimination ability from source domainsimultaneously. We evaluated the proposed approach on the Vox-Celeb (labeled source domain) and CnCeleb (unlabeled target do-main) datasets, and the best SSDA system obtains 10.2% Equal ErrorRate (EER) on the CnCeleb dataset without using any speaker labelson CnCeleb, which also can achieve the state-of-the-art results onthis corpus.

Houjun Huang, Xu Xiang, Fei Zhao et al.

Data augmentation is commonly used to help build a robust speaker verification system, especially in limited-resource case. However, conventional data augmentation methods usually focus on the diversity of acoustic environment, leaving the lexicon variation neglected. For text dependent speaker verification tasks, it's well-known that preparing training data with the target transcript is the most effectual approach to build a well-performing system, however collecting such data is time-consuming and expensive. In this work, we propose a unit selection synthesis based data augmentation method to leverage the abundant text-independent data resources. In this approach text-independent speeches of each speaker are firstly broke up to speech segments each contains one phone unit. Then segments that contain phonetics in the target transcript are selected to produce a speech with the target transcript by concatenating them in turn. Experiments are carried out on the AISHELL Speaker Verification Challenge 2019 database, the results and analysis shows that our proposed method can boost the system performance significantly.

Xu Xiang, Shuai Wang, Houjun Huang et al.

Recently, speaker embeddings extracted from a speaker discriminative deep neural network (DNN) yield better performance than the conventional methods such as i-vector. In most cases, the DNN speaker classifier is trained using cross entropy loss with softmax. However, this kind of loss function does not explicitly encourage inter-class separability and intra-class compactness. As a result, the embeddings are not optimal for speaker recognition tasks. In this paper, to address this issue, three different margin based losses which not only separate classes but also demand a fixed margin between classes are introduced to deep speaker embedding learning. It could be demonstrated that the margin is the key to obtain more discriminative speaker embeddings. Experiments are conducted on two public text independent tasks: VoxCeleb1 and Speaker in The Wild (SITW). The proposed approach can achieve the state-of-the-art performance, with 25% ~ 30% equal error rate (EER) reduction on both tasks when compared to strong baselines using cross entropy loss with softmax, obtaining 2.238% EER on VoxCeleb1 test set and 2.761% EER on SITW core-core test set, respectively.