Xiao Dong

Xiao Dong, Runhui Huang, Xiaoyong Wei et al.

Recent advances in vision-language pre-training have enabled machines to perform better in multimodal object discrimination (e.g., image-text semantic alignment) and image synthesis (e.g., text-to-image generation). On the other hand, fine-tuning pre-trained models with discriminative or generative capabilities such as CLIP and Stable Diffusion on domain-specific datasets has shown to be effective in various tasks by adapting to specific domains. However, few studies have explored the possibility of learning both discriminative and generative capabilities and leveraging their synergistic effects to create a powerful and personalized multimodal model during fine-tuning. This paper presents UniDiff, a unified multi-modal model that integrates image-text contrastive learning (ITC), text-conditioned image synthesis learning (IS), and reciprocal semantic consistency modeling (RSC). UniDiff effectively learns aligned semantics and mitigates the issue of semantic collapse during fine-tuning on small datasets by leveraging RSC on visual features from CLIP and diffusion models, without altering the pre-trained model's basic architecture. UniDiff demonstrates versatility in both multi-modal understanding and generative tasks. Experimental results on three datasets (Fashion-man, Fashion-woman, and E-commercial Product) showcase substantial enhancements in vision-language retrieval and text-to-image generation, illustrating the advantages of combining discriminative and generative fine-tuning. The proposed UniDiff model establishes a robust pipeline for personalized modeling and serves as a benchmark for future comparisons in the field.

Xunlin Zhan, Yangxin Wu, Xiao Dong et al.

Nowadays, customer's demands for E-commerce are more diversified, which introduces more complications to the product retrieval industry. Previous methods are either subject to single-modal input or perform supervised image-level product retrieval, thus fail to accommodate real-life scenarios where enormous weakly annotated multi-modal data are present. In this paper, we investigate a more realistic setting that aims to perform weakly-supervised multi-modal instance-level product retrieval among fine-grained product categories. To promote the study of this challenging task, we contribute Product1M, one of the largest multi-modal cosmetic datasets for real-world instance-level retrieval. Notably, Product1M contains over 1 million image-caption pairs and consists of two sample types, i.e., single-product and multi-product samples, which encompass a wide variety of cosmetics brands. In addition to the great diversity, Product1M enjoys several appealing characteristics including fine-grained categories, complex combinations, and fuzzy correspondence that well mimic the real-world scenes. Moreover, we propose a novel model named Cross-modal contrAstive Product Transformer for instance-level prodUct REtrieval (CAPTURE), that excels in capturing the potential synergy between multi-modal inputs via a hybrid-stream transformer in a self-supervised manner.CAPTURE generates discriminative instance features via masked multi-modal learning as well as cross-modal contrastive pretraining and it outperforms several SOTA cross-modal baselines. Extensive ablation studies well demonstrate the effectiveness and the generalization capacity of our model. Dataset and codes are available at https: //github.com/zhanxlin/Product1M.

Zheng Chong, Wenqing Zhang, Shiyue Zhang et al.

Virtual try-on (VTON) technology has gained attention due to its potential to transform online retail by enabling realistic clothing visualization of images and videos. However, most existing methods struggle to achieve high-quality results across image and video try-on tasks, especially in long video scenarios. In this work, we introduce CatV2TON, a simple and effective vision-based virtual try-on (V2TON) method that supports both image and video try-on tasks with a single diffusion transformer model. By temporally concatenating garment and person inputs and training on a mix of image and video datasets, CatV2TON achieves robust try-on performance across static and dynamic settings. For efficient long-video generation, we propose an overlapping clip-based inference strategy that uses sequential frame guidance and Adaptive Clip Normalization (AdaCN) to maintain temporal consistency with reduced resource demands. We also present ViViD-S, a refined video try-on dataset, achieved by filtering back-facing frames and applying 3D mask smoothing for enhanced temporal consistency. Comprehensive experiments demonstrate that CatV2TON outperforms existing methods in both image and video try-on tasks, offering a versatile and reliable solution for realistic virtual try-ons across diverse scenarios.

Wei Wang, Baopu Li, Shuhui Yang et al.

Domain adaptation has received a lot of attention in recent years, and many algorithms have been proposed with impressive progress. However, it is still not fully explored concerning the joint probability distribution (P(X, Y)) distance for this problem, since its empirical estimation derived from the maximum mean discrepancy (joint maximum mean discrepancy, JMMD) will involve complex tensor-product operator that is hard to manipulate. To solve this issue, this paper theoretically derives a unified form of JMMD that is easy to optimize, and proves that the marginal, class conditional and weighted class conditional probability distribution distances are our special cases with different label kernels, among which the weighted class conditional one not only can realize feature alignment across domains in the category level, but also deal with imbalance dataset using the class prior probabilities. From the revealed unified JMMD, we illustrate that JMMD degrades the feature-label dependence (discriminability) that benefits to classification, and it is sensitive to the label distribution shift when the label kernel is the weighted class conditional one. Therefore, we leverage Hilbert Schmidt independence criterion and propose a novel MMD matrix to promote the dependence, and devise a novel label kernel that is robust to label distribution shift. Finally, we conduct extensive experiments on several cross-domain datasets to demonstrate the validity and effectiveness of the revealed theoretical results.

X. Dong, L. Zhou

By bridging deep networks and physics, the programme of geometrization of deep networks was proposed as a framework for the interpretability of deep learning systems. Following this programme we can apply two key ideas of physics, the geometrization of physics and the least action principle, on deep networks and deliver a new picture of deep networks: deep networks as memory space of information, where the capacity, robustness and efficiency of the memory are closely related with the complexity, generalization and disentanglement of deep networks. The key components of this understanding include:(1) a Fisher metric based formulation of the network complexity; (2)the least action (complexity=action) principle on deep networks and (3)the geometry built on deep network configurations. We will show how this picture will bring us a new understanding of the interpretability of deep learning systems.

Xiao Dong, Lei Zhu, Xuemeng Song et al.

In this paper, we investigate the research problem of unsupervised multi-view feature selection. Conventional solutions first simply combine multiple pre-constructed view-specific similarity structures into a collaborative similarity structure, and then perform the subsequent feature selection. These two processes are separate and independent. The collaborative similarity structure remains fixed during feature selection. Further, the simple undirected view combination may adversely reduce the reliability of the ultimate similarity structure for feature selection, as the view-specific similarity structures generally involve noises and outlying entries. To alleviate these problems, we propose an adaptive collaborative similarity learning (ACSL) for multi-view feature selection. We propose to dynamically learn the collaborative similarity structure, and further integrate it with the ultimate feature selection into a unified framework. Moreover, a reasonable rank constraint is devised to adaptively learn an ideal collaborative similarity structure with proper similarity combination weights and desirable neighbor assignment, both of which could positively facilitate the feature selection. An effective solution guaranteed with the proved convergence is derived to iteratively tackle the formulated optimization problem. Experiments demonstrate the superiority of the proposed approach.

Xiao Dong, Jiasong Wu, Ling Zhou

The astonishing success of AlphaGo Zero\cite{Silver_AlphaGo} invokes a worldwide discussion of the future of our human society with a mixed mood of hope, anxiousness, excitement and fear. We try to dymystify AlphaGo Zero by a qualitative analysis to indicate that AlphaGo Zero can be understood as a specially structured GAN system which is expected to possess an inherent good convergence property. Thus we deduct the success of AlphaGo Zero may not be a sign of a new generation of AI.