Zhiwu Lu

Haoyu Lu, Yuqi Huo, Guoxing Yang et al.

Large-scale vision-language pre-trained models have shown promising transferability to various downstream tasks. As the size of these foundation models and the number of downstream tasks grow, the standard full fine-tuning paradigm becomes unsustainable due to heavy computational and storage costs. This paper proposes UniAdapter, which unifies unimodal and multimodal adapters for parameter-efficient cross-modal adaptation on pre-trained vision-language models. Specifically, adapters are distributed to different modalities and their interactions, with the total number of tunable parameters reduced by partial weight sharing. The unified and knowledge-sharing design enables powerful cross-modal representations that can benefit various downstream tasks, requiring only 1.0%-2.0% tunable parameters of the pre-trained model. Extensive experiments on 6 cross-modal downstream benchmarks (including video-text retrieval, image-text retrieval, VideoQA, and VQA) show that in most cases, UniAdapter not only outperforms the state-of-the-arts, but even beats the full fine-tuning strategy. Particularly, on the MSRVTT retrieval task, UniAdapter achieves 49.7% recall@1 with 2.2% model parameters, outperforming the latest competitors by 2.0%. The code and models are available at https://github.com/RERV/UniAdapter.

Sha Yuan, Hanyu Zhao, Shuai Zhao et al. · bytedance, pku

With the rapid development of deep learning, training Big Models (BMs) for multiple downstream tasks becomes a popular paradigm. Researchers have achieved various outcomes in the construction of BMs and the BM application in many fields. At present, there is a lack of research work that sorts out the overall progress of BMs and guides the follow-up research. In this paper, we cover not only the BM technologies themselves but also the prerequisites for BM training and applications with BMs, dividing the BM review into four parts: Resource, Models, Key Technologies and Application. We introduce 16 specific BM-related topics in those four parts, they are Data, Knowledge, Computing System, Parallel Training System, Language Model, Vision Model, Multi-modal Model, Theory&Interpretability, Commonsense Reasoning, Reliability&Security, Governance, Evaluation, Machine Translation, Text Generation, Dialogue and Protein Research. In each topic, we summarize clearly the current studies and propose some future research directions. At the end of this paper, we conclude the further development of BMs in a more general view.

Bing Su, Dazhao Du, Zhao Yang et al.

Although artificial intelligence (AI) has made significant progress in understanding molecules in a wide range of fields, existing models generally acquire the single cognitive ability from the single molecular modality. Since the hierarchy of molecular knowledge is profound, even humans learn from different modalities including both intuitive diagrams and professional texts to assist their understanding. Inspired by this, we propose a molecular multimodal foundation model which is pretrained from molecular graphs and their semantically related textual data (crawled from published Scientific Citation Index papers) via contrastive learning. This AI model represents a critical attempt that directly bridges molecular graphs and natural language. Importantly, through capturing the specific and complementary information of the two modalities, our proposed model can better grasp molecular expertise. Experimental results show that our model not only exhibits promising performance in cross-modal tasks such as cross-modal retrieval and molecule caption, but also enhances molecular property prediction and possesses capability to generate meaningful molecular graphs from natural language descriptions. We believe that our model would have a broad impact on AI-empowered fields across disciplines such as biology, chemistry, materials, environment, and medicine, among others.

Hongpeng Lin, Ludan Ruan, Wenke Xia et al.

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/}.

Haoyu Lu, Nanyi Fei, Yuqi Huo et al.

Large-scale single-stream pre-training has shown dramatic performance in image-text retrieval. Regrettably, it faces low inference efficiency due to heavy attention layers. Recently, two-stream methods like CLIP and ALIGN with high inference efficiency have also shown promising performance, however, they only consider instance-level alignment between the two streams (thus there is still room for improvement). To overcome these limitations, we propose a novel COllaborative Two-Stream vision-language pretraining model termed COTS for image-text retrieval by enhancing cross-modal interaction. In addition to instance level alignment via momentum contrastive learning, we leverage two extra levels of cross-modal interactions in our COTS: (1) Token-level interaction - a masked visionlanguage modeling (MVLM) learning objective is devised without using a cross-stream network module, where variational autoencoder is imposed on the visual encoder to generate visual tokens for each image. (2) Task-level interaction - a KL-alignment learning objective is devised between text-to-image and image-to-text retrieval tasks, where the probability distribution per task is computed with the negative queues in momentum contrastive learning. Under a fair comparison setting, our COTS achieves the highest performance among all two-stream methods and comparable performance (but with 10,800X faster in inference) w.r.t. the latest single-stream methods. Importantly, our COTS is also applicable to text-to-video retrieval, yielding new state-ofthe-art on the widely-used MSR-VTT dataset.

Haoyu Lu, Mingyu Ding, Nanyi Fei et al.

Video-language modeling has attracted much attention with the rapid growth of web videos. Most existing methods assume that the video frames and text description are semantically correlated, and focus on video-language modeling at video level. However, this hypothesis often fails for two reasons: (1) With the rich semantics of video contents, it is difficult to cover all frames with a single video-level description; (2) A raw video typically has noisy/meaningless information (e.g., scenery shot, transition or teaser). Although a number of recent works deploy attention mechanism to alleviate this problem, the irrelevant/noisy information still makes it very difficult to address. To overcome such challenge, we thus propose an efficient and effective model, termed Language-Guided Denoising Network (LGDN), for video-language modeling. Different from most existing methods that utilize all extracted video frames, LGDN dynamically filters out the misaligned or redundant frames under the language supervision and obtains only 2--4 salient frames per video for cross-modal token-level alignment. Extensive experiments on five public datasets show that our LGDN outperforms the state-of-the-arts by large margins. We also provide detailed ablation study to reveal the critical importance of solving the noise issue, in hope of inspiring future video-language work.

Chuhao Jin, Hongteng Xu, Ruihua Song et al.

Poster generation is a significant task for a wide range of applications, which is often time-consuming and requires lots of manual editing and artistic experience. In this paper, we propose a novel data-driven framework, called \textit{Text2Poster}, to automatically generate visually-effective posters from textual information. Imitating the process of manual poster editing, our framework leverages a large-scale pretrained visual-textual model to retrieve background images from given texts, lays out the texts on the images iteratively by cascaded auto-encoders, and finally, stylizes the texts by a matching-based method. We learn the modules of the framework by weakly- and self-supervised learning strategies, mitigating the demand for labeled data. Both objective and subjective experiments demonstrate that our Text2Poster outperforms state-of-the-art methods, including academic research and commercial software, on the quality of generated posters.

An Zhao, Mingyu Ding, Zhiwu Lu et al.

Existing few-shot learning (FSL) methods make the implicit assumption that the few target class samples are from the same domain as the source class samples. However, in practice this assumption is often invalid -- the target classes could come from a different domain. This poses an additional challenge of domain adaptation (DA) with few training samples. In this paper, the problem of domain-adaptive few-shot learning (DA-FSL) is tackled, which requires solving FSL and DA in a unified framework. To this end, we propose a novel domain-adversarial prototypical network (DAPN) model. It is designed to address a specific challenge in DA-FSL: the DA objective means that the source and target data distributions need to be aligned, typically through a shared domain-adaptive feature embedding space; but the FSL objective dictates that the target domain per class distribution must be different from that of any source domain class, meaning aligning the distributions across domains may harm the FSL performance. How to achieve global domain distribution alignment whilst maintaining source/target per-class discriminativeness thus becomes the key. Our solution is to explicitly enhance the source/target per-class separation before domain-adaptive feature embedding learning in the DAPN, in order to alleviate the negative effect of domain alignment on FSL. Extensive experiments show that our DAPN outperforms the state-of-the-art FSL and DA models, as well as their naïve combinations. The code is available at https://github.com/dingmyu/DAPN.

Yulei Niu, Hanwang Zhang, Manli Zhang et al.

Visual dialog is a challenging vision-language task, which requires the agent to answer multi-round questions about an image. It typically needs to address two major problems: (1) How to answer visually-grounded questions, which is the core challenge in visual question answering (VQA); (2) How to infer the co-reference between questions and the dialog history. An example of visual co-reference is: pronouns (\eg, ``they'') in the question (\eg, ``Are they on or off?'') are linked with nouns (\eg, ``lamps'') appearing in the dialog history (\eg, ``How many lamps are there?'') and the object grounded in the image. In this work, to resolve the visual co-reference for visual dialog, we propose a novel attention mechanism called Recursive Visual Attention (RvA). Specifically, our dialog agent browses the dialog history until the agent has sufficient confidence in the visual co-reference resolution, and refines the visual attention recursively. The quantitative and qualitative experimental results on the large-scale VisDial v0.9 and v1.0 datasets demonstrate that the proposed RvA not only outperforms the state-of-the-art methods, but also achieves reasonable recursion and interpretable attention maps without additional annotations. The code is available at \url{https://github.com/yuleiniu/rva}.

Weiliang Tang, Dong Jing, Jia-Hui Pan et al.

Recent Large Multimodal Models have demonstrated remarkable reasoning capabilities, especially in solving complex mathematical problems and realizing accurate spatial perception. Our key insight is that these emerging abilities can naturally extend to robotic manipulation by enabling LMMs to directly infer the next goal in language via reasoning, rather than relying on a separate action head. However, this paradigm meets two main challenges: i) How to make LMMs understand the spatial action space, and ii) How to fully exploit the reasoning capacity of LMMs in solving these tasks. To tackle the former challenge, we propose a novel task formulation, which inputs the current states of object parts and the gripper, and reformulates rotation by a new axis representation instead of traditional Euler angles. This representation is more compatible with spatial reasoning and easier to interpret within a unified language space. For the latter challenge, we design a pipeline to utilize cutting-edge LMMs to generate a small but high-quality reasoning dataset of multi-round dialogues that successfully solve manipulation tasks for supervised fine-tuning. Then, we perform reinforcement learning by trial-and-error interactions in simulation to further enhance the model's reasoning abilities for robotic manipulation. Our resulting reasoning model built upon a 7B backbone, named ReasonManip, demonstrates three notable advantages driven by its system-2 level reasoning capabilities: i) exceptional generalizability to out-of-distribution environments, objects, and tasks; ii) inherent sim-to-real transfer ability enabled by the unified language representation shared across domains; iii) transparent interpretability connecting high-level reasoning and low-level control. Extensive experiments demonstrate the effectiveness of the proposed paradigm and its potential to advance LMM-driven robotic manipulation.

Yanbiao Ma, Wei Dai, Bowei Liu et al.

Despite the fast progress of deep learning, one standing challenge is the gap of the observed training samples and the underlying true distribution. There are multiple reasons for the causing of this gap e.g. sampling bias, noise etc. In the era of foundation models, we show that when leveraging the off-the-shelf (vision) foundation models (e.g., CLIP, DINOv2) for feature extraction, the geometric shapes of the resulting feature distributions exhibit remarkable transferability across domains and datasets. To verify its practical usefulness, we embody our geometric knowledge-guided distribution calibration framework in two popular and challenging settings: federated learning and long-tailed recognition. In the federated setting, we devise a technique of acquiring the global geometric shape under privacy constraints, then leverage this knowledge to generate new samples for clients, in the aim of bridging the gap between local and global observations. In long-tailed learning, it utilizes the geometric knowledge transferred from sample-rich categories to recover the true distribution for sample-scarce tail classes. Comprehensive experiments show that our proposed geometric knowledge-guided distribution calibration effectively overcomes information deficits caused by data heterogeneity and sample imbalance, with boosted performance across benchmarks.

Haoyu Lu, Guoxing Yang, Nanyi Fei et al.

This work introduces Video Diffusion Transformer (VDT), which pioneers the use of transformers in diffusion-based video generation. It features transformer blocks with modularized temporal and spatial attention modules to leverage the rich spatial-temporal representation inherited in transformers. We also propose a unified spatial-temporal mask modeling mechanism, seamlessly integrated with the model, to cater to diverse video generation scenarios. VDT offers several appealing benefits. 1) It excels at capturing temporal dependencies to produce temporally consistent video frames and even simulate the physics and dynamics of 3D objects over time. 2) It facilitates flexible conditioning information, \eg, simple concatenation in the token space, effectively unifying different token lengths and modalities. 3) Pairing with our proposed spatial-temporal mask modeling mechanism, it becomes a general-purpose video diffuser for harnessing a range of tasks, including unconditional generation, video prediction, interpolation, animation, and completion, etc. Extensive experiments on these tasks spanning various scenarios, including autonomous driving, natural weather, human action, and physics-based simulation, demonstrate the effectiveness of VDT. Additionally, we present comprehensive studies on how \model handles conditioning information with the mask modeling mechanism, which we believe will benefit future research and advance the field. Project page: https:VDT-2023.github.io

Nanyi Fei, Zhiwu Lu, Yizhao Gao et al.

The fundamental goal of artificial intelligence (AI) is to mimic the core cognitive activities of human. Despite tremendous success in the AI research, most of existing methods have only single-cognitive ability. To overcome this limitation and take a solid step towards artificial general intelligence (AGI), we develop a foundation model pre-trained with huge multimodal data, which can be quickly adapted for various downstream cognitive tasks. To achieve this goal, we propose to pre-train our foundation model by self-supervised learning with weak semantic correlation data crawled from the Internet and show that promising results can be obtained on a wide range of downstream tasks. Particularly, with the developed model-interpretability tools, we demonstrate that strong imagination ability is now possessed by our foundation model. We believe that our work makes a transformative stride towards AGI, from our common practice of "weak or narrow AI" to that of "strong or generalized AI".

Zhaoxin Fan, Zhenbo Song, Hongyan Liu et al.

Point cloud-based large scale place recognition is fundamental for many applications like Simultaneous Localization and Mapping (SLAM). Although many models have been proposed and have achieved good performance by learning short-range local features, long-range contextual properties have often been neglected. Moreover, the model size has also become a bottleneck for their wide applications. To overcome these challenges, we propose a super light-weight network model termed SVT-Net for large scale place recognition. Specifically, on top of the highly efficient 3D Sparse Convolution (SP-Conv), an Atom-based Sparse Voxel Transformer (ASVT) and a Cluster-based Sparse Voxel Transformer (CSVT) are proposed to learn both short-range local features and long-range contextual features in this model. Consisting of ASVT and CSVT, SVT-Net can achieve state-of-the-art on benchmark datasets in terms of both accuracy and speed with a super-light model size (0.9M). Meanwhile, two simplified versions of SVT-Net are introduced, which also achieve state-of-the-art and further reduce the model size to 0.8M and 0.4M respectively.

Yizhao Gao, Nanyi Fei, Guangzhen Liu et al.

Most recent few-shot learning (FSL) methods are based on meta-learning with episodic training. In each meta-training episode, a discriminative feature embedding and/or classifier are first constructed from a support set in an inner loop, and then evaluated in an outer loop using a query set for model updating. This query set sample centered learning objective is however intrinsically limited in addressing the lack of training data problem in the support set. In this paper, a novel contrastive prototype learning with augmented embeddings (CPLAE) model is proposed to overcome this limitation. First, data augmentations are introduced to both the support and query sets with each sample now being represented as an augmented embedding (AE) composed of concatenated embeddings of both the original and augmented versions. Second, a novel support set class prototype centered contrastive loss is proposed for contrastive prototype learning (CPL). With a class prototype as an anchor, CPL aims to pull the query samples of the same class closer and those of different classes further away. This support set sample centered loss is highly complementary to the existing query centered loss, fully exploiting the limited training data in each episode. Extensive experiments on several benchmarks demonstrate that our proposed CPLAE achieves new state-of-the-art.

Jiechao Guan, Zhiwu Lu, Tao Xiang et al.

To recognize the unseen classes with only few samples, few-shot learning (FSL) uses prior knowledge learned from the seen classes. A major challenge for FSL is that the distribution of the unseen classes is different from that of those seen, resulting in poor generalization even when a model is meta-trained on the seen classes. This class-difference-caused distribution shift can be considered as a special case of domain shift. In this paper, for the first time, we propose a domain adaptation prototypical network with attention (DAPNA) to explicitly tackle such a domain shift problem in a meta-learning framework. Specifically, armed with a set transformer based attention module, we construct each episode with two sub-episodes without class overlap on the seen classes to simulate the domain shift between the seen and unseen classes. To align the feature distributions of the two sub-episodes with limited training samples, a feature transfer network is employed together with a margin disparity discrepancy (MDD) loss. Importantly, theoretical analysis is provided to give the learning bound of our DAPNA. Extensive experiments show that our DAPNA outperforms the state-of-the-art FSL alternatives, often by significant margins.

Zhiwu Lu, Jiechao Guan, Aoxue Li et al.

Zero-shot learning (ZSL) is made possible by learning a projection function between a feature space and a semantic space (e.g.,~an attribute space). Key to ZSL is thus to learn a projection that is robust against the often large domain gap between the seen and unseen class domains. In this work, this is achieved by unseen class data synthesis and robust projection function learning. Specifically, a novel semantic data synthesis strategy is proposed, by which semantic class prototypes (e.g., attribute vectors) are used to simply perturb seen class data for generating unseen class ones. As in any data synthesis/hallucination approach, there are ambiguities and uncertainties on how well the synthesised data can capture the targeted unseen class data distribution. To cope with this, the second contribution of this work is a novel projection learning model termed competitive bidirectional projection learning (BPL) designed to best utilise the ambiguous synthesised data. Specifically, we assume that each synthesised data point can belong to any unseen class; and the most likely two class candidates are exploited to learn a robust projection function in a competitive fashion. As a third contribution, we show that the proposed ZSL model can be easily extended to few-shot learning (FSL) by again exploiting semantic (class prototype guided) feature synthesis and competitive BPL. Extensive experiments show that our model achieves the state-of-the-art results on both problems.

An Zhao, Mingyu Ding, Jiechao Guan et al.

Zero-shot learning (ZSL) aims to recognize unseen object classes without any training samples, which can be regarded as a form of transfer learning from seen classes to unseen ones. This is made possible by learning a projection between a feature space and a semantic space (e.g. attribute space). Key to ZSL is thus to learn a projection function that is robust against the often large domain gap between the seen and unseen classes. In this paper, we propose a novel ZSL model termed domain-invariant projection learning (DIPL). Our model has two novel components: (1) A domain-invariant feature self-reconstruction task is introduced to the seen/unseen class data, resulting in a simple linear formulation that casts ZSL into a min-min optimization problem. Solving the problem is non-trivial, and a novel iterative algorithm is formulated as the solver, with rigorous theoretic algorithm analysis provided. (2) To further align the two domains via the learned projection, shared semantic structure among seen and unseen classes is explored via forming superclasses in the semantic space. Extensive experiments show that our model outperforms the state-of-the-art alternatives by significant margins.

Yulei Niu, Zhiwu Lu, Ji-Rong Wen et al.

Image annotation aims to annotate a given image with a variable number of class labels corresponding to diverse visual concepts. In this paper, we address two main issues in large-scale image annotation: 1) how to learn a rich feature representation suitable for predicting a diverse set of visual concepts ranging from object, scene to abstract concept; 2) how to annotate an image with the optimal number of class labels. To address the first issue, we propose a novel multi-scale deep model for extracting rich and discriminative features capable of representing a wide range of visual concepts. Specifically, a novel two-branch deep neural network architecture is proposed which comprises a very deep main network branch and a companion feature fusion network branch designed for fusing the multi-scale features computed from the main branch. The deep model is also made multi-modal by taking noisy user-provided tags as model input to complement the image input. For tackling the second issue, we introduce a label quantity prediction auxiliary task to the main label prediction task to explicitly estimate the optimal label number for a given image. Extensive experiments are carried out on two large-scale image annotation benchmark datasets and the results show that our method significantly outperforms the state-of-the-art.

Zhenyong Fu, Zhiwu Lu

As one of the most important types of (weaker) supervised information in machine learning and pattern recognition, pairwise constraint, which specifies whether a pair of data points occur together, has recently received significant attention, especially the problem of pairwise constraint propagation. At least two reasons account for this trend: the first is that compared to the data label, pairwise constraints are more general and easily to collect, and the second is that since the available pairwise constraints are usually limited, the constraint propagation problem is thus important. This paper provides an up-to-date critical survey of pairwise constraint propagation research. There are two underlying motivations for us to write this survey paper: the first is to provide an up-to-date review of the existing literature, and the second is to offer some insights into the studies of pairwise constraint propagation. To provide a comprehensive survey, we not only categorize existing propagation techniques but also present detailed descriptions of representative methods within each category.

Zhiwu Lu, Liwei Wang, Ji-Rong Wen

This paper presents a new framework for visual bag-of-words (BOW) refinement and reduction to overcome the drawbacks associated with the visual BOW model which has been widely used for image classification. Although very influential in the literature, the traditional visual BOW model has two distinct drawbacks. Firstly, for efficiency purposes, the visual vocabulary is commonly constructed by directly clustering the low-level visual feature vectors extracted from local keypoints, without considering the high-level semantics of images. That is, the visual BOW model still suffers from the semantic gap, and thus may lead to significant performance degradation in more challenging tasks (e.g. social image classification). Secondly, typically thousands of visual words are generated to obtain better performance on a relatively large image dataset. Due to such large vocabulary size, the subsequent image classification may take sheer amount of time. To overcome the first drawback, we develop a graph-based method for visual BOW refinement by exploiting the tags (easy to access although noisy) of social images. More notably, for efficient image classification, we further reduce the refined visual BOW model to a much smaller size through semantic spectral clustering. Extensive experimental results show the promising performance of the proposed framework for visual BOW refinement and reduction.

Zhiwu Lu, Liwei Wang

This paper presents a graph-based learning approach to pairwise constraint propagation on multi-view data. Although pairwise constraint propagation has been studied extensively, pairwise constraints are usually defined over pairs of data points from a single view, i.e., only intra-view constraint propagation is considered for multi-view tasks. In fact, very little attention has been paid to inter-view constraint propagation, which is more challenging since pairwise constraints are now defined over pairs of data points from different views. In this paper, we propose to decompose the challenging inter-view constraint propagation problem into semi-supervised learning subproblems so that they can be efficiently solved based on graph-based label propagation. To the best of our knowledge, this is the first attempt to give an efficient solution to inter-view constraint propagation from a semi-supervised learning viewpoint. Moreover, since graph-based label propagation has been adopted for basic optimization, we develop two constrained graph construction methods for interview constraint propagation, which only differ in how the intra-view pairwise constraints are exploited. The experimental results in cross-view retrieval have shown the promising performance of our inter-view constraint propagation.

Zhiwu Lu, Zhenyong Fu, Tao Xiang et al.

This paper presents a weakly supervised sparse learning approach to the problem of noisily tagged image parsing, or segmenting all the objects within a noisily tagged image and identifying their categories (i.e. tags). Different from the traditional image parsing that takes pixel-level labels as strong supervisory information, our noisily tagged image parsing is provided with noisy tags of all the images (i.e. image-level labels), which is a natural setting for social image collections (e.g. Flickr). By oversegmenting all the images into regions, we formulate noisily tagged image parsing as a weakly supervised sparse learning problem over all the regions, where the initial labels of each region are inferred from image-level labels. Furthermore, we develop an efficient algorithm to solve such weakly supervised sparse learning problem. The experimental results on two benchmark datasets show the effectiveness of our approach. More notably, the reported surprising results shed some light on answering the question: can image-level labels replace pixel-level labels (hard to access) as supervisory information for image parsing.