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, allowing separate optimization of each component and leveraging the rich spatial-temporal representation inherited from transformers. VDT offers several appealing benefits. 1) It excels at capturing temporal dependencies to produce temporally consistent video frames and even simulate the dynamics of 3D objects over time. 2) It enables flexible conditioning information through simple concatenation in the token space, effectively unifying video generation and prediction tasks. 3) Its modularized design facilitates a spatial-temporal decoupled training strategy, leading to improved efficiency. Extensive experiments on video generation, prediction, and dynamics modeling (i.e., physics-based QA) tasks have been conducted to demonstrate the effectiveness of VDT in various scenarios, including autonomous driving, human action, and physics-based simulation. We hope our study on the capabilities of transformer-based video diffusion in capturing accurate temporal dependencies, handling conditioning information, and achieving efficient training will benefit future research and advance the field. Codes and models are available at https://github.com/RERV/VDT.
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.
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.
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.
The fundamental goal of artificial intelligence (AI) is to mimic the core cognitive activities of human including perception, memory, and reasoning. Although tremendous success has been achieved in various AI research fields (e.g., computer vision and natural language processing), the majority of existing works only focus on acquiring single cognitive ability (e.g., image classification, reading comprehension, or visual commonsense reasoning). To overcome this limitation and take a solid step to artificial general intelligence (AGI), we develop a novel foundation model pre-trained with huge multimodal (visual and textual) data, which is able to be quickly adapted for a broad class of downstream cognitive tasks. Such a model is fundamentally different from the multimodal foundation models recently proposed in the literature that typically make strong semantic correlation assumption and expect exact alignment between image and text modalities in their pre-training data, which is often hard to satisfy in practice thus limiting their generalization abilities. To resolve this issue, we propose to pre-train our foundation model by self-supervised learning with weak semantic correlation data crawled from the Internet and show that state-of-the-art results can be obtained on a wide range of downstream tasks (both single-modal and cross-modal). Particularly, with novel model-interpretability tools developed in this work, we demonstrate that strong imagination ability (even with hints of commonsense) is now possessed by our foundation model. We believe our work makes a transformative stride towards AGI and will have broad impact on various AI+ fields (e.g., neuroscience and healthcare).
Large-scale pre-trained models (PTMs) such as BERT and GPT have recently achieved great success and become a milestone in the field of artificial intelligence (AI). Owing to sophisticated pre-training objectives and huge model parameters, large-scale PTMs can effectively capture knowledge from massive labeled and unlabeled data. By storing knowledge into huge parameters and fine-tuning on specific tasks, the rich knowledge implicitly encoded in huge parameters can benefit a variety of downstream tasks, which has been extensively demonstrated via experimental verification and empirical analysis. It is now the consensus of the AI community to adopt PTMs as backbone for downstream tasks rather than learning models from scratch. In this paper, we take a deep look into the history of pre-training, especially its special relation with transfer learning and self-supervised learning, to reveal the crucial position of PTMs in the AI development spectrum. Further, we comprehensively review the latest breakthroughs of PTMs. These breakthroughs are driven by the surge of computational power and the increasing availability of data, towards four important directions: designing effective architectures, utilizing rich contexts, improving computational efficiency, and conducting interpretation and theoretical analysis. Finally, we discuss a series of open problems and research directions of PTMs, and hope our view can inspire and advance the future study of PTMs.
This work explores how to design a single neural network that is capable of adapting to multiple heterogeneous tasks of computer vision, such as image segmentation, 3D detection, and video recognition. This goal is challenging because network architecture designs in different tasks are inconsistent. We solve this challenge by proposing Network Coding Propagation (NCP), a novel "neural predictor", which is able to predict an architecture's performance in multiple datasets and tasks. Unlike prior arts of neural architecture search (NAS) that typically focus on a single task, NCP has several unique benefits. (1) NCP can be trained on different NAS benchmarks, such as NAS-Bench-201 and NAS-Bench-MR, which contains a novel network space designed by us for jointly searching an architecture among multiple tasks, including ImageNet, Cityscapes, KITTI, and HMDB51. (2) NCP learns from network codes but not original data, enabling it to update the architecture efficiently across datasets. (3) Extensive experiments evaluate NCP on object classification, detection, segmentation, and video recognition. For example, with 17\% fewer FLOPs, a single architecture returned by NCP achieves 86\% and 77.16\% on ImageNet-50-1000 and Cityscapes respectively, outperforming its counterparts. More interestingly, NCP enables a single architecture applicable to both image segmentation and video recognition, which achieves competitive performance on both HMDB51 and ADE20K compared to the singular counterparts. Code is available at https://github.com/dingmyu/NCP}{https://github.com/dingmyu/NCP.
Multi-modal pre-training models have been intensively explored to bridge vision and language in recent years. However, most of them explicitly model the cross-modal interaction between image-text pairs, by assuming that there exists strong semantic correlation between the text and image modalities. Since this strong assumption is often invalid in real-world scenarios, we choose to implicitly model the cross-modal correlation for large-scale multi-modal pre-training, which is the focus of the Chinese project `WenLan' led by our team. Specifically, with the weak correlation assumption over image-text pairs, we propose a two-tower pre-training model called BriVL within the cross-modal contrastive learning framework. Unlike OpenAI CLIP that adopts a simple contrastive learning method, we devise a more advanced algorithm by adapting the latest method MoCo into the cross-modal scenario. By building a large queue-based dictionary, our BriVL can incorporate more negative samples in limited GPU resources. We further construct a large Chinese multi-source image-text dataset called RUC-CAS-WenLan for pre-training our BriVL model. Extensive experiments demonstrate that the pre-trained BriVL model outperforms both UNITER and OpenAI CLIP on various downstream tasks.