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).
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.