We launch EVA, a vision-centric foundation model to explore the limits of visual representation at scale using only publicly accessible data. EVA is a vanilla ViT pre-trained to reconstruct the masked out image-text aligned vision features conditioned on visible image patches. Via this pretext task, we can efficiently scale up EVA to one billion parameters, and sets new records on a broad range of representative vision downstream tasks, such as image recognition, video action recognition, object detection, instance segmentation and semantic segmentation without heavy supervised training. Moreover, we observe quantitative changes in scaling EVA result in qualitative changes in transfer learning performance that are not present in other models. For instance, EVA takes a great leap in the challenging large vocabulary instance segmentation task: our model achieves almost the same state-of-the-art performance on LVISv1.0 dataset with over a thousand categories and COCO dataset with only eighty categories. Beyond a pure vision encoder, EVA can also serve as a vision-centric, multi-modal pivot to connect images and text. We find initializing the vision tower of a giant CLIP from EVA can greatly stabilize the training and outperform the training from scratch counterpart with much fewer samples and less compute, providing a new direction for scaling up and accelerating the costly training of multi-modal foundation models. To facilitate future research, we release all the code and models at https://github.com/baaivision/EVA.

表格数据是信息时代的基础，并且已经进行了广泛的研究。最近的研究表明，基于神经的模型可有效学习表格数据的上下文表示。学习有效的上下文表示需要有意义的功能和大量数据。但是，当前的方法通常无法正确地从没有语义信息的功能中从功能中学习上下文表示。此外，由于数据集之间的差异，可以通过混合表格数据集扩大训练设置是很棘手的。为了解决这些问题，我们使用预先训练的语言模型来模拟表格数据，提出了一个新颖的框架PTAB。 PTAB通过三阶段处理来了解表格数据的上下文表示：模态转换（MT），掩盖语言微调（MF）和分类微调（CF）。我们使用预训练的模型（PTM）初始化模型，其中包含从大规模语言数据中学到的语义信息。因此，可以在微调阶段有效地学习上下文表示。此外，我们可以自然地混合文本化的表格数据，以扩大训练集以进一步改善表示形式学习。我们在八个流行的表格分类数据集上评估PTAB。实验结果表明，与最先进的基线（例如XGBoost）相比，我们的方法在监督的设置中取得了更好的AUC分数，并且在半监视设置下的方法优于对应方法。我们提出可视化结果，显示PTAB具有基于实例的解释性。

Open-domain question answering relies on efficient passage retrieval to select candidate contexts, where traditional sparse vector space models, such as TF-IDF or BM25, are the de facto method. In this work, we show that retrieval can be practically implemented using dense representations alone, where embeddings are learned from a small number of questions and passages by a simple dualencoder framework. When evaluated on a wide range of open-domain QA datasets, our dense retriever outperforms a strong Lucene-BM25 system greatly by 9%-19% absolute in terms of top-20 passage retrieval accuracy, and helps our end-to-end QA system establish new state-of-the-art on multiple open-domain QA benchmarks. 1 * Equal contribution 1 The code and trained models have been released at https://github.com/facebookresearch/DPR.

比较不同的汽车框架是具有挑战性的，并且经常做错了。我们引入了一个开放且可扩展的基准测试，该基准遵循最佳实践，并在比较自动框架时避免常见错误。我们对71个分类和33项回归任务进行了9个著名的自动框架进行了详尽的比较。通过多面分析，评估模型的准确性，与推理时间的权衡以及框架失败，探索了自动框架之间的差异。我们还使用Bradley-terry树来发现相对自动框架排名不同的任务子集。基准配备了一个开源工具，该工具与许多自动框架集成并自动化经验评估过程端到端：从框架安装和资源分配到深入评估。基准测试使用公共数据集，可以轻松地使用其他Automl框架和任务扩展，并且具有最新结果的网站。

A recent study has shown a phenomenon called neural collapse in that the within-class means of features and the classifier weight vectors converge to the vertices of a simplex equiangular tight frame at the terminal phase of training for classification. In this paper, we explore the corresponding structures of the last-layer feature centers and classifiers in semantic segmentation. Based on our empirical and theoretical analysis, we point out that semantic segmentation naturally brings contextual correlation and imbalanced distribution among classes, which breaks the equiangular and maximally separated structure of neural collapse for both feature centers and classifiers. However, such a symmetric structure is beneficial to discrimination for the minor classes. To preserve these advantages, we introduce a regularizer on feature centers to encourage the network to learn features closer to the appealing structure in imbalanced semantic segmentation. Experimental results show that our method can bring significant improvements on both 2D and 3D semantic segmentation benchmarks. Moreover, our method ranks 1st and sets a new record (+6.8% mIoU) on the ScanNet200 test leaderboard. Code will be available at https://github.com/dvlab-research/Imbalanced-Learning.

Weakly-supervised object localization aims to indicate the category as well as the scope of an object in an image given only the image-level labels. Most of the existing works are based on Class Activation Mapping (CAM) and endeavor to enlarge the discriminative area inside the activation map to perceive the whole object, yet ignore the co-occurrence confounder of the object and context (e.g., fish and water), which makes the model inspection hard to distinguish object boundaries. Besides, the use of CAM also brings a dilemma problem that the classification and localization always suffer from a performance gap and can not reach their highest accuracy simultaneously. In this paper, we propose a casual knowledge distillation method, dubbed KD-CI-CAM, to address these two under-explored issues in one go. More specifically, we tackle the co-occurrence context confounder problem via causal intervention (CI), which explores the causalities among image features, contexts, and categories to eliminate the biased object-context entanglement in the class activation maps. Based on the de-biased object feature, we additionally propose a multi-teacher causal distillation framework to balance the absorption of classification knowledge and localization knowledge during model training. Extensive experiments on several benchmarks demonstrate the effectiveness of KD-CI-CAM in learning clear object boundaries from confounding contexts and addressing the dilemma problem between classification and localization performance.

Witnessing the impressive achievements of pre-training techniques on large-scale data in the field of computer vision and natural language processing, we wonder whether this idea could be adapted in a grab-and-go spirit, and mitigate the sample inefficiency problem for visuomotor driving. Given the highly dynamic and variant nature of the input, the visuomotor driving task inherently lacks view and translation invariance, and the visual input contains massive irrelevant information for decision making, resulting in predominant pre-training approaches from general vision less suitable for the autonomous driving task. To this end, we propose PPGeo (Policy Pre-training via Geometric modeling), an intuitive and straightforward fully self-supervised framework curated for the policy pretraining in visuomotor driving. We aim at learning policy representations as a powerful abstraction by modeling 3D geometric scenes on large-scale unlabeled and uncalibrated YouTube driving videos. The proposed PPGeo is performed in two stages to support effective self-supervised training. In the first stage, the geometric modeling framework generates pose and depth predictions simultaneously, with two consecutive frames as input. In the second stage, the visual encoder learns driving policy representation by predicting the future ego-motion and optimizing with the photometric error based on current visual observation only. As such, the pre-trained visual encoder is equipped with rich driving policy related representations and thereby competent for multiple visuomotor driving tasks. Extensive experiments covering a wide span of challenging scenarios have demonstrated the superiority of our proposed approach, where improvements range from 2% to even over 100% with very limited data. Code and models will be available at https://github.com/OpenDriveLab/PPGeo.

In this work, we focus on instance-level open vocabulary segmentation, intending to expand a segmenter for instance-wise novel categories without mask annotations. We investigate a simple yet effective framework with the help of image captions, focusing on exploiting thousands of object nouns in captions to discover instances of novel classes. Rather than adopting pretrained caption models or using massive caption datasets with complex pipelines, we propose an end-to-end solution from two aspects: caption grounding and caption generation. In particular, we devise a joint Caption Grounding and Generation (CGG) framework based on a Mask Transformer baseline. The framework has a novel grounding loss that performs explicit and implicit multi-modal feature alignments. We further design a lightweight caption generation head to allow for additional caption supervision. We find that grounding and generation complement each other, significantly enhancing the segmentation performance for novel categories. We conduct extensive experiments on the COCO dataset with two settings: Open Vocabulary Instance Segmentation (OVIS) and Open Set Panoptic Segmentation (OSPS). The results demonstrate the superiority of our CGG framework over previous OVIS methods, achieving a large improvement of 6.8% mAP on novel classes without extra caption data. Our method also achieves over 15% PQ improvements for novel classes on the OSPS benchmark under various settings.

Nearest-Neighbor (NN) classification has been proven as a simple and effective approach for few-shot learning. The query data can be classified efficiently by finding the nearest support class based on features extracted by pretrained deep models. However, NN-based methods are sensitive to the data distribution and may produce false prediction if the samples in the support set happen to lie around the distribution boundary of different classes. To solve this issue, we present P3DC-Shot, an improved nearest-neighbor based few-shot classification method empowered by prior-driven data calibration. Inspired by the distribution calibration technique which utilizes the distribution or statistics of the base classes to calibrate the data for few-shot tasks, we propose a novel discrete data calibration operation which is more suitable for NN-based few-shot classification. Specifically, we treat the prototypes representing each base class as priors and calibrate each support data based on its similarity to different base prototypes. Then, we perform NN classification using these discretely calibrated support data. Results from extensive experiments on various datasets show our efficient non-learning based method can outperform or at least comparable to SOTA methods which need additional learning steps.

In this tutorial paper, we look into the evolution and prospect of network architecture and propose a novel conceptual architecture for the 6th generation (6G) networks. The proposed architecture has two key elements, i.e., holistic network virtualization and pervasive artificial intelligence (AI). The holistic network virtualization consists of network slicing and digital twin, from the aspects of service provision and service demand, respectively, to incorporate service-centric and user-centric networking. The pervasive network intelligence integrates AI into future networks from the perspectives of networking for AI and AI for networking, respectively. Building on holistic network virtualization and pervasive network intelligence, the proposed architecture can facilitate three types of interplay, i.e., the interplay between digital twin and network slicing paradigms, between model-driven and data-driven methods for network management, and between virtualization and AI, to maximize the flexibility, scalability, adaptivity, and intelligence for 6G networks. We also identify challenges and open issues related to the proposed architecture. By providing our vision, we aim to inspire further discussions and developments on the potential architecture of 6G.