We present Muse, a text-to-image Transformer model that achieves state-of-the-art image generation performance while being significantly more efficient than diffusion or autoregressive models. Muse is trained on a masked modeling task in discrete token space: given the text embedding extracted from a pre-trained large language model (LLM), Muse is trained to predict randomly masked image tokens. Compared to pixel-space diffusion models, such as Imagen and DALL-E 2, Muse is significantly more efficient due to the use of discrete tokens and requiring fewer sampling iterations; compared to autoregressive models, such as Parti, Muse is more efficient due to the use of parallel decoding. The use of a pre-trained LLM enables fine-grained language understanding, translating to high-fidelity image generation and the understanding of visual concepts such as objects, their spatial relationships, pose, cardinality etc. Our 900M parameter model achieves a new SOTA on CC3M, with an FID score of 6.06. The Muse 3B parameter model achieves an FID of 7.88 on zero-shot COCO evaluation, along with a CLIP score of 0.32. Muse also directly enables a number of image editing applications without the need to fine-tune or invert the model: inpainting, outpainting, and mask-free editing. More results are available at https://muse-model.github.io

Autonomous robotic surgery has advanced significantly based on analysis of visual and temporal cues in surgical workflow, but relational cues from domain knowledge remain under investigation. Complex relations in surgical annotations can be divided into intra- and inter-relations, both valuable to autonomous systems to comprehend surgical workflows. Intra- and inter-relations describe the relevance of various categories within a particular annotation type and the relevance of different annotation types, respectively. This paper aims to systematically investigate the importance of relational cues in surgery. First, we contribute the RLLS12M dataset, a large-scale collection of robotic left lateral sectionectomy (RLLS), by curating 50 videos of 50 patients operated by 5 surgeons and annotating a hierarchical workflow, which consists of 3 inter- and 6 intra-relations, 6 steps, 15 tasks, and 38 activities represented as the triplet of 11 instruments, 8 actions, and 16 objects, totaling 2,113,510 video frames and 12,681,060 annotation entities. Correspondingly, we propose a multi-relation purification hybrid network (MURPHY), which aptly incorporates novel relation modules to augment the feature representation by purifying relational features using the intra- and inter-relations embodied in annotations. The intra-relation module leverages a R-GCN to implant visual features in different graph relations, which are aggregated using a targeted relation purification with affinity information measuring label consistency and feature similarity. The inter-relation module is motivated by attention mechanisms to regularize the influence of relational features based on the hierarchy of annotation types from the domain knowledge. Extensive experimental results on the curated RLLS dataset confirm the effectiveness of our approach, demonstrating that relations matter in surgical workflow analysis.

Spurious correlations, or correlations that change across domains where a model can be deployed, present significant challenges to real-world applications of machine learning models. However, such correlations are not always "spurious"; often, they provide valuable prior information for a prediction beyond what can be extracted from the input alone. Here, we present a test-time adaptation method that exploits the spurious correlation phenomenon, in contrast to recent approaches that attempt to eliminate spurious correlations through invariance. We consider situations where the prior distribution $p(y, z)$, which models the marginal dependence between the class label $y$ and the nuisance factors $z$, may change across domains, but the generative model for features $p(\mathbf{x}|y, z)$ is constant. We note that this is an expanded version of the label shift assumption, where the labels now also include the nuisance factors $z$. Based on this observation, we train a classifier to predict $p(y, z|\mathbf{x})$ on the source distribution, and implement a test-time label shift correction that adapts to changes in the marginal distribution $p(y, z)$ using unlabeled samples from the target domain. We call our method "Test-Time Label-Shift Adaptation" or TTLSA. We apply our method to two different image datasets -- the CheXpert chest X-ray dataset and the colored MNIST dataset -- and show that it gives better downstream results than methods that try to train classifiers which are invariant to the changes in prior distribution. Code reproducing experiments is available at https://github.com/nalzok/test-time-label-shift .

促使模型表现出令人印象深刻的几次学习能力。在测试时间与单个模型或多个模型的组成一起重复相互作用，进一步扩展了功能。这些组成是概率模型，可以用具有随机变量的图形模型的语言表示，其值是复杂的数据类型，例如字符串。具有控制流和动态结构的情况需要概率编程的技术，这些技术允许以统一语言实施不同的模型结构和推理策略。我们从这个角度正式化了几种现有技术，包括刮擦板 /思想链，验证者，星星，选择 - 推动和工具使用。我们将结果程序称为语言模型级联。

人工智能的最新趋势是将验证的模型用于语言和视觉任务，这些模型已经实现了非凡的表现，但也令人困惑。因此，以各种方式探索这些模型的能力对该领域至关重要。在本文中，我们探讨了模型的可靠性，在其中我们将可靠的模型定义为一个不仅可以实现强大的预测性能，而且在许多涉及不确定性（例如选择性预测，开放式设置识别）的决策任务上，在许多决策任务上表现出色，而且表现良好。强大的概括（例如，准确性和适当的评分规则，例如在分布数据集中和分发数据集上的对数可能性）和适应性（例如，主动学习，几乎没有射击不确定性）。我们设计了40个数据集的10种任务类型，以评估视觉和语言域上可靠性的不同方面。为了提高可靠性，我们分别开发了VIT-PLEX和T5-PLEX，分别针对视觉和语言方式扩展了大型模型。 PLEX极大地改善了跨可靠性任务的最先进，并简化了传统协议，因为它可以改善开箱即用的性能，并且不需要设计分数或为每个任务调整模型。我们演示了高达1B参数的模型尺寸的缩放效果，并预处理数据集大小最多4B示例。我们还展示了PLEX在具有挑战性的任务上的功能，包括零射门的开放式识别，主动学习和对话语言理解中的不确定性。

在本文中，我们在贝叶斯神经网络中展示了一种用于在线（顺序）推断的新算法，并显示其适用于解决上下文强盗问题的适用性。关键的想法是将扩展的卡尔曼滤波器（在每个时间步地上局部化的似然函数与参数的（学习或随机）的低维仿射子空间组合;使用子空间使我们能够将我们的算法扩展到具有$ \ SIM 1M $参数的模型。虽然大多数其他神经匪徒方法需要存储整个过去的数据集，以避免“灾难性忘记”的问题，我们的方法使用恒定的内存。这是可能的，因为我们代表了模型中所有参数的不确定性，而不仅仅是最终的线性层。我们在“Deep Bayesian Bandit摊牌”基准和Mnist和推荐系统上显示出良好的结果。

对不确定度和鲁棒性的高质量估计对于众多现实世界的应用来说至关重要，特别是对于深入学习，这是利用许多部署的ML系统。因此，比较改善这些估计的技术的能力对于研究和实践相似非常重要。然而，由于一系列原因，通常缺乏方法的竞争比较，包括：计算广泛调整的可用性，加入足够多的基线，以及用于再现性的具体文件。在本文中，我们介绍了不确定性的基线：在各种任务中的标准和最先进的深度学习方法的高质量实现。从本撰写中，集合跨越9项方法，每个方法都有至少5个度量。每个基线都是一个独立的实验管道，易于可重复使用和可伸缩的部件。我们的目标是提供具有新方法或应用的实验的即时出发点。此外，我们还提供模型检查点，实验输出为Python笔记本，以及用于比较结果的排行榜。代码在https://github.com/google/uncertainty-baselines。

Self-supervised learning has become increasingly important to leverage the abundance of unlabeled data available on platforms like YouTube. Whereas most existing approaches learn low-level representations, we propose a joint visual-linguistic model to learn high-level features without any explicit supervision. In particular, inspired by its recent success in language modeling, we build upon the BERT model to learn bidirectional joint distributions over sequences of visual and linguistic tokens, derived from vector quantization of video data and off-the-shelf speech recognition outputs, respectively. We use VideoBERT in numerous tasks, including action classification and video captioning. We show that it can be applied directly to openvocabulary classification, and confirm that large amounts of training data and cross-modal information are critical to performance. Furthermore, we outperform the state-of-theart on video captioning, and quantitative results verify that the model learns high-level semantic features.

Recent advances in neural architecture search (NAS) demand tremendous computational resources, which makes it difficult to reproduce experiments and imposes a barrier-to-entry to researchers without access to large-scale computation. We aim to ameliorate these problems by introducing NAS-Bench-101, the first public architecture dataset for NAS research. To build NAS-Bench-101, we carefully constructed a compact, yet expressive, search space, exploiting graph isomorphisms to identify 423k unique convolutional architectures. We trained and evaluated all of these architectures multiple times on CIFAR-10 and compiled the results into a large dataset of over 5 million trained models. This allows researchers to evaluate the quality of a diverse range of models in milliseconds by querying the precomputed dataset. We demonstrate its utility by analyzing the dataset as a whole and by benchmarking a range of architecture optimization algorithms.

Despite the steady progress in video analysis led by the adoption of convolutional neural networks (CNNs), the relative improvement has been less drastic as that in 2D static image classification. Three main challenges exist including spatial (image) feature representation, temporal information representation, and model/computation complexity. It was recently shown by Carreira and Zisserman that 3D CNNs, inflated from 2D networks and pretrained on Ima-geNet, could be a promising way for spatial and temporal representation learning. However, as for model/computation complexity, 3D CNNs are much more expensive than 2D CNNs and prone to overfit. We seek a balance between speed and accuracy by building an effective and efficient video classification system through systematic exploration of critical network design choices. In particular, we show that it is possible to replace many of the 3D convolutions by low-cost 2D convolutions. Rather surprisingly, best result (in both speed and accuracy) is achieved when replacing the 3D convolutions at the bottom of the network, suggesting that temporal representation learning on high-level "semantic" features is more useful. Our conclusion generalizes to datasets with very different properties. When combined with several other cost-effective designs including separable spatial/temporal convolution and feature gating, our system results in an effective video classification system that that produces very competitive results on several action classification benchmarks (Kinetics, Something-something, UCF101 and HMDB), as well as two action detection (localization) benchmarks (JHMDB and UCF101-24).