This paper proposes a generalizable, end-to-end deep learning-based method for relative pose regression between two images. Given two images of the same scene captured from different viewpoints, our algorithm predicts the relative rotation and translation between the two respective cameras. Despite recent progress in the field, current deep-based methods exhibit only limited generalization to scenes not seen in training. Our approach introduces a network architecture that extracts a grid of coarse features for each input image using the pre-trained LoFTR network. It subsequently relates corresponding features in the two images, and finally uses a convolutional network to recover the relative rotation and translation between the respective cameras. Our experiments indicate that the proposed architecture can generalize to novel scenes, obtaining higher accuracy than existing deep-learning-based methods in various settings and datasets, in particular with limited training data.

In this paper, we formulate the problem of predicting a geolocation from free text as a sequence-to-sequence problem. Using this formulation, we obtain a geocoding model by training a T5 encoder-decoder transformer model using free text as an input and geolocation as an output. The geocoding model was trained on geo-tagged wikidump data with adaptive cell partitioning for the geolocation representation. All of the code including Rest-based application, dataset and model checkpoints used in this work are publicly available.

Real-life tools for decision-making in many critical domains are based on ranking results. With the increasing awareness of algorithmic fairness, recent works have presented measures for fairness in ranking. Many of those definitions consider the representation of different ``protected groups'', in the top-$k$ ranked items, for any reasonable $k$. Given the protected groups, confirming algorithmic fairness is a simple task. However, the groups' definitions may be unknown in advance. In this paper, we study the problem of detecting groups with biased representation in the top-$k$ ranked items, eliminating the need to pre-define protected groups. The number of such groups possible can be exponential, making the problem hard. We propose efficient search algorithms for two different fairness measures: global representation bounds, and proportional representation. Then we propose a method to explain the bias in the representations of groups utilizing the notion of Shapley values. We conclude with an experimental study, showing the scalability of our approach and demonstrating the usefulness of the proposed algorithms.

What role do augmentations play in contrastive learning? Recent work suggests that good augmentations are label-preserving with respect to a specific downstream task. We complicate this picture by showing that label-destroying augmentations can be useful in the foundation model setting, where the goal is to learn diverse, general-purpose representations for multiple downstream tasks. We perform contrastive learning experiments on a range of image and audio datasets with multiple downstream tasks (e.g. for digits superimposed on photographs, predicting the class of one vs. the other). We find that Viewmaker Networks, a recently proposed model for learning augmentations for contrastive learning, produce label-destroying augmentations that stochastically destroy features needed for different downstream tasks. These augmentations are interpretable (e.g. altering shapes, digits, or letters added to images) and surprisingly often result in better performance compared to expert-designed augmentations, despite not preserving label information. To support our empirical results, we theoretically analyze a simple contrastive learning setting with a linear model. In this setting, label-destroying augmentations are crucial for preventing one set of features from suppressing the learning of features useful for another downstream task. Our results highlight the need for analyzing the interaction between multiple downstream tasks when trying to explain the success of foundation models.

Neural volumetric representations have become a widely adopted model for radiance fields in 3D scenes. These representations are fully implicit or hybrid function approximators of the instantaneous volumetric radiance in a scene, which are typically learned from multi-view captures of the scene. We investigate the new task of neural volume super-resolution - rendering high-resolution views corresponding to a scene captured at low resolution. To this end, we propose a neural super-resolution network that operates directly on the volumetric representation of the scene. This approach allows us to exploit an advantage of operating in the volumetric domain, namely the ability to guarantee consistent super-resolution across different viewing directions. To realize our method, we devise a novel 3D representation that hinges on multiple 2D feature planes. This allows us to super-resolve the 3D scene representation by applying 2D convolutional networks on the 2D feature planes. We validate the proposed method's capability of super-resolving multi-view consistent views both quantitatively and qualitatively on a diverse set of unseen 3D scenes, demonstrating a significant advantage over existing approaches.

Out-of-distribution (OOD) detection has attracted a large amount of attention from the machine learning research community in recent years due to its importance in deployed systems. Most of the previous studies focused on the detection of OOD samples in the multi-class classification task. However, OOD detection in the multi-label classification task remains an underexplored domain. In this research, we propose YolOOD - a method that utilizes concepts from the object detection domain to perform OOD detection in the multi-label classification task. Object detection models have an inherent ability to distinguish between objects of interest (in-distribution) and irrelevant objects (e.g., OOD objects) on images that contain multiple objects from different categories. These abilities allow us to convert a regular object detection model into an image classifier with inherent OOD detection capabilities with just minor changes. We compare our approach to state-of-the-art OOD detection methods and demonstrate YolOOD's ability to outperform these methods on a comprehensive suite of in-distribution and OOD benchmark datasets.

We introduce MuJoCo MPC (MJPC), an open-source, interactive application and software framework for real-time predictive control, based on MuJoCo physics. MJPC allows the user to easily author and solve complex robotics tasks, and currently supports three shooting-based planners: derivative-based iLQG and Gradient Descent, and a simple derivative-free method we call Predictive Sampling. Predictive Sampling was designed as an elementary baseline, mostly for its pedagogical value, but turned out to be surprisingly competitive with the more established algorithms. This work does not present algorithmic advances, and instead, prioritises performant algorithms, simple code, and accessibility of model-based methods via intuitive and interactive software. MJPC is available at: github.com/deepmind/mujoco_mpc, a video summary can be viewed at: dpmd.ai/mjpc.

In this paper, we present a method for converting a given scene image into a sketch using different types and multiple levels of abstraction. We distinguish between two types of abstraction. The first considers the fidelity of the sketch, varying its representation from a more precise portrayal of the input to a looser depiction. The second is defined by the visual simplicity of the sketch, moving from a detailed depiction to a sparse sketch. Using an explicit disentanglement into two abstraction axes -- and multiple levels for each one -- provides users additional control over selecting the desired sketch based on their personal goals and preferences. To form a sketch at a given level of fidelity and simplification, we train two MLP networks. The first network learns the desired placement of strokes, while the second network learns to gradually remove strokes from the sketch without harming its recognizability and semantics. Our approach is able to generate sketches of complex scenes including those with complex backgrounds (e.g., natural and urban settings) and subjects (e.g., animals and people) while depicting gradual abstractions of the input scene in terms of fidelity and simplicity.

对抗性示例可用于恶意和秘密地改变模型的预测。众所周知，为一个模型设计的对抗示例也可以传输到其他模型。这构成了主要威胁，因为这意味着攻击者可以以黑框方式对准系统。在可转让性的领域，研究人员提出了使攻击更加可转移的方法，并使模型更强大，以转移的示例。但是，据我们所知，尚无作品提出一种在黑盒攻击者的角度对对抗性示例的转移性进行排名的方法。这是一项重要的任务，因为攻击者可能只使用一组选定的示例，因此需要选择最有可能传输的样本。在本文中，我们建议一种方法来排名在不访问受害者模型的情况下对对抗性示例的可传递性。为此，我们定义并估算了有关受害者信息有限的样本的预期可传递性。我们还探讨了实用的方案：对手可以选择要攻击的最佳样本以及对手必须使用特定样本，但可以选择不同的扰动。通过我们的实验，我们发现我们的排名方法可以将攻击者的成功率提高高达80％（而无需排名）。

观察到对于某些NLP任务，例如语义角色预测或主题拟合估计，随机嵌入性能以及预处理的嵌入方式，我们探索了哪些设置允许并检查大多数学习的编码：语义角色，语义角色，语义角色嵌入或``网络''。我们发现细微的答案，具体取决于任务及其与培训目标的关系。我们研究了多任务学习中的这些表示学习方面，在这些方面，角色预测和角色填充是受监督的任务，而几个主题拟合任务不在模型的直接监督之外。我们观察到某些任务的质量得分与培训数据规模之间的非单调关系。为了更好地理解此观察结果，我们使用这些任务的每个动力版本来分析这些结果。