本文的重点是具有属性操作的图像检索问题。我们所提出的工作能够在维护其它属性时操纵查询图像的所需属性。例如，查询图像的套环属性可以从圆形到V-N颈改变，以从大型数据集中检索类似的图像。电子商务中的一个关键挑战是图像具有多个属性，用户希望操纵，并且重要的是估计每个属性的判别特征表示。所提出的fashionsearchnet-v2架构能够通过利用其弱监管的本地化模块来学习属性特定表示，该模块忽略了特征空间中属性的不相关特征，从而提高了相似度学习。网络与属性分类和三联排名损失的组合进行了联合培训，以估计本地表示。然后，基于所指的属性操纵，这些本地表示被合并成单个全局表示，其中可以通过距离度量来检索期望的图像。该方法还提供了可解释性，以帮助提供有关网络注意的额外信息。在几个数据集上执行的实验，该数据集在属性的数量方面表明FashionSearchNet-V2优于其他最先进的属性操作技术。与我们之前的工作（FashionsearchNet）不同，我们提出了几种改进了学习程序，并表明所提出的FashionsearchNet-V2可以概括为除了时尚之外的不同域。

Recognizing the surrounding environment at low latency is critical in autonomous driving. In real-time environment, surrounding environment changes when processing is over. Current detection models are incapable of dealing with changes in the environment that occur after processing. Streaming perception is proposed to assess the latency and accuracy of real-time video perception. However, additional problems arise in real-world applications due to limited hardware resources, high temperatures, and other factors. In this study, we develop a model that can reflect processing delays in real time and produce the most reasonable results. By incorporating the proposed feature queue and feature select module, the system gains the ability to forecast specific time steps without any additional computational costs. Our method is tested on the Argoverse-HD dataset. It achieves higher performance than the current state-of-the-art methods(2022.10) in various environments when delayed . The code is available at https://github.com/danjos95/DADE

Emerging real-time multi-model ML (RTMM) workloads such as AR/VR and drone control often involve dynamic behaviors in various levels; task, model, and layers (or, ML operators) within a model. Such dynamic behaviors are new challenges to the system software in an ML system because the overall system load is unpredictable unlike traditional ML workloads. Also, the real-time processing requires to meet deadlines, and multi-model workloads involve highly heterogeneous models. As RTMM workloads often run on resource-constrained devices (e.g., VR headset), developing an effective scheduler is an important research problem. Therefore, we propose a new scheduler, SDRM3, that effectively handles various dynamicity in RTMM style workloads targeting multi-accelerator systems. To make scheduling decisions, SDRM3 quantifies the unique requirements for RTMM workloads and utilizes the quantified scores to drive scheduling decisions, considering the current system load and other inference jobs on different models and input frames. SDRM3 has tunable parameters that provide fast adaptivity to dynamic workload changes based on a gradient descent-like online optimization, which typically converges within five steps for new workloads. In addition, we also propose a method to exploit model level dynamicity based on Supernet for exploiting the trade-off between the scheduling effectiveness and model performance (e.g., accuracy), which dynamically selects a proper sub-network in a Supernet based on the system loads. In our evaluation on five realistic RTMM workload scenarios, SDRM3 reduces the overall UXCost, which is a energy-delay-product (EDP)-equivalent metric for real-time applications defined in the paper, by 37.7% and 53.2% on geometric mean (up to 97.6% and 97.1%) compared to state-of-the-art baselines, which shows the efficacy of our scheduling methodology.

We study critical systems that allocate scarce resources to satisfy basic needs, such as homeless services that provide housing. These systems often support communities disproportionately affected by systemic racial, gender, or other injustices, so it is crucial to design these systems with fairness considerations in mind. To address this problem, we propose a framework for evaluating fairness in contextual resource allocation systems that is inspired by fairness metrics in machine learning. This framework can be applied to evaluate the fairness properties of a historical policy, as well as to impose constraints in the design of new (counterfactual) allocation policies. Our work culminates with a set of incompatibility results that investigate the interplay between the different fairness metrics we propose. Notably, we demonstrate that: 1) fairness in allocation and fairness in outcomes are usually incompatible; 2) policies that prioritize based on a vulnerability score will usually result in unequal outcomes across groups, even if the score is perfectly calibrated; 3) policies using contextual information beyond what is needed to characterize baseline risk and treatment effects can be fairer in their outcomes than those using just baseline risk and treatment effects; and 4) policies using group status in addition to baseline risk and treatment effects are as fair as possible given all available information. Our framework can help guide the discussion among stakeholders in deciding which fairness metrics to impose when allocating scarce resources.

Applying suction grippers in unstructured environments is a challenging task because of depth and tilt errors in vision systems, requiring additional costs in elaborate sensing and control. To reduce additional costs, suction grippers with compliant bodies or mechanisms have been proposed; however, their bulkiness and limited allowable error hinder their use in complex environments with large errors. Here, we propose a compact suction gripper that can pick objects over a wide range of distances and tilt angles without elaborate sensing and control. The spring-inserted gripper body deploys and conforms to distant and tilted objects until the suction cup completely seals with the object and retracts immediately after, while holding the object. This seamless deployment and retraction is enabled by connecting the gripper body and suction cup to the same vacuum source, which couples the vacuum picking and retraction of the gripper body. Experimental results validated that the proposed gripper can pick objects within 79 mm, which is 1.4 times the initial length, and can pick objects with tilt angles up to 60{\deg}. The feasibility of the gripper was verified by demonstrations, including picking objects of different heights from the same picking height and the bin picking of transparent objects.

Mirror descent is a gradient descent method that uses a dual space of parametric models. The great idea has been developed in convex optimization, but not yet widely applied in machine learning. In this study, we provide a possible way that the mirror descent can help data-driven parameter initialization of neural networks. We adopt the Hopfield model as a prototype of neural networks, we demonstrate that the mirror descent can train the model more effectively than the usual gradient descent with random parameter initialization.

Scene text images have different shapes and are subjected to various distortions, e.g. perspective distortions. To handle these challenges, the state-of-the-art methods rely on a rectification network, which is connected to the text recognition network. They form a linear pipeline which uses text rectification on all input images, even for images that can be recognized without it. Undoubtedly, the rectification network improves the overall text recognition performance. However, in some cases, the rectification network generates unnecessary distortions on images, resulting in incorrect predictions in images that would have otherwise been correct without it. In order to alleviate the unnecessary distortions, the portmanteauing of features is proposed. The portmanteau feature, inspired by the portmanteau word, is a feature containing information from both the original text image and the rectified image. To generate the portmanteau feature, a non-linear input pipeline with a block matrix initialization is presented. In this work, the transformer is chosen as the recognition network due to its utilization of attention and inherent parallelism, which can effectively handle the portmanteau feature. The proposed method is examined on 6 benchmarks and compared with 13 state-of-the-art methods. The experimental results show that the proposed method outperforms the state-of-the-art methods on various of the benchmarks.

Scene text recognition (STR) involves the task of reading text in cropped images of natural scenes. Conventional models in STR employ convolutional neural network (CNN) followed by recurrent neural network in an encoder-decoder framework. In recent times, the transformer architecture is being widely adopted in STR as it shows strong capability in capturing long-term dependency which appears to be prominent in scene text images. Many researchers utilized transformer as part of a hybrid CNN-transformer encoder, often followed by a transformer decoder. However, such methods only make use of the long-term dependency mid-way through the encoding process. Although the vision transformer (ViT) is able to capture such dependency at an early stage, its utilization remains largely unexploited in STR. This work proposes the use of a transformer-only model as a simple baseline which outperforms hybrid CNN-transformer models. Furthermore, two key areas for improvement were identified. Firstly, the first decoded character has the lowest prediction accuracy. Secondly, images of different original aspect ratios react differently to the patch resolutions while ViT only employ one fixed patch resolution. To explore these areas, Pure Transformer with Integrated Experts (PTIE) is proposed. PTIE is a transformer model that can process multiple patch resolutions and decode in both the original and reverse character orders. It is examined on 7 commonly used benchmarks and compared with over 20 state-of-the-art methods. The experimental results show that the proposed method outperforms them and obtains state-of-the-art results in most benchmarks.

The continuous increase in global population and the impact of climate change on crop production are expected to affect the food sector significantly. In this context, there is need for timely, large-scale and precise mapping of crops for evidence-based decision making. A key enabler towards this direction are new satellite missions that freely offer big remote sensing data of high spatio-temporal resolution and global coverage. During the previous decade and because of this surge of big Earth observations, deep learning methods have dominated the remote sensing and crop mapping literature. Nevertheless, deep learning models require large amounts of annotated data that are scarce and hard-to-acquire. To address this problem, transfer learning methods can be used to exploit available annotations and enable crop mapping for other regions, crop types and years of inspection. In this work, we have developed and trained a deep learning model for paddy rice detection in South Korea using Sentinel-1 VH time-series. We then fine-tune the model for i) paddy rice detection in France and Spain and ii) barley detection in the Netherlands. Additionally, we propose a modification in the pre-trained weights in order to incorporate extra input features (Sentinel-1 VV). Our approach shows excellent performance when transferring in different areas for the same crop type and rather promising results when transferring in a different area and crop type.

Recommender systems are a long-standing research problem in data mining and machine learning. They are incremental in nature, as new user-item interaction logs arrive. In real-world applications, we need to periodically train a collaborative filtering algorithm to extract user/item embedding vectors and therefore, a time-series of embedding vectors can be naturally defined. We present a time-series forecasting-based upgrade kit (TimeKit), which works in the following way: it i) first decides a base collaborative filtering algorithm, ii) extracts user/item embedding vectors with the base algorithm from user-item interaction logs incrementally, e.g., every month, iii) trains our time-series forecasting model with the extracted time- series of embedding vectors, and then iv) forecasts the future embedding vectors and recommend with their dot-product scores owing to a recent breakthrough in processing complicated time- series data, i.e., neural controlled differential equations (NCDEs). Our experiments with four real-world benchmark datasets show that the proposed time-series forecasting-based upgrade kit can significantly enhance existing popular collaborative filtering algorithms.