人的凝视是一种成本效益的生理数据，揭示了人类的潜在注意力模式。选择性注意机制有助于通过忽略分散剂的存在，帮助认知系统专注于任务相关的视觉线索。由于这种能力，人类可以有效地从一个非常有限数量的训练样本中学习。灵感来自这种机制，我们旨在利用具有小型训练数据的医学图像分析任务的凝视。我们所提出的框架包括骨干编码器和选择性注意网络（SAN），用于模拟潜在的注意力。 SAN通过估计实际的人的凝视，隐含地编码与医学诊断任务相关的可疑区域。然后我们设计一种新颖的辅助注意力块（AAB），以允许从骨干编码器使用SAN的信息，以专注于选择性区域。具体而言，该块使用多针注意层的修改版本来模拟人类视觉搜索过程。请注意，SAN和AAB可以插入不同的底部，并且在配备有任务特定的头部时，该框架可用于多个医学图像分析任务。我们的方法经过证明在3D肿瘤分割和2D胸X射线分类任务中实现了卓越的性能。我们还表明，SAN的估计凝视概率图与由董事会认证的医生获得的实际凝视固定图一致。

In this paper, we propose a diffusion-based face swapping framework for the first time, called DiffFace, composed of training ID conditional DDPM, sampling with facial guidance, and a target-preserving blending. In specific, in the training process, the ID conditional DDPM is trained to generate face images with the desired identity. In the sampling process, we use the off-the-shelf facial expert models to make the model transfer source identity while preserving target attributes faithfully. During this process, to preserve the background of the target image and obtain the desired face swapping result, we additionally propose a target-preserving blending strategy. It helps our model to keep the attributes of the target face from noise while transferring the source facial identity. In addition, without any re-training, our model can flexibly apply additional facial guidance and adaptively control the ID-attributes trade-off to achieve the desired results. To the best of our knowledge, this is the first approach that applies the diffusion model in face swapping task. Compared with previous GAN-based approaches, by taking advantage of the diffusion model for the face swapping task, DiffFace achieves better benefits such as training stability, high fidelity, diversity of the samples, and controllability. Extensive experiments show that our DiffFace is comparable or superior to the state-of-the-art methods on several standard face swapping benchmarks.

For change detection in remote sensing, constructing a training dataset for deep learning models is difficult due to the requirements of bi-temporal supervision. To overcome this issue, single-temporal supervision which treats change labels as the difference of two semantic masks has been proposed. This novel method trains a change detector using two spatially unrelated images with corresponding semantic labels such as building. However, training on unpaired datasets could confuse the change detector in the case of pixels that are labeled unchanged but are visually significantly different. In order to maintain the visual similarity in unchanged area, in this paper, we emphasize that the change originates from the source image and show that manipulating the source image as an after-image is crucial to the performance of change detection. Extensive experiments demonstrate the importance of maintaining visual information between pre- and post-event images, and our method outperforms existing methods based on single-temporal supervision. code is available at https://github.com/seominseok0429/Self-Pair-for-Change-Detection.

In recent years, generative models have undergone significant advancement due to the success of diffusion models. The success of these models is often attributed to their use of guidance techniques, such as classifier and classifier-free methods, which provides effective mechanisms to trade-off between fidelity and diversity. However, these methods are not capable of guiding a generated image to be aware of its geometric configuration, e.g., depth, which hinders the application of diffusion models to areas that require a certain level of depth awareness. To address this limitation, we propose a novel guidance approach for diffusion models that uses estimated depth information derived from the rich intermediate representations of diffusion models. To do this, we first present a label-efficient depth estimation framework using the internal representations of diffusion models. At the sampling phase, we utilize two guidance techniques to self-condition the generated image using the estimated depth map, the first of which uses pseudo-labeling, and the subsequent one uses a depth-domain diffusion prior. Experiments and extensive ablation studies demonstrate the effectiveness of our method in guiding the diffusion models toward geometrically plausible image generation. Project page is available at https://ku-cvlab.github.io/DAG/.

Direct speech-to-speech translation (S2ST), in which all components can be optimized jointly, is advantageous over cascaded approaches to achieve fast inference with a simplified pipeline. We present a novel two-pass direct S2ST architecture, {\textit UnitY}, which first generates textual representations and predicts discrete acoustic units subsequently. We enhance the model performance by subword prediction in the first-pass decoder, advanced two-pass decoder architecture design and search strategy, and better training regularization. To leverage large amounts of unlabeled text data, we pre-train the first-pass text decoder based on the self-supervised denoising auto-encoding task. Experimental evaluations on benchmark datasets at various data scales demonstrate that UnitY outperforms a single-pass speech-to-unit translation model by 2.5-4.2 ASR-BLEU with 2.83x decoding speed-up. We show that the proposed methods boost the performance even when predicting spectrogram in the second pass. However, predicting discrete units achieves 2.51x decoding speed-up compared to that case.

Deep learning-based weather prediction models have advanced significantly in recent years. However, data-driven models based on deep learning are difficult to apply to real-world applications because they are vulnerable to spatial-temporal shifts. A weather prediction task is especially susceptible to spatial-temporal shifts when the model is overfitted to locality and seasonality. In this paper, we propose a training strategy to make the weather prediction model robust to spatial-temporal shifts. We first analyze the effect of hyperparameters and augmentations of the existing training strategy on the spatial-temporal shift robustness of the model. Next, we propose an optimal combination of hyperparameters and augmentation based on the analysis results and a test-time augmentation. We performed all experiments on the W4C22 Transfer dataset and achieved the 1st performance.

Traditional weather forecasting relies on domain expertise and computationally intensive numerical simulation systems. Recently, with the development of a data-driven approach, weather forecasting based on deep learning has been receiving attention. Deep learning-based weather forecasting has made stunning progress, from various backbone studies using CNN, RNN, and Transformer to training strategies using weather observations datasets with auxiliary inputs. All of this progress has contributed to the field of weather forecasting; however, many elements and complex structures of deep learning models prevent us from reaching physical interpretations. This paper proposes a SImple baseline with a spatiotemporal context Aggregation Network (SIANet) that achieved state-of-the-art in 4 parts of 5 benchmarks of W4C22. This simple but efficient structure uses only satellite images and CNNs in an end-to-end fashion without using a multi-model ensemble or fine-tuning. This simplicity of SIANet can be used as a solid baseline that can be easily applied in weather forecasting using deep learning.

Traversability estimation for mobile robots in off-road environments requires more than conventional semantic segmentation used in constrained environments like on-road conditions. Recently, approaches to learning a traversability estimation from past driving experiences in a self-supervised manner are arising as they can significantly reduce human labeling costs and labeling errors. However, the self-supervised data only provide supervision for the actually traversed regions, inducing epistemic uncertainty according to the scarcity of negative information. Negative data are rarely harvested as the system can be severely damaged while logging the data. To mitigate the uncertainty, we introduce a deep metric learning-based method to incorporate unlabeled data with a few positive and negative prototypes in order to leverage the uncertainty, which jointly learns using semantic segmentation and traversability regression. To firmly evaluate the proposed framework, we introduce a new evaluation metric that comprehensively evaluates the segmentation and regression. Additionally, we construct a driving dataset `Dtrail' in off-road environments with a mobile robot platform, which is composed of a wide variety of negative data. We examine our method on Dtrail as well as the publicly available SemanticKITTI dataset.

This work presents six structural quality metrics that can measure the quality of knowledge graphs and analyzes five cross-domain knowledge graphs on the web (Wikidata, DBpedia, YAGO, Google Knowledge Graph, Freebase) as well as 'Raftel', Naver's integrated knowledge graph. The 'Good Knowledge Graph' should define detailed classes and properties in its ontology so that knowledge in the real world can be expressed abundantly. Also, instances and RDF triples should use the classes and properties actively. Therefore, we tried to examine the internal quality of knowledge graphs numerically by focusing on the structure of the ontology, which is the schema of knowledge graphs, and the degree of use thereof. As a result of the analysis, it was possible to find the characteristics of a knowledge graph that could not be known only by scale-related indicators such as the number of classes and properties.

Wire actuation in tendon-driven continuum robots enables the transmission of force from a distance, but it is understood that tension control problems can arise when a pulley is used to actuate two cables in a push-pull mode. This paper analyzes the relationship between angle of rotation, pressure, as well as variables of a single continuum unit in a quasi-static equilibrium. The primary objective of the quasi-static analysis was to output pressure and the analysis, given the tensions applied. Static equilibrium condition was established, and the bisection method was carried out for the angle of rotation. The function for the bisection method considered pressure-induced forces, friction forces, and weight. {\theta} was 17.14{\deg}, and p was 405.6 Pa when Tl and Ts were given the values of 1 N and 2 N, respectively. The results seemed to be consistent with the preliminary design specification, calling for further simulations and experiments.