Bowen Wang 교수

Interpreting and explaining the behavior of deep neural networks is critical for many tasks. Explainable AI provides a way to address this challenge, mostly by providing per-pixel relevance to the decision. Yet, interpreting such explanations may require expert knowledge. Some recent attempts toward interpretability adopt a concept-based framework, giving a higher-level relationship between some concepts and model decisions. This paper proposes Bottleneck Concept Learner (BotCL), which represent

Few-shot learning (FSL) approaches, mostly neural network-based, are assuming that the pre-trained knowledge can be obtained from base (seen) categories and transferred to novel (unseen) categories. However, the black-box nature of neural networks makes it difficult to understand what is actually transferred, which may hamper its application in some risk-sensitive areas. In this paper, we reveal a new way to perform explainable FSL for image classification, using discriminative patterns and pair

Abstract Few-shot learning (FSL) approaches, mostly neural network-based, assume that pre-trained knowledge can be obtained from base (seen) classes and transferred to novel (unseen) classes. However, the black-box nature of neural networks makes it difficult to understand what is actually transferred, which may hamper FSL application in some risk-sensitive areas. In this paper, we reveal a new way to perform FSL for image classification, using a visual representation from the backbone model and

Semantic video segmentation is a key challenge for various applications. This paper presents a new model named Noisy-LSTM, which is trainable in an end-to-end manner, with convolutional LSTMs (ConvLSTMs) to leverage the temporal coherence in video frames, together with a simple yet effective training strategy that replaces a frame in a given video sequence with noises. Our training strategy spoils the temporal coherence in video frames and thus makes the temporal links in ConvLSTMs unreliable; t

Rural residential environment governance (RRE), as the first tough battle of China's rural revitalization strategy, relies on farmers' participation since farmers are the main laborers, builders, and administrators in environmental governance. However, lackluster farmers' enthusiasm and initiative have hindered RRE initiatives, prompting this paper. Based on the survey data of 1804 farmers in China, this paper, from the perspective of mobilization governance, empirically analyzes the impact of i

The independent living ability of the elderly in urban areas in Liaoning Province in China was at a low level. Physical activity was one of the important roles in both men and women; whereas the role of social-psychological factors only existed in men. Gender-specific healthcare and education to avoid sedentary life should be advocated for the elderly to maintain/improve their independent living ability.

Machine learning for computer aided image diagnosis requires annotation of images, but manual annotation is time-consuming for medical doctor. In this study, we tried to create a machine-learning method that creates bounding boxes with disease lesions on chest X-ray (CXR) images using the positional information extracted from CXR reports. We set the nodule as the target lesion. First, we use PSP-Net to segment the lung field according to the CXR reports. Next, a classification model ResNeSt-50 w

An approach to build a pre-trained model for estimating RSD estimation based on a single surgeon and then transfer to other surgeons demonstrated both low prediction error and good transferability with minimum fine-tuning videos.

Our findings highlight the pivotal role of Atg5-mediated lipophagy in driving ferroptosis in corneal epithelial cells in DED, proposing Atg5 as a promising therapeutic target for mitigating ferroptosis-induced cell damage and inflammation in DED.