2 code implementations • 10 Mar 2024 • Thang Doan, Sima Behpour, Xin Li, Wenbin He, Liang Gou, Liu Ren
Few-shot Class-Incremental Learning (FSCIL) poses the challenge of retaining prior knowledge while learning from limited new data streams, all without overfitting.
no code implementations • 6 Nov 2023 • Jinbin Huang, Wenbin He, Liang Gou, Liu Ren, Chris Bryan
Deep learning models are widely used in critical applications, highlighting the need for pre-deployment model understanding and improvement.
2 code implementations • 25 Jun 2023 • Thang Doan, Xin Li, Sima Behpour, Wenbin He, Liang Gou, Liu Ren
We argue that this contextual information should already be embedded within the known classes.
no code implementations • 30 May 2023 • Wenbin He, Jianxu Mao, Yaonan Wang, Zhe Li, Qiu Fang, Haotian Wu
To improve the performance in identifying the faults under strong noise for rotating machinery, this paper presents a dynamic feature reconstruction signal graph method, which plays the key role of the proposed end-to-end fault diagnosis model.
no code implementations • 1 May 2023 • Wenbin He, Suphanut Jamonnak, Liang Gou, Liu Ren
To further improve the pixel embeddings and enable language-driven semantic segmentation, we design two types of consistency guided by vision-language models: 1) embedding consistency, aligning our pixel embeddings to the joint feature space of a pre-trained vision-language model, CLIP; and 2) semantic consistency, forcing our model to make the same predictions as CLIP over a set of carefully designed target classes with both known and unknown prototypes.
no code implementations • CVPR 2023 • Wenbin He, Suphanut Jamonnak, Liang Gou, Liu Ren
To further improve the pixel embeddings and enable language-driven semantic segmentation, we design two types of consistency guided by vision-language models: 1) embedding consistency, aligning our pixel embeddings to the joint feature space of a pre-trained vision-language model, CLIP; and 2) semantic consistency, forcing our model to make the same predictions as CLIP over a set of carefully designed target classes with both known and unknown prototypes.
no code implementations • 25 Mar 2022 • Wenbin He, William Surmeier, Arvind Kumar Shekar, Liang Gou, Liu Ren
In this work, we propose a self-supervised pixel representation learning method for semantic segmentation by using visual concepts (i. e., groups of pixels with semantic meanings, such as parts, objects, and scenes) extracted from images.
no code implementations • 1 Aug 2019 • Wenbin He, Junpeng Wang, Hanqi Guo, Ko-Chih Wang, Han-Wei Shen, Mukund Raj, Youssef S. G. Nashed, Tom Peterka
We propose InSituNet, a deep learning based surrogate model to support parameter space exploration for ensemble simulations that are visualized in situ.