2022-07-15 更新
Towards Highly Expressive Machine Learning Models of Non-Melanoma Skin Cancer
Authors:Simon M. Thomas, James G. Lefevre, Glenn Baxter, Nicholas A. Hamilton
Pathologists have a rich vocabulary with which they can describe all the nuances of cellular morphology. In their world, there is a natural pairing of images and words. Recent advances demonstrate that machine learning models can now be trained to learn high-quality image features and represent them as discrete units of information. This enables natural language, which is also discrete, to be jointly modelled alongside the imaging, resulting in a description of the contents of the imaging. Here we present experiments in applying discrete modelling techniques to the problem domain of non-melanoma skin cancer, specifically, histological images of Intraepidermal Carcinoma (IEC). Implementing a VQ-GAN model to reconstruct high-resolution (256x256) images of IEC images, we trained a sequence-to-sequence transformer to generate natural language descriptions using pathologist terminology. Combined with the idea of interactive concept vectors available by using continuous generative methods, we demonstrate an additional angle of interpretability. The result is a promising means of working towards highly expressive machine learning systems which are not only useful as predictive/classification tools, but also means to further our scientific understanding of disease.
PDF 12 figures, 29 pages
点此查看论文截图
Towards Counterfactual Image Manipulation via CLIP
Authors:Yingchen Yu, Fangneng Zhan, Rongliang Wu, Jiahui Zhang, Shijian Lu, Miaomiao Cui, Xuansong Xie, Xian-Sheng Hua, Chunyan Miao
Leveraging StyleGAN’s expressivity and its disentangled latent codes, existing methods can achieve realistic editing of different visual attributes such as age and gender of facial images. An intriguing yet challenging problem arises: Can generative models achieve counterfactual editing against their learnt priors? Due to the lack of counterfactual samples in natural datasets, we investigate this problem in a text-driven manner with Contrastive-Language-Image-Pretraining (CLIP), which can offer rich semantic knowledge even for various counterfactual concepts. Different from in-domain manipulation, counterfactual manipulation requires more comprehensive exploitation of semantic knowledge encapsulated in CLIP as well as more delicate handling of editing directions for avoiding being stuck in local minimum or undesired editing. To this end, we design a novel contrastive loss that exploits predefined CLIP-space directions to guide the editing toward desired directions from different perspectives. In addition, we design a simple yet effective scheme that explicitly maps CLIP embeddings (of target text) to the latent space and fuses them with latent codes for effective latent code optimization and accurate editing. Extensive experiments show that our design achieves accurate and realistic editing while driving by target texts with various counterfactual concepts.
PDF This paper has been accepted to ACM MM 2022, code may be found here: https://github.com/yingchen001/CF-CLIP
点此查看论文截图
Efficient Augmentation for Imbalanced Deep Learning
Authors:Damien Dablain, Colin Bellinger, Bartosz Krawczyk, Nitesh Chawla
Deep learning models memorize training data, which hurts their ability to generalize to under-represented classes. We empirically study a convolutional neural network’s internal representation of imbalanced image data and measure the generalization gap between a model’s feature embeddings in the training and test sets, showing that the gap is wider for minority classes. This insight enables us to design an efficient three-phase CNN training framework for imbalanced data. The framework involves training the network end-to-end on imbalanced data to learn accurate feature embeddings, performing data augmentation in the learned embedded space to balance the train distribution, and fine-tuning the classifier head on the embedded balanced training data. We propose Expansive Over-Sampling (EOS) as a data augmentation technique to utilize in the training framework. EOS forms synthetic training instances as convex combinations between the minority class samples and their nearest enemies in the embedded space to reduce the generalization gap. The proposed framework improves the accuracy over leading cost-sensitive and resampling methods commonly used in imbalanced learning. Moreover, it is more computationally efficient than standard data pre-processing methods, such as SMOTE and GAN-based oversampling, as it requires fewer parameters and less training time.
PDF
点此查看论文截图
Generate and Edit Your Own Character in a Canonical View
Authors:Jeong-gi Kwak, Yuanming Li, Dongsik Yoon, David Han, Hanseok Ko
Recently, synthesizing personalized characters from a single user-given portrait has received remarkable attention as a drastic popularization of social media and the metaverse. The input image is not always in frontal view, thus it is important to acquire or predict canonical view for 3D modeling or other applications. Although the progress of generative models enables the stylization of a portrait, obtaining the stylized image in canonical view is still a challenging task. There have been several studies on face frontalization but their performance significantly decreases when input is not in the real image domain, e.g., cartoon or painting. Stylizing after frontalization also results in degenerated output. In this paper, we propose a novel and unified framework which generates stylized portraits in canonical view. With a proposed latent mapper, we analyze and discover frontalization mapping in a latent space of StyleGAN to stylize and frontalize at once. In addition, our model can be trained with unlabelled 2D image sets, without any 3D supervision. The effectiveness of our method is demonstrated by experimental results.
PDF AI for Content Creation Workshop at CVPR 2022
点此查看论文截图