In this paper, we generate and control semantically interpretable filters that are directly learned from natural images in an unsupervised fashion. Each semantic filter learns a visually interpretable local structure in conjunction with other filters. The significance of learning these interpretable filter sets is demonstrated on two contrasting applications. The first application is image recognition under progressive decolorization, in which recognition algorithms should be color-insensitive to achieve a robust performance. The second application is image quality assessment where objective methods should be sensitive to color degradations. In the proposed work, the sensitivity and lack thereof are controlled by weighing the semantic filters based on the local structures they represent. To validate the proposed approach, we utilize the CURE-TSR dataset for image recognition and the TID 2013 dataset for image quality assessment. We show that the proposed semantic filter set achieves state-of-the-art performances in both datasets while maintaining its robustness across progressive distortions.
Coarse-to-Fine: Progressive Image Compression for Semantically Hierarchical Classification
School of Integrated Technology, Yonsei University（延世大学整合技术学院）；BK21 Graduate Program in Intelligent Semiconductor Technology, Yonsei University（延世大学智能半导体技术研究生项目）；Department of Artificial Intelligence, Chung-Ang University（成均馆大学人工智能系）
Tampere University（坦佩雷大学）；Aalto University of Technology（阿尔托理工大学）
This paper presents a generic face animator that is able to control the pose and expressions of a given face image. The animation is driven by human interpretable control signals consisting of head pose angles and the Action Unit (AU) values. The control information can be obtained from multiple sources including external driving videos and manual controls. Due to the interpretable nature of the driving signal, one can easily mix the information between multiple sources (e.g. pose from one image and expression from another) and apply selective post-production editing. The proposed face animato…
Image inpainting aims at restoring missing region of corrupted images, which has many applications such as image restoration and object removal. However, current GAN-based inpainting models fail to explicitly consider the semantic consistency between restored images and original images. Forexample, given a male image with image region of one eye missing, current models may restore it with a female eye. This is due to the ambiguity of GAN-based inpainting models: these models can generate many possible restorations given a missing region. To address this limitation, our key insight is that sema…
The inability to interpret the model prediction in semantically and visually meaningful ways is a well-known shortcoming of most existing computer-aided diagnosis methods. In this paper, we propose MDNet to establish a direct multimodal mapping between medical images and diagnostic reports that can read images, generate diagnostic reports, retrieve images by symptom descriptions, and visualize attention, to provide justifications of the network diagnosis process. MDNet includes an image model and a language model. The image model is proposed to enhance multi-scale feature ensembles and utiliza…
A main issue preventing the use of Convolutional Neural Networks (CNN) in end user applications is the low level of transparency in the decision process. Previous work on CNN interpretability has mostly focused either on localizing the regions of the image that contribute to the result or on building an external model that generates plausible explanations. However, the former does not provide any semantic information and the latter does not guarantee the faithfulness of the explanation. We propose an intermediate representation composed of multiple Semantically Interpretable Activation Maps (S…
CLIP-PAE: Projection-Augmentation Embedding to Extract Relevant Features for a Disentangled, Interpretable, and Controllable Text-Guided Face Manipulation
The Pennsylvania State University（宾夕法尼亚州立大学）；Johns Hopkins University（约翰斯·霍普金斯大学）；Upper Dublin High School（上达比高中）
Generative models have been applied in the medical imaging domain for various image recognition and synthesis tasks. However, a more controllable and interpretable image synthesis model is still lacking yet necessary for important applications such as assisting in medical training. In this work, we leverage the efficient self-attention and contrastive learning modules and build upon state-of-the-art generative adversarial networks (GANs) to achieve an attribute-aware image synthesis model, termed AttributeGAN, which can generate high-quality histopathology images based on multi-attribute input…
CFCS, Peking University（北京大学CFCS）；University College London（伦敦大学学院）；Tel Aviv University（特拉维夫大学）；AICFVE, Beijing Film Academy（北京电影学院AICFVE）；Adobe Research（奥多比研究院）
In this paper, we leverage advances in neural networks towards forming a neural rendering for controllable image generation, and thereby bypassing the need for detailed modeling in conventional graphics pipeline. To this end, we present Neural Graphics Pipeline (NGP), a hybrid generative model that brings together neural and traditional image formation models. NGP decomposes the image into a set of interpretable appearance feature maps, uncovering direct control handles for controllable image generation. To form an image, NGP generates coarse 3D models that are fed into neural rendering module…
We propose VecGAN, an image-to-image translation framework for facial attribute editing with interpretable latent directions. Facial attribute editing task faces the challenges of precise attribute editing with controllable strength and preservation of the other attributes of an image. For this goal, we design the attribute editing by latent space factorization and for each attribute, we learn a linear direction that is orthogonal to the others. The other component is the controllable strength of the change, a scalar value. In our framework, this scalar can be either sampled or encoded from a …
Nvidia（英伟达）；Carnegie Mellon University（卡内基梅隆大学）；California Institute of Technology（加州理工学院）；University of Toronto（多伦多大学）；Vector Institute（矢量研究所）
Auditing trained deep learning (DL) models prior to deployment is vital for preventing unintended consequences. One of the biggest challenges in auditing is the lack of human-interpretable specifications for the DL models that are directly useful to the auditor. We address this challenge through a sequence of semantically-aligned unit tests, where each unit test verifies whether a predefined specification (e.g., accuracy over 95%) is satisfied with respect to controlled and semantically aligned variations in the input space (e.g., in face recognition, the angle relative to the camera). We enab…
This paper proposes a learning strategy that extracts object-part concepts from a pre-trained convolutional neural network (CNN), in an attempt to 1) explore explicit semantics hidden in CNN units and 2) gradually grow a semantically interpretable graphical model on the pre-trained CNN for hierarchical object understanding. Given part annotations on very few (e.g., 3-12) objects, our method mines certain latent patterns from the pre-trained CNN and associates them with different semantic parts. We use a four-layer And-Or graph to organize the mined latent patterns, so as to clarify their inter…
University of California, Los Angeles（加利福尼亚大学洛杉矶分校）
This paper proposes a method to modify traditional convolutional neural networks (CNNs) into interpretable CNNs, in order to clarify knowledge representations in high conv-layers of CNNs. In an interpretable CNN, each filter in a high conv-layer represents a certain object part. We do not need any annotations of object parts or textures to supervise the learning process. Instead, the interpretable CNN automatically assigns each filter in a high conv-layer with an object part during the learning process. Our method can be applied to different types of CNNs with different structures. The clear k…
Shanghai Jiao Tong University（上海交通大学）；University of California, Los Angeles（加州大学洛杉矶分校）
This paper proposes a generic method to learn interpretable convolutional filters in a deep convolutional neural network (CNN) for object classification, where each interpretable filter encodes features of a specific object part. Our method does not require additional annotations of object parts or textures for supervision. Instead, we use the same training data as traditional CNNs. Our method automatically assigns each interpretable filter in a high conv-layer with an object part of a certain category during the learning process. Such explicit knowledge representations in conv-layers of CNN h…
Unified and Semantically Grounded Domain Adaptation for Medical Image Segmentation
Department of Electrical and Computer Engineering, University of Washington（电气与计算机工程系，华盛顿大学）；Department of Bioengineering, University of Washington（生物工程系，华盛顿大学）；Department of Radiology, University of Washington（放射学系，华盛顿大学）；Department of Electrical and Computer Engineering and Paul G. Allen School of Computer Science and Engineering, University of Washington（电气与计算机工程系及保罗·G·阿伦计算机科学与工程学院，华盛顿大学）；Department of Radiology and Imaging Sciences, University of Utah（放射学与影像科学系，犹他大学）
Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）；University of Tübingen（蒂宾根大学）；Amazon（亚马逊）
In recent years, Generative Adversarial Networks have achieved impressive results in photorealistic image synthesis. This progress nurtures hopes that one day the classical rendering pipeline can be replaced by efficient models that are learned directly from images. However, current image synthesis models operate in the 2D domain where disentangling 3D properties such as camera viewpoint or object pose is challenging. Furthermore, they lack an interpretable and controllable representation. Our key hypothesis is that the image generation process should be modeled in 3D space as the physical wor…
Peking University（北京大学）；Advanced Institute of Information Technology, Peking University（北京大学信息技术高等研究院）；Tencent America（腾讯美国）
Generating portrait images by controlling the motions of existing faces is an important task of great consequence to social media industries. For easy use and intuitive control, semantically meaningful and fully disentangled parameters should be used as modifications. However, many existing techniques do not provide such fine-grained controls or use indirect editing methods i.e. mimic motions of other individuals. In this paper, a Portrait Image Neural Renderer (PIRenderer) is proposed to control the face motions with the parameters of three-dimensional morphable face models (3DMMs). The propo…
Our ability to sample realistic natural images, particularly faces, has advanced by leaps and bounds in recent years, yet our ability to exert fine-tuned control over the generative process has lagged behind. If this new technology is to find practical uses, we need to achieve a level of control over generative networks which, without sacrificing realism, is on par with that seen in computer graphics and character animation. To this end we propose ConfigNet, a neural face model that allows for controlling individual aspects of output images in semantically meaningful ways and that is a signifi…
SVIP: Semantically Contextualized Visual Patches for Zero-Shot Learning
University of Southern Queensland（南昆士兰大学）；University of Queensland（昆士兰大学）；The Hong Kong Polytechnic University（香港理工大学）；University of Electronic Science and Technology of China（中国电子科学技术研究中心）
The face reenactment is a popular facial animation method where the person's identity is taken from the source image and the facial motion from the driving image. Recent works have demonstrated high quality results by combining the facial landmark based motion representations with the generative adversarial networks. These models perform best if the source and driving images depict the same person or if the facial structures are otherwise very similar. However, if the identity differs, the driving facial structures leak to the output distorting the reenactment result. We propose a novel Facial…
University of Copenhagen（哥本哈根大学）；Rigshospitalet（哥本哈根大学国立医院）
Generative models such as Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs) play an increasingly important role in medical image analysis. The latent spaces of these models often show semantically meaningful directions corresponding to human-interpretable image transformations. However, until now, their exploration for medical images has been limited due to the requirement of supervised data. Several methods for unsupervised discovery of interpretable directions in GAN latent spaces have shown interesting results on natural images. This work explores the potential of a…
Technical University of Kaiserslautern（凯泽斯劳滕工业大学）；Technical University of Berlin（柏林工业大学）；University of Birmingham（伯明翰大学）；NPZ Innovation GmbH（NPZ创新有限公司）；University of St.Gallen（圣加仑大学）
We propose a novel training methodology -- Concept Group Learning (CGL) -- that encourages training of interpretable CNN filters by partitioning filters in each layer into concept groups, each of which is trained to learn a single visual concept. We achieve this through a novel regularization strategy that forces filters in the same group to be active in similar image regions for a given layer. We additionally use a regularizer to encourage a sparse weighting of the concept groups in each layer so that a few concept groups can have greater importance than others. We quantitatively evaluate CGL…
The semantically disentangled latent subspace in GAN provides rich interpretable controls in image generation. This paper includes two contributions on semantic latent subspace analysis in the scenario of face generation using StyleGAN2. First, we propose a novel approach to disentangle latent subspace semantics by exploiting existing face analysis models, e.g., face parsers and face landmark detectors. These models provide the flexibility to construct various criterions with very concrete and interpretable semantic meanings (e.g., change face shape or change skin color) to restrict latent sub…
College of Computer Science and Technology, Zhejiang University（浙江大学计算机科学与技术学院）；Alibaba Group（阿里巴巴集团）；Faculty of Engineering and Information Technology, University of Technology Sydney（悉尼科技大学工程与信息技术学院）
In this paper, we present an approach, namely Lexical Semantic Image Completion (LSIC), that may have potential applications in art, design, and heritage conservation, among several others. Existing image completion procedure is highly subjective by considering only visual context, which may trigger unpredictable results which are plausible but not faithful to a grounded knowledge. To permit both grounded and controllable completion process, we advocate generating results faithful to both visual and lexical semantic context, i.e., the description of leaving holes or blank regions in the image …
Hierarchical Vision Transformer with Prototypes for Interpretable Medical Image Classification
Ulm University Medical Center（乌尔姆大学医学中心）；BGZ - Bildgebungszentrum（BGZ影像中心）；i2SouI - Innovative Imaging in Surgical Oncology Ulm（乌尔姆外科肿瘤创新影像中心）；XAIRAD - Cooperation for Artificial Intelligence in Experimental Radiology（XAIRAD实验放射学人工智能合作中心）
We present a framework for training GANs with explicit control over generated images. We are able to control the generated image by settings exact attributes such as age, pose, expression, etc. Most approaches for editing GAN-generated images achieve partial control by leveraging the latent space disentanglement properties, obtained implicitly after standard GAN training. Such methods are able to change the relative intensity of certain attributes, but not explicitly set their values. Recently proposed methods, designed for explicit control over human faces, harness morphable 3D face models to…
Trajectory Forcing: Structure-First Generation with Controllable Semantic Trajectories
University of Tübingen（图宾根大学）；ETH Zürich（苏黎世联邦理工学院）；Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）；ELLIS Institute（ELLIS研究所）；Tübingen AI Center（图宾根人工智能中心）
PiPViT: Patch-based Visual Interpretable Prototypes for Retinal Image Analysis
Christian Doppler Laboratory for Artificial Intelligence in Retina（人工智能在视网膜领域的克里斯蒂安·多普勒实验室）；Institute of Artificial Intelligence（人工智能研究所）；Center for Medical Data Science（医学数据科学中心）；Medical University of Vienna（维也纳医学大学）
Condition Weaving Meets Expert Modulation: Towards Universal and Controllable Image Generation
State Key Laboratory of Advanced Rail Autonomous Operation（先进轨道交通自主运行国家重点实验室）；School of Computer Science and Technology（计算机科学与技术学院）；Visual Intellgence +X International Cooperation Joint Laboratory of MOE（教育部视觉智能+X国际合作联合实验室）；Hong Kong University of Science and Technology（香港科技大学）；SenseTime Research（商汤科技研究院）；Beijing Jiaotong University（北京交通大学）；SenseTime Research Institute（时光机器研究院）
Latent space exploration is a technique that discovers interpretable latent directions and manipulates latent codes to edit various attributes in images generated by generative adversarial networks (GANs). However, in previous work, spatial control is limited to simple transformations (e.g., translation and rotation), and it is laborious to identify appropriate latent directions and adjust their parameters. In this paper, we tackle the problem of editing the StyleGAN image layout by annotating the image directly. To do so, we propose an interactive framework for manipulating latent codes in ac…
Wageningen University（瓦赫宁根大学）；Oxford University（牛津大学）；CMAP, École Polytechnique（巴黎综合理工学院应用数学中心）；IRISA, University Bretagne Sud, CNRS（南布列塔尼大学、法国国家科学研究中心、IRISA）；EPFL（洛桑联邦理工学院）
Convolutional neural networks (CNN) are known to learn an image representation that captures concepts relevant to the task, but do so in an implicit way that hampers model interpretability. However, one could argue that such a representation is hidden in the neurons and can be made explicit by teaching the model to recognize semantically interpretable attributes that are present in the scene. We call such an intermediate layer a \emph{semantic bottleneck}. Once the attributes are learned, they can be re-combined to reach the final decision and provide both an accurate prediction and an explici…
