Synthesizing face images from monochrome sketches is one of the most fundamental tasks in the field of image-to-image translation. However, it is still challenging to (1)~make models learn the high-dimensional face features such as geometry and color, and (2)~take into account the characteristics of input sketches. Existing methods often use sketches as indirect inputs (or as auxiliary inputs) to guide the models, resulting in the loss of sketch features or the alteration of geometry information. In this paper, we introduce a Sketch-Guided Latent Diffusion Model (SGLDM), an LDM-based network architect trained on the paired sketch-face dataset. We apply a Multi-Auto-Encoder (AE) to encode the different input sketches from different regions of a face from pixel space to a feature map in latent space, which enables us to reduce the dimension of the sketch input while preserving the geometry-related information of local face details. We build a sketch-face paired dataset based on the existing method that extracts the edge map from an image. We then introduce a Stochastic Region Abstraction (SRA), an approach to augment our dataset to improve the robustness of SGLDM to handle sketch input with arbitrary abstraction. The evaluation study shows that SGLDM can synthesize high-quality face images with different expressions, facial accessories, and hairstyles from various sketches with different abstraction levels.
Sentiment analysis AKA opinion mining is one of the most widely used NLP applications to identify human intentions from their reviews. In the education sector, opinion mining is used to listen to student opinions and enhance their learning-teaching practices pedagogically. With advancements in sentiment annotation techniques and AI methodologies, student comments can be labelled with their sentiment orientation without much human intervention. In this review article, (1) we consider the role of emotional analysis in education from four levels: document level, sentence level, entity level, and aspect level, (2) sentiment annotation techniques including lexicon-based and corpus-based approaches for unsupervised annotations are explored, (3) the role of AI in sentiment analysis with methodologies like machine learning, deep learning, and transformers are discussed, (4) the impact of sentiment analysis on educational procedures to enhance pedagogy, decision-making, and evaluation are presented. Educational institutions have been widely invested to build sentiment analysis tools and process their student feedback to draw their opinions and insights. Applications built on sentiment analysis of student feedback are reviewed in this study. Challenges in sentiment analysis like multi-polarity, polysemous, negation words, and opinion spam detection are explored and their trends in the research space are discussed. The future directions of sentiment analysis in education are discussed.
What will happen when unsupervised learning meets diffusion models for real-world image deraining? To answer it, we propose RainDiffusion, the first unsupervised image deraining paradigm based on diffusion models. Beyond the traditional unsupervised wisdom of image deraining, RainDiffusion introduces stable training of unpaired real-world data instead of weakly adversarial training. RainDiffusion consists of two cooperative branches: Non-diffusive Translation Branch (NTB) and Diffusive Translation Branch (DTB). NTB exploits a cycle-consistent architecture to bypass the difficulty in unpaired training of standard diffusion models by generating initial clean/rainy image pairs. DTB leverages two conditional diffusion modules to progressively refine the desired output with initial image pairs and diffusive generative prior, to obtain a better generalization ability of deraining and rain generation. Rain-Diffusion is a non adversarial training paradigm, serving as a new standard bar for real-world image deraining. Extensive experiments confirm the superiority of our RainDiffusion over un/semi-supervised methods and show its competitive advantages over fully-supervised ones.
Mental healthcare is one of the prominent parts of the healthcare industry with alarming concerns related to patients depression, stress leading to self-harm and threat to fellow patients and medical staff. To provide a therapeutic environment for both patients and staff, aggressive or agitated patients need to be monitored remotely and track their vital signs and physical activities continuously. Remote patient monitoring (RPM) using non-invasive technology could enable contactless monitoring of acutely ill patients in a mental health facility. Enabling the RPM system with AI unlocks a predictive environment in which future vital signs of the patients can be forecasted. This paper discusses an AI-enabled RPM system framework with a non-invasive digital technology RFID using its in-built NCS mechanism to retrieve vital signs and physical actions of patients. Based on the retrieved time series data, future vital signs of patients for the upcoming 3 hours and classify their physical actions into 10 labelled physical activities. This framework assists to avoid any unforeseen clinical disasters and take precautionary measures with medical intervention at right time. A case study of a middle-aged PTSD patient treated with the AI-enabled RPM system is demonstrated in this study.
End-to-end generative methods are considered a more promising solution for image restoration in physics-based vision compared with the traditional deconstructive methods based on handcrafted composition models. However, existing generative methods still have plenty of room for improvement in quantitative performance. More crucially, these methods are considered black boxes due to weak interpretability and there is rarely a theory trying to explain their mechanism and learning process. In this study, we try to re-interpret these generative methods for image restoration tasks using information theory. Different from conventional understanding, we analyzed the information flow of these methods and identified three sources of information (extracted high-level information, retained low-level information, and external information that is absent from the source inputs) are involved and optimized respectively in generating the restoration results. We further derived their learning behaviors, optimization objectives, and the corresponding information boundaries by extending the information bottleneck principle. Based on this theoretic framework, we found that many existing generative methods tend to be direct applications of the general models designed for conventional generation tasks, which may suffer from problems including over-invested abstraction processes, inherent details loss, and vanishing gradients or imbalance in training. We analyzed these issues with both intuitive and theoretical explanations and proved them with empirical evidence respectively. Ultimately, we proposed general solutions or ideas to address the above issue and validated these approaches with performance boosts on six datasets of three different image restoration tasks.
We propose an interactive editing method that allows humans to help deep neural networks (DNNs) learn a latent space more consistent with human knowledge, thereby improving classification accuracy on indistinguishable ambiguous data. Firstly, we visualize high-dimensional data features through dimensionality reduction methods and design an interactive system \textit{SpaceEditing} to display the visualized data. \textit{SpaceEditing} provides a 2D workspace based on the idea of spatial layout. In this workspace, the user can move the projection data in it according to the system guidance. Then, \textit{SpaceEditing} will find the corresponding high-dimensional features according to the projection data moved by the user, and feed the high-dimensional features back to the network for retraining, therefore achieving the purpose of interactively modifying the high-dimensional latent space for the user. Secondly, to more rationally incorporate human knowledge into the training process of neural networks, we design a new loss function that enables the network to learn user-modified information. Finally, We demonstrate how \textit{SpaceEditing} meets user needs through three case studies while evaluating our proposed new method, and the results confirm the effectiveness of our method.
Scene understanding is an essential and challenging task in computer vision. To provide the visually fundamental graphical structure of an image, the scene graph has received increased attention due to its powerful semantic representation. However, it is difficult to draw a proper scene graph for image retrieval, image generation, and multi-modal applications. The conventional scene graph annotation interface is not easy to use in image annotations, and the automatic scene graph generation approaches using deep neural networks are prone to generate redundant content while disregarding details. In this work, we propose SGDraw, a scene graph drawing interface using object-oriented scene graph representation to help users draw and edit scene graphs interactively. For the proposed object-oriented representation, we consider the objects, attributes, and relationships of objects as a structural unit. SGDraw provides a web-based scene graph annotation and generation tool for scene understanding applications. To verify the effectiveness of the proposed interface, we conducted a comparison study with the conventional tool and the user experience study. The results show that SGDraw can help generate scene graphs with richer details and describe the images more accurately than traditional bounding box annotations. We believe the proposed SGDraw can be useful in various vision tasks, such as image retrieval and generation.
LiDAR and camera, as two different sensors, supply geometric (point clouds) and semantic (RGB images) information of 3D scenes. However, it is still challenging for existing methods to fuse data from the two cross sensors, making them complementary for quality 3D object detection (3OD). We propose ImLiDAR, a new 3OD paradigm to narrow the cross-sensor discrepancies by progressively fusing the multi-scale features of camera Images and LiDAR point clouds. ImLiDAR enables to provide the detection head with cross-sensor yet robustly fused features. To achieve this, two core designs exist in ImLiDAR. First, we propose a cross-sensor dynamic message propagation module to combine the best of the multi-scale image and point features. Second, we raise a direct set prediction problem that allows designing an effective set-based detector to tackle the inconsistency of the classification and localization confidences, and the sensitivity of hand-tuned hyperparameters. Besides, the novel set-based detector can be detachable and easily integrated into various detection networks. Comparisons on both the KITTI and SUN-RGBD datasets show clear visual and numerical improvements of our ImLiDAR over twenty-three state-of-the-art 3OD methods.
There is a trend to fuse multi-modal information for 3D object detection (3OD). However, the challenging problems of low lightweightness, poor flexibility of plug-and-play, and inaccurate alignment of features are still not well-solved, when designing multi-modal fusion newtorks. We propose PointSee, a lightweight, flexible and effective multi-modal fusion solution to facilitate various 3OD networks by semantic feature enhancement of LiDAR point clouds assembled with scene images. Beyond the existing wisdom of 3OD, PointSee consists of a hidden module (HM) and a seen module (SM): HM decorates LiDAR point clouds using 2D image information in an offline fusion manner, leading to minimal or even no adaptations of existing 3OD networks; SM further enriches the LiDAR point clouds by acquiring point-wise representative semantic features, leading to enhanced performance of existing 3OD networks. Besides the new architecture of PointSee, we propose a simple yet efficient training strategy, to ease the potential inaccurate regressions of 2D object detection networks. Extensive experiments on the popular outdoor/indoor benchmarks show numerical improvements of our PointSee over twenty-two state-of-the-arts.