Alzheimer's disease and related dementias (ADRD) ranks as the sixth leading cause of death in the US, underlining the importance of accurate ADRD risk prediction. While recent advancement in ADRD risk prediction have primarily relied on imaging analysis, yet not all patients undergo medical imaging before an ADRD diagnosis. Merging machine learning with claims data can reveal additional risk factors and uncover interconnections among diverse medical codes. Our goal is to utilize Graph Neural Networks (GNNs) with claims data for ADRD risk prediction. Addressing the lack of human-interpretable reasons behind these predictions, we introduce an innovative method to evaluate relationship importance and its influence on ADRD risk prediction, ensuring comprehensive interpretation. We employed Variationally Regularized Encoder-decoder Graph Neural Network (VGNN) for estimating ADRD likelihood. We created three scenarios to assess the model's efficiency, using Random Forest and Light Gradient Boost Machine as baselines. We further used our relation importance method to clarify the key relationships for ADRD risk prediction. VGNN surpassed other baseline models by 10% in the area under the receiver operating characteristic. The integration of the GNN model and relation importance interpretation could potentially play an essential role in providing valuable insight into factors that may contribute to or delay ADRD progression. Employing a GNN approach with claims data enhances ADRD risk prediction and provides insights into the impact of interconnected medical code relationships. This methodology not only enables ADRD risk modeling but also shows potential for other image analysis predictions using claims data.
Backdoor attack aims to compromise a model, which returns an adversary-wanted output when a specific trigger pattern appears yet behaves normally for clean inputs. Current backdoor attacks require changing pixels of clean images, which results in poor stealthiness of attacks and increases the difficulty of the physical implementation. This paper proposes a novel physical invisible backdoor based on camera imaging without changing nature image pixels. Specifically, a compromised model returns a target label for images taken by a particular camera, while it returns correct results for other images. To implement and evaluate the proposed backdoor, we take shots of different objects from multi-angles using multiple smartphones to build a new dataset of 21,500 images. Conventional backdoor attacks work ineffectively with some classical models, such as ResNet18, over the above-mentioned dataset. Therefore, we propose a three-step training strategy to mount the backdoor attack. First, we design and train a camera identification model with the phone IDs to extract the camera fingerprint feature. Subsequently, we elaborate a special network architecture, which is easily compromised by our backdoor attack, by leveraging the attributes of the CFA interpolation algorithm and combining it with the feature extraction block in the camera identification model. Finally, we transfer the backdoor from the elaborated special network architecture to the classical architecture model via teacher-student distillation learning. Since the trigger of our method is related to the specific phone, our attack works effectively in the physical world. Experiment results demonstrate the feasibility of our proposed approach and robustness against various backdoor defenses.
Decisions made by convolutional neural networks(CNN) can be understood and explained by visualizing discriminative regions on images. To this end, Class Activation Map (CAM) based methods were proposed as powerful interpretation tools, making the prediction of deep learning models more explainable, transparent, and trustworthy. However, all the CAM-based methods (e.g., CAM, Grad-CAM, and Relevance-CAM) can only be used for interpreting CNN models with fully-connected (FC) layers as a classifier. It is worth noting that many deep learning models classify images without FC layers, e.g., few-shot learning image classification, contrastive learning image classification, and image retrieval tasks. In this work, a post-hoc interpretation tool named feature activation map (FAM) is proposed, which can interpret deep learning models without FC layers as a classifier. In the proposed FAM algorithm, the channel-wise contribution weights are derived from the similarity scores between two image embeddings. The activation maps are linearly combined with the corresponding normalized contribution weights, forming the explanation map for visualization. The quantitative and qualitative experiments conducted on ten deep learning models for few-shot image classification, contrastive learning image classification and image retrieval tasks demonstrate the effectiveness of the proposed FAM algorithm.
Player identification is a crucial component in vision-driven soccer analytics, enabling various downstream tasks such as player assessment, in-game analysis, and broadcast production. However, automatically detecting jersey numbers from player tracklets in videos presents challenges due to motion blur, low resolution, distortions, and occlusions. Existing methods, utilizing Spatial Transformer Networks, CNNs, and Vision Transformers, have shown success in image data but struggle with real-world video data, where jersey numbers are not visible in most of the frames. Hence, identifying frames that contain the jersey number is a key sub-problem to tackle. To address these issues, we propose a robust keyframe identification module that extracts frames containing essential high-level information about the jersey number. A spatio-temporal network is then employed to model spatial and temporal context and predict the probabilities of jersey numbers in the video. Additionally, we adopt a multi-task loss function to predict the probability distribution of each digit separately. Extensive evaluations on the SoccerNet dataset demonstrate that incorporating our proposed keyframe identification module results in a significant 37.81% and 37.70% increase in the accuracies of 2 different test sets with domain gaps. These results highlight the effectiveness and importance of our approach in tackling the challenges of automatic jersey number detection in sports videos.
Deepfake has recently raised a plethora of societal concerns over its possible security threats and dissemination of fake information. Much research on deepfake detection has been undertaken. However, detecting low quality as well as simultaneously detecting different qualities of deepfakes still remains a grave challenge. Most SOTA approaches are limited by using a single specific model for detecting certain deepfake video quality type. When constructing multiple models with prior information about video quality, this kind of strategy incurs significant computational cost, as well as model and training data overhead. Further, it cannot be scalable and practical to deploy in real-world settings. In this work, we propose a universal intra-model collaborative learning framework to enable the effective and simultaneous detection of different quality of deepfakes. That is, our approach is the quality-agnostic deepfake detection method, dubbed QAD . In particular, by observing the upper bound of general error expectation, we maximize the dependency between intermediate representations of images from different quality levels via Hilbert-Schmidt Independence Criterion. In addition, an Adversarial Weight Perturbation module is carefully devised to enable the model to be more robust against image corruption while boosting the overall model's performance. Extensive experiments over seven popular deepfake datasets demonstrate the superiority of our QAD model over prior SOTA benchmarks.
Tsetlin Machines (TMs) provide a fundamental shift from arithmetic-based to logic-based machine learning. Supporting convolution, they deal successfully with image classification datasets like MNIST, Fashion-MNIST, and CIFAR-2. However, the TM struggles with getting state-of-the-art performance on CIFAR-10 and CIFAR-100, representing more complex tasks. This paper introduces plug-and-play collaboration between specialized TMs, referred to as TM Composites. The collaboration relies on a TM's ability to specialize during learning and to assess its competence during inference. When teaming up, the most confident TMs make the decisions, relieving the uncertain ones. In this manner, a TM Composite becomes more competent than its members, benefiting from their specializations. The collaboration is plug-and-play in that members can be combined in any way, at any time, without fine-tuning. We implement three TM specializations in our empirical evaluation: Histogram of Gradients, Adaptive Gaussian Thresholding, and Color Thermometers. The resulting TM Composite increases accuracy on Fashion-MNIST by two percentage points, CIFAR-10 by twelve points, and CIFAR-100 by nine points, yielding new state-of-the-art results for TMs. Overall, we envision that TM Composites will enable an ultra-low energy and transparent alternative to state-of-the-art deep learning on more tasks and datasets.
Diffusion models have emerged as potential tools to tackle the challenge of sparse-view CT reconstruction, displaying superior performance compared to conventional methods. Nevertheless, these prevailing diffusion models predominantly focus on the sinogram or image domains, which can lead to instability during model training, potentially culminating in convergence towards local minimal solutions. The wavelet trans-form serves to disentangle image contents and features into distinct frequency-component bands at varying scales, adeptly capturing diverse directional structures. Employing the Wavelet transform as a guiding sparsity prior significantly enhances the robustness of diffusion models. In this study, we present an innovative approach named the Stage-by-stage Wavelet Optimization Refinement Diffusion (SWORD) model for sparse-view CT reconstruction. Specifically, we establish a unified mathematical model integrating low-frequency and high-frequency generative models, achieving the solution with optimization procedure. Furthermore, we perform the low-frequency and high-frequency generative models on wavelet's decomposed components rather than sinogram or image domains, ensuring the stability of model training. Our method rooted in established optimization theory, comprising three distinct stages, including low-frequency generation, high-frequency refinement and domain transform. Our experimental results demonstrate that the proposed method outperforms existing state-of-the-art methods both quantitatively and qualitatively.
In this work, we investigate the usefulness of vision-language models (VLMs) and large language models for binary few-shot classification of medical images. We utilize the GPT-4 model to generate text descriptors that encapsulate the shape and texture characteristics of objects in medical images. Subsequently, these GPT-4 generated descriptors, alongside VLMs pre-trained on natural images, are employed to classify chest X-rays and breast ultrasound images. Our results indicate that few-shot classification of medical images using VLMs and GPT-4 generated descriptors is a viable approach. However, accurate classification requires to exclude certain descriptors from the calculations of the classification scores. Moreover, we assess the ability of VLMs to evaluate shape features in breast mass ultrasound images. We further investigate the degree of variability among the sets of text descriptors produced by GPT-4. Our work provides several important insights about the application of VLMs for medical image analysis.
Omni-directional images have been used in wide range of applications. For the applications, it would be useful to estimate saliency maps representing probability distributions of gazing points with a head-mounted display, to detect important regions in the omni-directional images. This paper proposes a novel saliency-map estimation model for the omni-directional images by extracting overlapping 2-dimensional (2D) plane images from omni-directional images at various directions and angles of view. While 2D saliency maps tend to have high probability at the center of images (center bias), the high-probability region appears at horizontal directions in omni-directional saliency maps when a head-mounted display is used (equator bias). Therefore, the 2D saliency model with a center-bias layer was fine-tuned with an omni-directional dataset by replacing the center-bias layer to an equator-bias layer conditioned on the elevation angle for the extraction of the 2D plane image. The limited availability of omni-directional images in saliency datasets can be compensated by using the well-established 2D saliency model pretrained by a large number of training images with the ground truth of 2D saliency maps. In addition, this paper proposes a multi-scale estimation method by extracting 2D images in multiple angles of view to detect objects of various sizes with variable receptive fields. The saliency maps estimated from the multiple angles of view were integrated by using pixel-wise attention weights calculated in an integration layer for weighting the optimal scale to each object. The proposed method was evaluated using a publicly available dataset with evaluation metrics for omni-directional saliency maps. It was confirmed that the accuracy of the saliency maps was improved by the proposed method.
The task of Visual Object Navigation (VON) involves an agent's ability to locate a particular object within a given scene. In order to successfully accomplish the VON task, two essential conditions must be fulfilled:1) the user must know the name of the desired object; and 2) the user-specified object must actually be present within the scene. To meet these conditions, a simulator can incorporate pre-defined object names and positions into the metadata of the scene. However, in real-world scenarios, it is often challenging to ensure that these conditions are always met. Human in an unfamiliar environment may not know which objects are present in the scene, or they may mistakenly specify an object that is not actually present. Nevertheless, despite these challenges, human may still have a demand for an object, which could potentially be fulfilled by other objects present within the scene in an equivalent manner. Hence, we propose Demand-driven Navigation (DDN), which leverages the user's demand as the task instruction and prompts the agent to find the object matches the specified demand. DDN aims to relax the stringent conditions of VON by focusing on fulfilling the user's demand rather than relying solely on predefined object categories or names. We propose a method first acquire textual attribute features of objects by extracting common knowledge from a large language model. These textual attribute features are subsequently aligned with visual attribute features using Contrastive Language-Image Pre-training (CLIP). By incorporating the visual attribute features as prior knowledge, we enhance the navigation process. Experiments on AI2Thor with the ProcThor dataset demonstrate the visual attribute features improve the agent's navigation performance and outperform the baseline methods commonly used in VON.