Recently, multi-modal vision-language foundation models have gained significant attention in the medical field. While these models offer great opportunities, they still face crucial challenges, such as the requirement for fine-grained knowledge understanding in computer-aided diagnosis and the capability of utilizing very limited or even no task-specific labeled data in real-world clinical applications. In this study, we present MaCo, a masked contrastive chest X-ray foundation model that tackles these challenges. MaCo explores masked contrastive learning to simultaneously achieve fine-grained image understanding and zero-shot learning for a variety of medical imaging tasks. It designs a correlation weighting mechanism to adjust the correlation between masked chest X-ray image patches and their corresponding reports, thereby enhancing the model's representation learning capabilities. To evaluate the performance of MaCo, we conducted extensive experiments using 6 well-known open-source X-ray datasets. The experimental results demonstrate the superiority of MaCo over 10 state-of-the-art approaches across tasks such as classification, segmentation, detection, and phrase grounding. These findings highlight the significant potential of MaCo in advancing a wide range of medical image analysis tasks.
Visual document understanding (VDU) has rapidly advanced with the development of powerful multi-modal language models. However, these models typically require extensive document pre-training data to learn intermediate representations and often suffer a significant performance drop in real-world online industrial settings. A primary issue is their heavy reliance on OCR engines to extract local positional information within document pages, which limits the models' ability to capture global information and hinders their generalizability, flexibility, and robustness. In this paper, we introduce GlobalDoc, a cross-modal transformer-based architecture pre-trained in a self-supervised manner using three novel pretext objective tasks. GlobalDoc improves the learning of richer semantic concepts by unifying language and visual representations, resulting in more transferable models. For proper evaluation, we also propose two novel document-level downstream VDU tasks, Few-Shot Document Image Classification (DIC) and Content-based Document Image Retrieval (DIR), designed to simulate industrial scenarios more closely. Extensive experimentation has been conducted to demonstrate GlobalDoc's effectiveness in practical settings.
Multivariate time series (MTS) data collected from multiple sensors provide the potential for accurate abnormal activity detection in smart healthcare scenarios. However, anomalies exhibit diverse patterns and become unnoticeable in MTS data. Consequently, achieving accurate anomaly detection is challenging since we have to capture both temporal dependencies of time series and inter-relationships among variables. To address this problem, we propose a Residual-based Anomaly Detection approach, Rs-AD, for effective representation learning and abnormal activity detection. We evaluate our scheme on a real-world gait dataset and the experimental results demonstrate an F1 score of 0.839.
Obtaining sparse, interpretable representations of observable data is crucial in many machine learning and signal processing tasks. For data representing flows along the edges of a graph, an intuitively interpretable way to obtain such representations is to lift the graph structure to a simplicial complex: The eigenvectors of the associated Hodge-Laplacian, respectively the incidence matrices of the corresponding simplicial complex then induce a Hodge decomposition, which can be used to represent the observed data in terms of gradient, curl, and harmonic flows. In this paper, we generalize this approach to cellular complexes and introduce the flow representation learning problem, i.e., the problem of augmenting the observed graph by a set of cells, such that the eigenvectors of the associated Hodge Laplacian provide a sparse, interpretable representation of the observed edge flows on the graph. We show that this problem is NP-hard and introduce an efficient approximation algorithm for its solution. Experiments on real-world and synthetic data demonstrate that our algorithm outperforms state-of-the-art methods with respect to approximation error, while being computationally efficient.
The cross-modal retrieval task has raised continuous attention in recent years with the increasing scale of multi-modal data, which has broad application prospects including multimedia data management and intelligent search engine. Most existing methods mainly project data of different modalities into a common representation space where label information is often exploited to distinguish samples from different semantic categories. However, they typically treat each label as an independent individual and ignore the underlying semantic structure of labels. In this paper, we propose an end-to-end adaptive label-aware graph convolutional network (ALGCN) by designing both the instance representation learning branch and the label representation learning branch, which can obtain modality-invariant and discriminative representations for cross-modal retrieval. Firstly, we construct an instance representation learning branch to transform instances of different modalities into a common representation space. Secondly, we adopt Graph Convolutional Network (GCN) to learn inter-dependent classifiers in the label representation learning branch. In addition, a novel adaptive correlation matrix is proposed to efficiently explore and preserve the semantic structure of labels in a data-driven manner. Together with a robust self-supervision loss for GCN, the GCN model can be supervised to learn an effective and robust correlation matrix for feature propagation. Comprehensive experimental results on three benchmark datasets, NUS-WIDE, MIRFlickr and MS-COCO, demonstrate the superiority of ALGCN, compared with the state-of-the-art methods in cross-modal retrieval.
Repeated parameter sharing in federated learning causes significant information leakage about private data, thus defeating its main purpose: data privacy. Mitigating the risk of this information leakage, using state of the art differentially private algorithms, also does not come for free. Randomized mechanisms can prevent convergence of models on learning even the useful representation functions, especially if there is more disagreement between local models on the classification functions (due to data heterogeneity). In this paper, we consider a representation federated learning objective that encourages various parties to collaboratively refine the consensus part of the model, with differential privacy guarantees, while separately allowing sufficient freedom for local personalization (without releasing it). We prove that in the linear representation setting, while the objective is non-convex, our proposed new algorithm \DPFEDREP\ converges to a ball centered around the \emph{global optimal} solution at a linear rate, and the radius of the ball is proportional to the reciprocal of the privacy budget. With this novel utility analysis, we improve the SOTA utility-privacy trade-off for this problem by a factor of $\sqrt{d}$, where $d$ is the input dimension. We empirically evaluate our method with the image classification task on CIFAR10, CIFAR100, and EMNIST, and observe a significant performance improvement over the prior work under the same small privacy budget. The code can be found in this link: https://github.com/shenzebang/CENTAUR-Privacy-Federated-Representation-Learning.
Face forgery videos have caused severe public concerns, and many detectors have been proposed. However, most of these detectors suffer from limited generalization when detecting videos from unknown distributions, such as from unseen forgery methods. In this paper, we find that different forgery videos have distinct spatiotemporal patterns, which may be the key to generalization. To leverage this finding, we propose a Latent Spatiotemporal Adaptation~(LAST) approach to facilitate generalized face forgery video detection. The key idea is to optimize the detector adaptive to the spatiotemporal patterns of unknown videos in latent space to improve the generalization. Specifically, we first model the spatiotemporal patterns of face videos by incorporating a lightweight CNN to extract local spatial features of each frame and then cascading a vision transformer to learn the long-term spatiotemporal representations in latent space, which should contain more clues than in pixel space. Then by optimizing a transferable linear head to perform the usual forgery detection task on known videos and recover the spatiotemporal clues of unknown target videos in a semi-supervised manner, our detector could flexibly adapt to unknown videos' spatiotemporal patterns, leading to improved generalization. Additionally, to eliminate the influence of specific forgery videos, we pre-train our CNN and transformer only on real videos with two simple yet effective self-supervised tasks: reconstruction and contrastive learning in latent space and keep them frozen during fine-tuning. Extensive experiments on public datasets demonstrate that our approach achieves state-of-the-art performance against other competitors with impressive generalization and robustness.
Since rain streaks show a variety of shapes and directions, learning the degradation representation is extremely challenging for single image deraining. Existing methods are mainly targeted at designing complicated modules to implicitly learn latent degradation representation from coupled rainy images. This way, it is hard to decouple the content-independent degradation representation due to the lack of explicit constraint, resulting in over- or under-enhancement problems. To tackle this issue, we propose a novel Latent Degradation Representation Constraint Network (LDRCNet) that consists of Direction-Aware Encoder (DAEncoder), UNet Deraining Network, and Multi-Scale Interaction Block (MSIBlock). Specifically, the DAEncoder is proposed to adaptively extract latent degradation representation by using the deformable convolutions to exploit the direction consistency of rain streaks. Next, a constraint loss is introduced to explicitly constraint the degradation representation learning during training. Last, we propose an MSIBlock to fuse with the learned degradation representation and decoder features of the deraining network for adaptive information interaction, which enables the deraining network to remove various complicated rainy patterns and reconstruct image details. Experimental results on synthetic and real datasets demonstrate that our method achieves new state-of-the-art performance.
The linear take-make-dispose paradigm at the foundations of our traditional economy is proving to be unsustainable due to waste pollution and material supply uncertainties. Hence, increasing the circularity of material flows is necessary. In this paper, we make a step towards circular healthcare by developing several vision systems targeting three main circular economy tasks: resources mapping and quantification, waste sorting, and disassembly. The performance of our systems demonstrates that representation-learning vision can improve the recovery chain, where autonomous systems are key enablers due to the contamination risks. We also published two fully-annotated datasets for image segmentation and for key-point tracking in disassembly operations of inhalers and glucose meters. The datasets and source code are publicly available.
Appearance-based gaze estimation has shown great promise in many applications by using a single general-purpose camera as the input device. However, its success is highly depending on the availability of large-scale well-annotated gaze datasets, which are sparse and expensive to collect. To alleviate this challenge we propose ConGaze, a contrastive learning-based framework that leverages unlabeled facial images to learn generic gaze-aware representations across subjects in an unsupervised way. Specifically, we introduce the gaze-specific data augmentation to preserve the gaze-semantic features and maintain the gaze consistency, which are proven to be crucial for effective contrastive gaze representation learning. Moreover, we devise a novel subject-conditional projection module that encourages a share feature extractor to learn gaze-aware and generic representations. Our experiments on three public gaze estimation datasets show that ConGaze outperforms existing unsupervised learning solutions by 6.7% to 22.5%; and achieves 15.1% to 24.6% improvement over its supervised learning-based counterpart in cross-dataset evaluations.
We address the problem of learning representations from observations of a scene involving an agent and an external object the agent interacts with. To this end, we propose a representation learning framework extracting the location in physical space of both the agent and the object from unstructured observations of arbitrary nature. Our framework relies on the actions performed by the agent as the only source of supervision, while assuming that the object is displaced by the agent via unknown dynamics. We provide a theoretical foundation and formally prove that an ideal learner is guaranteed to infer an isometric representation, disentangling the agent from the object and correctly extracting their locations. We evaluate empirically our framework on a variety of scenarios, showing that it outperforms vision-based approaches such as a state-of-the-art keypoint extractor. We moreover demonstrate how the extracted representations enable the agent to solve downstream tasks via reinforcement learning in an efficient manner.
Irregular data in real-world are usually organized as heterogeneous graphs (HGs) consisting of multiple types of nodes and edges. To explore useful knowledge from real-world data, both the large-scale encyclopedic HG datasets and corresponding effective learning methods are crucial, but haven't been well investigated. In this paper, we construct a large-scale HG benchmark dataset named UniKG from Wikidata to facilitate knowledge mining and heterogeneous graph representation learning. Overall, UniKG contains more than 77 million multi-attribute entities and 2000 diverse association types, which significantly surpasses the scale of existing HG datasets. To perform effective learning on the large-scale UniKG, two key measures are taken, including (i) the semantic alignment strategy for multi-attribute entities, which projects the feature description of multi-attribute nodes into a common embedding space to facilitate node aggregation in a large receptive field; (ii) proposing a novel plug-and-play anisotropy propagation module (APM) to learn effective multi-hop anisotropy propagation kernels, which extends methods of large-scale homogeneous graphs to heterogeneous graphs. These two strategies enable efficient information propagation among a tremendous number of multi-attribute entities and meantimes adaptively mine multi-attribute association through the multi-hop aggregation in large-scale HGs. We set up a node classification task on our UniKG dataset, and evaluate multiple baseline methods which are constructed by embedding our APM into large-scale homogenous graph learning methods. Our UniKG dataset and the baseline codes have been released at https://github.com/Yide-Qiu/UniKG.
Large machine learning models trained on diverse data have recently seen unprecedented success. Federated learning enables training on private data that may otherwise be inaccessible, such as domain-specific datasets decentralized across many clients. However, federated learning can be difficult to scale to large models when clients have limited resources. This challenge often results in a trade-off between model size and access to diverse data. To mitigate this issue and facilitate training of large models on edge devices, we introduce a simple yet effective strategy, Federated Layer-wise Learning, to simultaneously reduce per-client memory, computation, and communication costs. Clients train just a single layer each round, reducing resource costs considerably with minimal performance degradation. We also introduce Federated Depth Dropout, a complementary technique that randomly drops frozen layers during training, to further reduce resource usage. Coupling these two techniques enables us to effectively train significantly larger models on edge devices. Specifically, we reduce training memory usage by 5x or more in federated self-supervised representation learning and demonstrate that performance in downstream tasks is comparable to conventional federated self-supervised learning.
Knowledge graph (KG) embedding has been used to benefit the diagnosis of animal diseases by analyzing electronic medical records (EMRs), such as notes and veterinary records. However, learning representations to capture entities and relations with literal information in KGs is challenging as the KGs show heterogeneous properties and various types of literal information. Meanwhile, the existing methods mostly aim to preserve graph structures surrounding target nodes without considering different types of literals, which could also carry significant information. In this paper, we propose a knowledge graph embedding model for the efficient diagnosis of animal diseases, which could learn various types of literal information and graph structure and fuse them into unified representations, namely LiteralKG. Specifically, we construct a knowledge graph that is built from EMRs along with literal information collected from various animal hospitals. We then fuse different types of entities and node feature information into unified vector representations through gate networks. Finally, we propose a self-supervised learning task to learn graph structure in pretext tasks and then towards various downstream tasks. Experimental results on link prediction tasks demonstrate that our model outperforms the baselines that consist of state-of-the-art models. The source code is available at https://github.com/NSLab-CUK/LiteralKG.
Message Passing Neural Networks (MPNNs) have emerged as the {\em de facto} standard in graph representation learning. However, when it comes to link prediction, they often struggle, surpassed by simple heuristics such as Common Neighbor (CN). This discrepancy stems from a fundamental limitation: while MPNNs excel in node-level representation, they stumble with encoding the joint structural features essential to link prediction, like CN. To bridge this gap, we posit that, by harnessing the orthogonality of input vectors, pure message-passing can indeed capture joint structural features. Specifically, we study the proficiency of MPNNs in approximating CN heuristics. Based on our findings, we introduce the Message Passing Link Predictor (MPLP), a novel link prediction model. MPLP taps into quasi-orthogonal vectors to estimate link-level structural features, all while preserving the node-level complexities. Moreover, our approach demonstrates that leveraging message-passing to capture structural features could offset MPNNs' expressiveness limitations at the expense of estimation variance. We conduct experiments on benchmark datasets from various domains, where our method consistently outperforms the baseline methods.
The recently released artificial intelligence conversational agent, ChatGPT, has gained significant attention in academia and real life. A multitude of early ChatGPT users eagerly explore its capabilities and share their opinions on it via social media. Both user queries and social media posts express public concerns regarding this advanced dialogue system. To mine public concerns about ChatGPT, a novel Self-Supervised neural Topic Model (SSTM), which formalizes topic modeling as a representation learning procedure, is proposed in this paper. Extensive experiments have been conducted on Twitter posts about ChatGPT and queries asked by ChatGPT users. And experimental results demonstrate that the proposed approach could extract higher quality public concerns with improved interpretability and diversity, surpassing the performance of state-of-the-art approaches.
Several domains increasingly rely on machine learning in their applications. The resulting heavy dependence on data has led to the emergence of various laws and regulations around data ethics and privacy and growing awareness of the need for privacy-preserving machine learning (ppML). Current ppML techniques utilize methods that are either purely based on cryptography, such as homomorphic encryption, or that introduce noise into the input, such as differential privacy. The main criticism given to those techniques is the fact that they either are too slow or they trade off a model s performance for improved confidentiality. To address this performance reduction, we aim to leverage robust representation learning as a way of encoding our data while optimizing the privacy-utility trade-off. Our method centers on training autoencoders in a multi-objective manner and then concatenating the latent and learned features from the encoding part as the encoded form of our data. Such a deep learning-powered encoding can then safely be sent to a third party for intensive training and hyperparameter tuning. With our proposed framework, we can share our data and use third party tools without being under the threat of revealing its original form. We empirically validate our results on unimodal and multimodal settings, the latter following a vertical splitting system and show improved performance over state-of-the-art.
Current state-of-the-art self-supervised approaches, are effective when trained on individual domains but show limited generalization on unseen domains. We observe that these models poorly generalize even when trained on a mixture of domains, making them unsuitable to be deployed under diverse real-world setups. We therefore propose a general-purpose, lightweight Domain Disentanglement Module (DDM) that can be plugged into any self-supervised encoder to effectively perform representation learning on multiple, diverse domains with or without shared classes. During pre-training according to a self-supervised loss, DDM enforces a disentanglement in the representation space by splitting it into a domain-variant and a domain-invariant portion. When domain labels are not available, DDM uses a robust clustering approach to discover pseudo-domains. We show that pre-training with DDM can show up to 3.5% improvement in linear probing accuracy on state-of-the-art self-supervised models including SimCLR, MoCo, BYOL, DINO, SimSiam and Barlow Twins on multi-domain benchmarks including PACS, DomainNet and WILDS. Models trained with DDM show significantly improved generalization (7.4%) to unseen domains compared to baselines. Therefore, DDM can efficiently adapt self-supervised encoders to provide high-quality, generalizable representations for diverse multi-domain data.
Face analysis tasks have a wide range of applications, but the universal facial representation has only been explored in a few works. In this paper, we explore high-performance pre-training methods to boost the face analysis tasks such as face alignment and face parsing. We propose a self-supervised pre-training framework, called \textbf{\it Mask Contrastive Face (MCF)}, with mask image modeling and a contrastive strategy specially adjusted for face domain tasks. To improve the facial representation quality, we use feature map of a pre-trained visual backbone as a supervision item and use a partially pre-trained decoder for mask image modeling. To handle the face identity during the pre-training stage, we further use random masks to build contrastive learning pairs. We conduct the pre-training on the LAION-FACE-cropped dataset, a variants of LAION-FACE 20M, which contains more than 20 million face images from Internet websites. For efficiency pre-training, we explore our framework pre-training performance on a small part of LAION-FACE-cropped and verify the superiority with different pre-training settings. Our model pre-trained with the full pre-training dataset outperforms the state-of-the-art methods on multiple downstream tasks. Our model achieves 0.932 NME$_{diag}$ for AFLW-19 face alignment and 93.96 F1 score for LaPa face parsing. Code is available at https://github.com/nomewang/MCF.
Joint Embedding Architecture-based self-supervised learning methods have attributed the composition of data augmentations as a crucial factor for their strong representation learning capabilities. While regional dropout strategies have proven to guide models to focus on lesser indicative parts of the objects in supervised methods, it hasn't been adopted by self-supervised methods for generating positive pairs. This is because the regional dropout methods are not suitable for the input sampling process of the self-supervised methodology. Whereas dropping informative pixels from the positive pairs can result in inefficient training, replacing patches of a specific object with a different one can steer the model from maximizing the agreement between different positive pairs. Moreover, joint embedding representation learning methods have not made robustness their primary training outcome. To this end, we propose the ViewMix augmentation policy, specially designed for self-supervised learning, upon generating different views of the same image, patches are cut and pasted from one view to another. By leveraging the different views created by this augmentation strategy, multiple joint embedding-based self-supervised methodologies obtained better localization capability and consistently outperformed their corresponding baseline methods. It is also demonstrated that incorporating ViewMix augmentation policy promotes robustness of the representations in the state-of-the-art methods. Furthermore, our experimentation and analysis of compute times suggest that ViewMix augmentation doesn't introduce any additional overhead compared to other counterparts.