Although monocular 3D human pose estimation methods have made significant progress, it is far from being solved due to the inherent depth ambiguity. Instead, exploiting multi-view information is a practical way to achieve absolute 3D human pose estimation. In this paper, we propose a simple yet effective pipeline for weakly-supervised cross-view 3D human pose estimation. By only using two camera views, our method can achieve state-of-the-art performance in a weakly-supervised manner, requiring no 3D ground truth but only 2D annotations. Specifically, our method contains two steps: triangulation and refinement. First, given the 2D keypoints that can be obtained through any classic 2D detection methods, triangulation is performed across two views to lift the 2D keypoints into coarse 3D poses. Then, a novel cross-view U-shaped graph convolutional network (CV-UGCN), which can explore the spatial configurations and cross-view correlations, is designed to refine the coarse 3D poses. In particular, the refinement progress is achieved through weakly-supervised learning, in which geometric and structure-aware consistency checks are performed. We evaluate our method on the standard benchmark dataset, Human3.6M. The Mean Per Joint Position Error on the benchmark dataset is 27.4 mm, which outperforms existing state-of-the-art methods remarkably (27.4 mm vs 30.2 mm).
Multisource image analysis that leverages complementary spectral, spatial, and structural information benefits fine-grained object recognition that aims to classify an object into one of many similar subcategories. However, for multisource tasks that involve relatively small objects, even the smallest registration errors can introduce high uncertainty in the classification process. We approach this problem from a weakly supervised learning perspective in which the input images correspond to larger neighborhoods around the expected object locations where an object with a given class label is present in the neighborhood without any knowledge of its exact location. The proposed method uses a single-source deep instance attention model with parallel branches for joint localization and classification of objects, and extends this model into a multisource setting where a reference source that is assumed to have no location uncertainty is used to aid the fusion of multiple sources in four different levels: probability level, logit level, feature level, and pixel level. We show that all levels of fusion provide higher accuracies compared to the state-of-the-art, with the best performing method of feature-level fusion resulting in 53% accuracy for the recognition of 40 different types of trees, corresponding to an improvement of 5.7% over the best performing baseline when RGB, multispectral, and LiDAR data are used. We also provide an in-depth comparison by evaluating each model at various parameter complexity settings, where the increased model capacity results in a further improvement of 6.3% over the default capacity setting.
Deepfakes have become a critical social problem, and detecting them is of utmost importance. Also, deepfake generation methods are advancing, and it is becoming harder to detect. While many deepfake detection models can detect different types of deepfakes separately, they perform poorly on generalizing the detection performance over multiple types of deepfake. This motivates us to develop a generalized model to detect different types of deepfakes. Therefore, in this work, we introduce a practical digital forensic tool to detect different types of deepfakes simultaneously and propose Transfer learning-based Autoencoder with Residuals (TAR). The ultimate goal of our work is to develop a unified model to detect various types of deepfake videos with high accuracy, with only a small number of training samples that can work well in real-world settings. We develop an autoencoder-based detection model with Residual blocks and sequentially perform transfer learning to detect different types of deepfakes simultaneously. Our approach achieves a much higher generalized detection performance than the state-of-the-art methods on the FaceForensics++ dataset. In addition, we evaluate our model on 200 real-world Deepfake-in-the-Wild (DW) videos of 50 celebrities available on the Internet and achieve 89.49% zero-shot accuracy, which is significantly higher than the best baseline model (gaining 10.77%), demonstrating and validating the practicability of our approach.
The use of gait for person identification has important advantages such as being non-invasive, unobtrusive, not requiring cooperation and being less likely to be obscured compared to other biometrics. Existing methods for gait recognition require cooperative gait scenarios, in which a single person is walking multiple times in a straight line in front of a camera. We aim to address the challenges of real-world scenarios in which camera feeds capture multiple people, who in most cases pass in front of the camera only once. We address privacy concerns by using only motion information of walking individuals, with no identifiable appearance-based information. As such, we propose a novel weakly supervised learning framework, WildGait, which consists of training a Spatio-Temporal Graph Convolutional Network on a large number of automatically annotated skeleton sequences obtained from raw, real-world, surveillance streams to learn useful gait signatures. We collected the training data and compiled the largest dataset of walking skeletons called Uncooperative Wild Gait, containing over 38k tracklets of anonymized walking 2D skeletons. We release the dataset for public use. Our results show that, with fine-tuning, we surpass the current state-of-the-art pose-based gait recognition solutions. Our proposed method is reliable in training gait recognition methods in unconstrained environments, especially in settings with scarce amounts of annotated data.
Multiple-instance learning is a subset of weakly supervised learning where labels are applied to sets of instances rather than the instances themselves. Under the standard assumption, a set is positive only there is if at least one instance in the set which is positive. This paper introduces a series of multiple-instance learning benchmarks generated from MNIST, Fashion-MNIST, and CIFAR10. These benchmarks test the standard, presence, absence, and complex assumptions and provide a framework for future benchmarks to be distributed. I implement and evaluate several multiple-instance learning techniques against the benchmarks. Further, I evaluate the Noisy-And method with label noise and find mixed results with different datasets. The models are implemented in TensorFlow 2.4.1 and are available on GitHub. The benchmarks are available from PyPi as mil-benchmarks and on GitHub.
Multi-instance learning is a type of weakly supervised learning. It deals with tasks where the data is a set of bags and each bag is a set of instances. Only the bag labels are observed whereas the labels for the instances are unknown. An important advantage of multi-instance learning is that by representing objects as a bag of instances, it is able to preserve the inherent dependencies among parts of the objects. Unfortunately, most existing algorithms assume all instances to be \textit{identically and independently distributed}, which violates real-world scenarios since the instances within a bag are rarely independent. In this work, we propose the Multi-Instance Variational Auto-Encoder (MIVAE) algorithm which explicitly models the dependencies among the instances for predicting both bag labels and instance labels. Experimental results on several multi-instance benchmarks and end-to-end medical imaging datasets demonstrate that MIVAE performs better than state-of-the-art algorithms for both instance label and bag label prediction tasks.
Strategies for improving the training and prediction quality of weakly supervised machine learning models vary in how much they are tailored to a specific task or integrated with a specific model architecture. In this work, we introduce Knodle, a software framework that treats weak data annotations, deep learning models, and methods for improving weakly supervised training as separate, modular components. This modularization gives the training process access to fine-grained information such as data set characteristics, matches of heuristic rules, or elements of the deep learning model ultimately used for prediction. Hence, our framework can encompass a wide range of training methods for improving weak supervision, ranging from methods that only look at correlations of rules and output classes (independently of the machine learning model trained with the resulting labels), to those that harness the interplay of neural networks and weakly labeled data. We illustrate the benchmarking potential of the framework with a performance comparison of several reference implementations on a selection of datasets that are already available in Knodle. The framework is published as an open-source Python package knodle and available at https://github.com/knodle/knodle.
Weakly-supervised text classification aims to induce text classifiers from only a few user-provided seed words. The vast majority of previous work assumes high-quality seed words are given. However, the expert-annotated seed words are sometimes non-trivial to come up with. Furthermore, in the weakly-supervised learning setting, we do not have any labeled document to measure the seed words' efficacy, making the seed word selection process "a walk in the dark". In this work, we remove the need for expert-curated seed words by first mining (noisy) candidate seed words associated with the category names. We then train interim models with individual candidate seed words. Lastly, we estimate the interim models' error rate in an unsupervised manner. The seed words that yield the lowest estimated error rates are added to the final seed word set. A comprehensive evaluation of six binary classification tasks on four popular datasets demonstrates that the proposed method outperforms a baseline using only category name seed words and obtained comparable performance as a counterpart using expert-annotated seed words.
Detecting and localizing objects in the real 3D space, which plays a crucial role in scene understanding, is particularly challenging given only a monocular image due to the geometric information loss during imagery projection. We propose MonoGRNet for the amodal 3D object detection from a monocular image via geometric reasoning in both the observed 2D projection and the unobserved depth dimension. MonoGRNet decomposes the monocular 3D object detection task into four sub-tasks including 2D object detection, instance-level depth estimation, projected 3D center estimation and local corner regression. The task decomposition significantly facilitates the monocular 3D object detection, allowing the target 3D bounding boxes to be efficiently predicted in a single forward pass, without using object proposals, post-processing or the computationally expensive pixel-level depth estimation utilized by previous methods. In addition, MonoGRNet flexibly adapts to both fully and weakly supervised learning, which improves the feasibility of our framework in diverse settings. Experiments are conducted on KITTI, Cityscapes and MS COCO datasets. Results demonstrate the promising performance of our framework in various scenarios.
Visual engagement in social media platforms comprises interactions with photo posts including comments, shares, and likes. In this paper, we leverage such visual engagement clues as supervisory signals for representation learning. However, learning from engagement signals is non-trivial as it is not clear how to bridge the gap between low-level visual information and high-level social interactions. We present VisE, a weakly supervised learning approach, which maps social images to pseudo labels derived by clustered engagement signals. We then study how models trained in this way benefit subjective downstream computer vision tasks such as emotion recognition or political bias detection. Through extensive studies, we empirically demonstrate the effectiveness of VisE across a diverse set of classification tasks beyond the scope of conventional recognition.
We present SCANimate, an end-to-end trainable framework that takes raw 3D scans of a clothed human and turns them into an animatable avatar. These avatars are driven by pose parameters and have realistic clothing that moves and deforms naturally. SCANimate does not rely on a customized mesh template or surface mesh registration. We observe that fitting a parametric 3D body model, like SMPL, to a clothed human scan is tractable while surface registration of the body topology to the scan is often not, because clothing can deviate significantly from the body shape. We also observe that articulated transformations are invertible, resulting in geometric cycle consistency in the posed and unposed shapes. These observations lead us to a weakly supervised learning method that aligns scans into a canonical pose by disentangling articulated deformations without template-based surface registration. Furthermore, to complete missing regions in the aligned scans while modeling pose-dependent deformations, we introduce a locally pose-aware implicit function that learns to complete and model geometry with learned pose correctives. In contrast to commonly used global pose embeddings, our local pose conditioning significantly reduces long-range spurious correlations and improves generalization to unseen poses, especially when training data is limited. Our method can be applied to pose-aware appearance modeling to generate a fully textured avatar. We demonstrate our approach on various clothing types with different amounts of training data, outperforming existing solutions and other variants in terms of fidelity and generality in every setting. The code is available at https://scanimate.is.tue.mpg.de.
Weakly supervised learning has emerged as an appealing alternative to alleviate the need for large labeled datasets in semantic segmentation. Most current approaches exploit class activation maps (CAMs), which can be generated from image-level annotations. Nevertheless, resulting maps have been demonstrated to be highly discriminant, failing to serve as optimal proxy pixel-level labels. We present a novel learning strategy that leverages self-supervision in a multi-modal image scenario to significantly enhance original CAMs. In particular, the proposed method is based on two observations. First, the learning of fully-supervised segmentation networks implicitly imposes equivariance by means of data augmentation, whereas this implicit constraint disappears on CAMs generated with image tags. And second, the commonalities between image modalities can be employed as an efficient self-supervisory signal, correcting the inconsistency shown by CAMs obtained across multiple modalities. To effectively train our model, we integrate a novel loss function that includes a within-modality and a cross-modality equivariant term to explicitly impose these constraints during training. In addition, we add a KL-divergence on the class prediction distributions to facilitate the information exchange between modalities, which, combined with the equivariant regularizers further improves the performance of our model. Exhaustive experiments on the popular multi-modal BRATS dataset demonstrate that our approach outperforms relevant recent literature under the same learning conditions.
Visual grounding, which aims to build a correspondence between visual objects and their language entities, plays a key role in cross-modal scene understanding. One promising and scalable strategy for learning visual grounding is to utilize weak supervision from only image-caption pairs. Previous methods typically rely on matching query phrases directly to a precomputed, fixed object candidate pool, which leads to inaccurate localization and ambiguous matching due to lack of semantic relation constraints. In our paper, we propose a novel context-aware weakly-supervised learning method that incorporates coarse-to-fine object refinement and entity relation modeling into a two-stage deep network, capable of producing more accurate object representation and matching. To effectively train our network, we introduce a self-taught regression loss for the proposal locations and a classification loss based on parsed entity relations. Extensive experiments on two public benchmarks Flickr30K Entities and ReferItGame demonstrate the efficacy of our weakly grounding framework. The results show that we outperform the previous methods by a considerable margin, achieving 59.27\% top-1 accuracy in Flickr30K Entities and 37.68\% in the ReferItGame dataset respectively (Code is available at https://github.com/youngfly11/ReIR-WeaklyGrounding.pytorch.git).
In recent years, there has been a rapid growth in the application of machine learning techniques that leverage aviation data collected from commercial airline operations to improve safety. Anomaly detection and predictive maintenance have been the main targets for machine learning applications. However, this paper focuses on the identification of precursors, which is a relatively newer application. Precursors are events correlated with adverse events that happen prior to the adverse event itself. Therefore, precursor mining provides many benefits including understanding the reasons behind a safety incident and the ability to identify signatures, which can be tracked throughout a flight to alert the operators of the potential for an adverse event in the future. This work proposes using the multiple-instance learning (MIL) framework, a weakly supervised learning task, combined with carefully designed binary classifier leveraging a Multi-Head Convolutional Neural Network-Recurrent Neural Network (MHCNN-RNN) architecture. Multi-class classifiers are then created and compared, enabling the prediction of different adverse events for any given flight by combining binary classifiers, and by modifying the MHCNN-RNN to handle multiple outputs. Results obtained showed that the multiple binary classifiers perform better and are able to accurately forecast high speed and high path angle events during the approach phase. Multiple binary classifiers are also capable of determining the aircraft's parameters that are correlated to these events. The identified parameters can be considered precursors to the events and may be studied/tracked further to prevent these events in the future.
Recently, several weakly supervised learning methods have been devoted to utilize bounding box supervision for training deep semantic segmentation models. Most existing methods usually leverage the generic proposal generators (e.g., dense CRF and MCG) to produce enhanced segmentation masks for further training segmentation models. These proposal generators, however, are generic and not specifically designed for box-supervised semantic segmentation, thereby leaving some leeway for improving segmentation performance. In this paper, we aim at seeking for a more accurate learning-based class-agnostic pseudo mask generator tailored to box-supervised semantic segmentation. To this end, we resort to a pixel-level annotated auxiliary dataset where the class labels are non-overlapped with those of the box-annotated dataset. For learning pseudo mask generator from the auxiliary dataset, we present a bi-level optimization formulation. In particular, the lower subproblem is used to learn box-supervised semantic segmentation, while the upper subproblem is used to learn an optimal class-agnostic pseudo mask generator. The learned pseudo segmentation mask generator can then be deployed to the box-annotated dataset for improving weakly supervised semantic segmentation. Experiments on PASCAL VOC 2012 dataset show that the learned pseudo mask generator is effective in boosting segmentation performance, and our method can further close the performance gap between box-supervised and fully-supervised models. Our code will be made publicly available at https://github.com/Vious/LPG_BBox_Segmentation .
Despite tremendous efforts, it is very challenging to generate a robust model to assist in the accurate quantification assessment of COVID-19 on chest CT images. Due to the nature of blurred boundaries, the supervised segmentation methods usually suffer from annotation biases. To support unbiased lesion localisation and to minimise the labeling costs, we propose a data-driven framework supervised by only image-level labels. The framework can explicitly separate potential lesions from original images, with the help of a generative adversarial network and a lesion-specific decoder. Experiments on two COVID-19 datasets demonstrate the effectiveness of the proposed framework and its superior performance to several existing methods.
In the Gastric Histopathology Image Classification (GHIC) tasks, which are usually weakly supervised learning missions, there is inevitably redundant information in the images. Therefore, designing networks that can focus on effective distinguishing features has become a popular research topic. In this paper, to accomplish the tasks of GHIC superiorly and to assist pathologists in clinical diagnosis, an intelligent Hierarchical Conditional Random Field based Attention Mechanism (HCRF-AM) model is proposed. The HCRF-AM model consists of an Attention Mechanism (AM) module and an Image Classification (IC) module. In the AM module, an HCRF model is built to extract attention regions. In the IC module, a Convolutional Neural Network (CNN) model is trained with the attention regions selected and then an algorithm called Classification Probability-based Ensemble Learning is applied to obtain the image-level results from patch-level output of the CNN. In the experiment, a classification specificity of 96.67% is achieved on a gastric histopathology dataset with 700 images. Our HCRF-AM model demonstrates high classification performance and shows its effectiveness and future potential in the GHIC field.
We propose a data-driven scene flow estimation algorithm exploiting the observation that many 3D scenes can be explained by a collection of agents moving as rigid bodies. At the core of our method lies a deep architecture able to reason at the \textbf{object-level} by considering 3D scene flow in conjunction with other 3D tasks. This object level abstraction, enables us to relax the requirement for dense scene flow supervision with simpler binary background segmentation mask and ego-motion annotations. Our mild supervision requirements make our method well suited for recently released massive data collections for autonomous driving, which do not contain dense scene flow annotations. As output, our model provides low-level cues like pointwise flow and higher-level cues such as holistic scene understanding at the level of rigid objects. We further propose a test-time optimization refining the predicted rigid scene flow. We showcase the effectiveness and generalization capacity of our method on four different autonomous driving datasets. We release our source code and pre-trained models under \url{github.com/zgojcic/Rigid3DSceneFlow}.
Weakly supervised learning has drawn considerable attention recently to reduce the expensive time and labor consumption of labeling massive data. In this paper, we investigate a novel weakly supervised learning problem of learning from similarity-confidence (Sconf) data, where we aim to learn an effective binary classifier from only unlabeled data pairs equipped with confidence that illustrates their degree of similarity (two examples are similar if they belong to the same class). To solve this problem, we propose an unbiased estimator of the classification risk that can be calculated from only Sconf data and show that the estimation error bound achieves the optimal convergence rate. To alleviate potential overfitting when flexible models are used, we further employ a risk correction scheme on the proposed risk estimator. Experimental results demonstrate the effectiveness of the proposed methods.
Recent studies demonstrated the eligibility of convolutional neural networks (CNNs) for solving the image registration problem. CNNs enable faster transformation estimation and greater generalization capability needed for better support during medical interventions. Conventional fully-supervised training requires a lot of high-quality ground truth data such as voxel-to-voxel transformations, which typically are attained in a too tedious and error-prone manner. In our work, we use weakly-supervised learning, which optimizes the model indirectly only via segmentation masks that are a more accessible ground truth than the deformation fields. Concerning the weak supervision, we investigate two segmentation similarity measures: multiscale Dice similarity coefficient (mDSC) and the similarity between segmentation-derived signed distance maps (SDMs). We show that the combination of mDSC and SDM similarity measures results in a more accurate and natural transformation pattern together with a stronger gradient coverage. Furthermore, we introduce an auxiliary input to the neural network for the prior information about the prostate location in the MR sequence, which mostly is available preoperatively. This approach significantly outperforms the standard two-input models. With weakly labelled MR-TRUS prostate data, we showed registration quality comparable to the state-of-the-art deep learning-based method.