Text recognition is a major computer vision task with a big set of associated challenges. One of those traditional challenges is the coupled nature of text recognition and segmentation. This problem has been progressively solved over the past decades, going from segmentation based recognition to segmentation free approaches, which proved more accurate and much cheaper to annotate data for. We take a step from segmentation-free single line recognition towards segmentation-free multi-line / full page recognition. We propose a novel and simple neural network module, termed \textbf{OrigamiNet}, that can augment any CTC-trained, fully convolutional single line text recognizer, to convert it into a multi-line version by providing the model with enough spatial capacity to be able to properly collapse a 2D input signal into 1D without losing information. Such modified networks can be trained using exactly their same simple original procedure, and using only \textbf{unsegmented} image and text pairs. We carry out a set of interpretability experiments that show that our trained models learn an accurate implicit line segmentation. We achieve state-of-the-art character error rate on both IAM \& ICDAR 2017 HTR benchmarks for handwriting recognition, surpassing all other methods in the literature. On IAM we even surpass single line methods that use accurate localization information during training. Our code is available online at \url{https://github.com/IntuitionMachines/OrigamiNet}.
We propose adversarial constrained-CNN loss, a new paradigm of constrained-CNN loss methods, for weakly supervised medical image segmentation. In the new paradigm, prior knowledge is encoded and depicted by reference masks, and is further employed to impose constraints on segmentation outputs through adversarial learning with reference masks. Unlike pseudo label methods for weakly supervised segmentation, such reference masks are used to train a discriminator rather than a segmentation network, and thus are not required to be paired with specific images. Our new paradigm not only greatly facilitates imposing prior knowledge on network's outputs, but also provides stronger and higher-order constraints, i.e., distribution approximation, through adversarial learning. Extensive experiments involving different medical modalities, different anatomical structures, different topologies of the object of interest, different levels of prior knowledge and weakly supervised annotations with different annotation ratios is conducted to evaluate our ACCL method. Consistently superior segmentation results over the size constrained-CNN loss method have been achieved, some of which are close to the results of full supervision, thus fully verifying the effectiveness and generalization of our method. Specifically, we report an average Dice score of 75.4% with an average annotation ratio of 0.65%, surpassing the prior art, i.e., the size constrained-CNN loss method, by a large margin of 11.4%. Our codes are made publicly available at https://github.com/PengyiZhang/ACCL.
We propose a novel weakly supervised learning segmentation based on several global constraints derived from box annotations. Particularly, we leverage a classical tightness prior to a deep learning setting via imposing a set of constraints on the network outputs. Such a powerful topological prior prevents solutions from excessive shrinking by enforcing any horizontal or vertical line within the bounding box to contain, at least, one pixel of the foreground region. Furthermore, we integrate our deep tightness prior with a global background emptiness constraint, guiding training with information outside the bounding box. We demonstrate experimentally that such a global constraint is much more powerful than standard cross-entropy for the background class. Our optimization problem is challenging as it takes the form of a large set of inequality constraints on the outputs of deep networks. We solve it with sequence of unconstrained losses based on a recent powerful extension of the log-barrier method, which is well-known in the context of interior-point methods. This accommodates standard stochastic gradient descent (SGD) for training deep networks, while avoiding computationally expensive and unstable Lagrangian dual steps and projections. Extensive experiments over two different public data sets and applications (prostate and brain lesions) demonstrate that the synergy between our global tightness and emptiness priors yield very competitive performances, approaching full supervision and outperforming significantly DeepCut. Furthermore, our approach removes the need for computationally expensive proposal generation. Our code is shared anonymously.
Segmentation using deep learning has shown promising directions in medical imaging as it aids in the analysis and diagnosis of diseases. Nevertheless, a main drawback of deep models is that they require a large amount of pixel-level labels, which are laborious and expensive to obtain. To mitigate this problem, weakly supervised learning has emerged as an efficient alternative, which employs image-level labels, scribbles, points, or bounding boxes as supervision. Among these, image-level labels are easier to obtain. However, since this type of annotation only contains object category information, the segmentation task under this learning paradigm is a challenging problem. To address this issue, visual salient regions derived from trained classification networks are typically used. Despite their success to identify important regions on classification tasks, these saliency regions only focus on the most discriminant areas of an image, limiting their use in semantic segmentation. In this work, we propose a manifold driven attention-based network to enhance visual salient regions, thereby improving segmentation accuracy in a weakly supervised setting. Our method generates superior attention maps directly during inference without the need of extra computations. We evaluate the benefits of our approach in the task of segmentation using a public benchmark on skin lesion images. Results demonstrate that our method outperforms the state-of-the-art GradCAM by a margin of ~22% in terms of Dice score.
Recent work in word spotting in handwritten documents has yielded impressive results. This progress has largely been made by supervised learning systems, which are dependent on manually annotated data, making deployment to new collections a significant effort. In this paper, we propose an approach that utilises transcripts without bounding box annotations to train segmentation-free query-by-string word spotting models, given a partially trained model. This is done through a training-free alignment procedure based on hidden Markov models. This procedure creates a tentative mapping between word region proposals and the transcriptions to automatically create additional weakly annotated training data, without choosing any single alignment possibility as the correct one. When only using between 1% and 7% of the fully annotated training sets for partial convergence, we automatically annotate the remaining training data and successfully train using it. On all our datasets, our final trained model then comes within a few mAP% of the performance from a model trained with the full training set used as ground truth. We believe that this will be a significant advance towards a more general use of word spotting, since digital transcription data will already exist for parts of many collections of interest.
Photovoltaic is one of the most important renewable energy sources for dealing with world-wide steadily increasing energy consumption. This raises the demand for fast and scalable automatic quality management during production and operation. However, the detection and segmentation of cracks on electroluminescence (EL) images of mono- or polycrystalline solar modules is a challenging task. In this work, we propose a weakly supervised learning strategy that only uses image-level annotations to obtain a method that is capable of segmenting cracks on EL images of solar cells. We use a modified ResNet-50 to derive a segmentation from network activation maps. We use defect classification as a surrogate task to train the network. To this end, we apply normalized Lp normalization to aggregate the activation maps into single scores for classification. In addition, we provide a study how different parameterizations of the normalized Lp layer affect the segmentation performance. This approach shows promising results for the given task. However, we think that the method has the potential to solve other weakly supervised segmentation problems as well.
The recent state-of-the-art deep learning methods have significantly improved brain tumor segmentation. However, fully supervised training requires a large amount of manually labeled masks, which is highly time-consuming and needs domain expertise. Weakly supervised learning with scribbles provides a good trade-off between model accuracy and the effort of manual labeling. However, for segmenting the hierarchical brain tumor structures, manually labeling scribbles for each substructure could still be demanding. In this paper, we use only two kinds of weak labels, i.e., scribbles on whole tumor and healthy brain tissue, and global labels for the presence of each substructure, to train a deep learning model to segment all the sub-regions. Specifically, we train two networks in two phases: first, we only use whole tumor scribbles to train a whole tumor (WT) segmentation network, which roughly recovers the WT mask of training data; then we cluster the WT region with the guide of global labels. The rough substructure segmentation from clustering is used as weak labels to train the second network. The dense CRF loss is used to refine the weakly supervised segmentation. We evaluate our approach on the BraTS2017 dataset and achieve competitive WT dice score as well as comparable scores on substructure segmentation compared to an upper bound when trained with fully annotated masks.
To minimize the annotation costs associated with the training of semantic segmentation models, researchers have extensively investigated weakly-supervised segmentation approaches. In the current weakly-supervised segmentation methods, the most widely adopted approach is based on visualization. However, the visualization results are not generally equal to semantic segmentation. Therefore, to perform accurate semantic segmentation under the weakly supervised condition, it is necessary to consider the mapping functions that convert the visualization results into semantic segmentation. For such mapping functions, the conditional random field and iterative re-training using the outputs of a segmentation model are usually used. However, these methods do not always guarantee improvements in accuracy; therefore, if we apply these mapping functions iteratively multiple times, eventually the accuracy will not improve or will decrease. In this paper, to make the most of such mapping functions, we assume that the results of the mapping function include noise, and we improve the accuracy by removing noise. To achieve our aim, we propose the self-supervised difference detection module, which estimates noise from the results of the mapping functions by predicting the difference between the segmentation masks before and after the mapping. We verified the effectiveness of the proposed method by performing experiments on the PASCAL Visual Object Classes 2012 dataset, and we achieved 64.9\% in the val set and 65.5\% in the test set. Both of the results become new state-of-the-art under the same setting of weakly supervised semantic segmentation.
Annotation of medical images has been a major bottleneck for the development of accurate and robust machine learning models. Annotation is costly and time-consuming and typically requires expert knowledge, especially in the medical domain. Here, we propose to use minimal user interaction in the form of extreme point clicks in order to train a segmentation model that can, in turn, be used to speed up the annotation of medical images. We use extreme points in each dimension of a 3D medical image to constrain an initial segmentation based on the random walker algorithm. This segmentation is then used as a weak supervisory signal to train a fully convolutional network that can segment the organ of interest based on the provided user clicks. We show that the network's predictions can be refined through several iterations of training and prediction using the same weakly annotated data. Ultimately, our method has the potential to speed up the generation process of new training datasets for the development of new machine learning and deep learning-based models for, but not exclusively, medical image analysis.
Many functional and structural neuroimaging studies call for accurate morphometric segmentation of different brain structures starting from image intensity values of MRI scans. Current automatic (multi-) atlas-based segmentation strategies often lack accuracy on difficult-to-segment brain structures and, since these methods rely on atlas-to-scan alignment, they may take long processing times. Recently, methods deploying solutions based on Convolutional Neural Networks (CNNs) are making the direct analysis of out-of-the-scanner data feasible. However, current CNN-based solutions partition the test volume into 2D or 3D patches, which are processed independently. This entails a loss of global contextual information thereby negatively impacting the segmentation accuracy. In this work, we design and test an optimised end-to-end CNN architecture that makes the exploitation of global spatial information computationally tractable, allowing to process a whole MRI volume at once. We adopt a weakly supervised learning strategy by exploiting a large dataset composed by 947 out-of-the-scanner (3 Tesla T1-weighted 1mm isotropic MP-RAGE 3D sequences) MR Images. The resulting model is able to produce accurate multi-structure segmentation results in only few seconds. Different quantitative measures demonstrate an improved accuracy of our solution when compared to state-of-the-art techniques. Moreover, through a randomised survey involving expert neuroscientists, we show that subjective judgements clearly prefer our solution with respect to the widely adopted atlas-based FreeSurfer software.
Existing weakly supervised semantic segmentation (WSSS) methods usually utilize the results of pre-trained saliency detection (SD) models without explicitly modeling the connections between the two tasks, which is not the most efficient configuration. Here we propose a unified multi-task learning framework to jointly solve WSSS and SD using a single network, \ie saliency, and segmentation network (SSNet). SSNet consists of a segmentation network (SN) and a saliency aggregation module (SAM). For an input image, SN generates the segmentation result and, SAM predicts the saliency of each category and aggregating the segmentation masks of all categories into a saliency map. The proposed network is trained end-to-end with image-level category labels and class-agnostic pixel-level saliency labels. Experiments on PASCAL VOC 2012 segmentation dataset and four saliency benchmark datasets show the performance of our method compares favorably against state-of-the-art weakly supervised segmentation methods and fully supervised saliency detection methods.
The performance of the state-of-the-art image segmentation methods heavily relies on the high-quality annotations, which are not easily affordable, particularly for medical data. To alleviate this limitation, in this study, we propose a weakly supervised image segmentation method based on a deep geodesic prior. We hypothesize that integration of this prior information can reduce the adverse effects of weak labels in segmentation accuracy. Our proposed algorithm is based on a prior information, extracted from an auto-encoder, trained to map objects geodesic maps to their corresponding binary maps. The obtained information is then used as an extra term in the loss function of the segmentor. In order to show efficacy of the proposed strategy, we have experimented segmentation of cardiac substructures with clean and two levels of noisy labels (L1, L2). Our experiments showed that the proposed algorithm boosted the performance of baseline deep learning-based segmentation for both clean and noisy labels by 4.4%, 4.6%(L1), and 6.3%(L2) in dice score, respectively. We also showed that the proposed method was more robust in the presence of high-level noise due to the existence of shape priors.
An efficient strategy for weakly-supervised segmentation is to impose constraints or regularization priors on target regions. Recent efforts have focused on incorporating such constraints in the training of convolutional neural networks (CNN), however this has so far been done within a continuous optimization framework. Yet, various segmentation constraints and regularization can be modeled and optimized more efficiently in a discrete formulation. This paper proposes a method, based on the alternating direction method of multipliers (ADMM) algorithm, to train a CNN with discrete constraints and regularization priors. This method is applied to the segmentation of medical images with weak annotations, where both size constraints and boundary length regularization are enforced. Experiments on a benchmark cardiac segmentation dataset show our method to yield a performance near to full supervision.
Object detection plays an important role in various visual applications. However, the precision and speed of detector are usually contradictory. One main reason for fast detectors' precision reduction is that small objects are hard to be detected. To address this problem, we propose a multiple receptive field and small-object-focusing weakly-supervised segmentation network (MRFSWSnet) to achieve fast object detection. In MRFSWSnet, multiple receptive fields block (MRF) is used to pay attention to the object and its adjacent background's different spatial location with different weights to enhance the feature's discriminability. In addition, in order to improve the accuracy of small object detection, a small-object-focusing weakly-supervised segmentation module which only focuses on small object instead of all objects is integrated into the detection network for auxiliary training to improve the precision of small object detection. Extensive experiments show the effectiveness of our method on both PASCAL VOC and MS COCO detection datasets. In particular, with a lower resolution version of 300x300, MRFSWSnet achieves 80.9% mAP on VOC2007 test with an inference speed of 15 milliseconds per frame, which is the state-of-the-art detector among real-time detectors.
This study investigates imposing hard inequality constraints on the outputs of convolutional neural networks (CNN) during training. Several recent works showed that the theoretical and practical advantages of Lagrangian optimization over simple penalties do not materialize in practice when dealing with modern CNNs involving millions of parameters. Therefore, constrained CNNs are typically handled with penalties. We propose *log-barrier extensions*, which approximate Lagrangian optimization of constrained-CNN problems with a sequence of unconstrained losses. Unlike standard interior-point and log-barrier methods, our formulation does not need an initial feasible solution. The proposed extension yields an upper bound on the duality gap -- generalizing the result of standard log-barriers -- and yielding sub-optimality certificates for feasible solutions. While sub-optimality is not guaranteed for non-convex problems, this result shows that log-barrier extensions are a principled way to approximate Lagrangian optimization for constrained CNNs via implicit dual variables. We report weakly supervised image segmentation experiments, with various constraints, showing that our formulation outperforms substantially the existing constrained-CNN methods, in terms of accuracy, constraint satisfaction and training stability, more so when dealing with a large number of constraints.
Weakly supervised semantic segmentation with only image-level labels saves large human effort to annotate pixel-level labels. Cutting-edge approaches rely on various innovative constraints and heuristic rules to generate the masks for every single image. Although great progress has been achieved by these methods, they treat each image independently and do not take account of the relationships across different images. In this paper, however, we argue that the cross-image relationship is vital for weakly supervised segmentation. Because it connects related regions across images, where supplementary representations can be propagated to obtain more consistent and integral regions. To leverage this information, we propose an end-to-end cross-image affinity module, which exploits pixel-level cross-image relationships with only image-level labels. By means of this, our approach achieves 64.3% and 65.3% mIoU on Pascal VOC 2012 validation and test set respectively, which is a new state-of-the-art result by only using image-level labels for weakly supervised semantic segmentation, demonstrating the superiority of our approach.
Rich high-quality annotated data is critical for semantic segmentation learning, yet acquiring dense and pixel-wise ground-truth is both labor- and time-consuming. Coarse annotations (e.g., scribbles, coarse polygons) offer an economical alternative, with which training phase could hardly generate satisfactory performance unfortunately. In order to generate high-quality annotated data with a low time cost for accurate segmentation, in this paper, we propose a novel annotation enrichment strategy, which expands existing coarse annotations of training data to a finer scale. Extensive experiments on the Cityscapes and PASCAL VOC 2012 benchmarks have shown that the neural networks trained with the enriched annotations from our framework yield a significant improvement over that trained with the original coarse labels. It is highly competitive to the performance obtained by using human annotated dense annotations. The proposed method also outperforms among other state-of-the-art weakly-supervised segmentation methods.
This work provides a simple approach to discover tight object bounding boxes with only image-level supervision, called Tight box mining with Surrounding Segmentation Context (TS2C). We observe that object candidates mined through current multiple instance learning methods are usually trapped to discriminative object parts, rather than the entire object. TS2C leverages surrounding segmentation context derived from weakly-supervised segmentation to suppress such low-quality distracting candidates and boost the high-quality ones. Specifically, TS2C is developed based on two key properties of desirable bounding boxes: 1) high purity, meaning most pixels in the box are with high object response, and 2) high completeness, meaning the box covers high object response pixels comprehensively. With such novel and computable criteria, more tight candidates can be discovered for learning a better object detector. With TS2C, we obtain 48.0% and 44.4% mAP scores on VOC 2007 and 2012 benchmarks, which are the new state-of-the-arts.
State-of-the-art visual recognition and detection systems increasingly rely on large amounts of training data and complex classifiers. Therefore it becomes increasingly expensive both to manually annotate datasets and to keep running times at levels acceptable for practical applications. In this paper, we propose two solutions to address these issues. First, we introduce a weakly supervised, segmentation-based approach to learn accurate detectors and image classifiers from weak supervisory signals that provide only approximate constraints on target localization. We illustrate our system on the problem of action detection in static images (Pascal VOC Actions 2012), using human visual search patterns as our training signal. Second, inspired from the saccade-and-fixate operating principle of the human visual system, we use reinforcement learning techniques to train efficient search models for detection. Our sequential method is weakly supervised and general (it does not require eye movements), finds optimal search strategies for any given detection confidence function and achieves performance similar to exhaustive sliding window search at a fraction of its computational cost.
We are interested in inferring object segmentation by leveraging only object class information, and by considering only minimal priors on the object segmentation task. This problem could be viewed as a kind of weakly supervised segmentation task, and naturally fits the Multiple Instance Learning (MIL) framework: every training image is known to have (or not) at least one pixel corresponding to the image class label, and the segmentation task can be rewritten as inferring the pixels belonging to the class of the object (given one image, and its object class). We propose a Convolutional Neural Network-based model, which is constrained during training to put more weight on pixels which are important for classifying the image. We show that at test time, the model has learned to discriminate the right pixels well enough, such that it performs very well on an existing segmentation benchmark, by adding only few smoothing priors. Our system is trained using a subset of the Imagenet dataset and the segmentation experiments are performed on the challenging Pascal VOC dataset (with no fine-tuning of the model on Pascal VOC). Our model beats the state of the art results in weakly supervised object segmentation task by a large margin. We also compare the performance of our model with state of the art fully-supervised segmentation approaches.