Co-occurrent visual pattern makes aggregating contextual information a common paradigm to enhance the pixel representation for semantic image segmentation. The existing approaches focus on modeling the context from the perspective of the whole image, i.e., aggregating the image-level contextual information. Despite impressive, these methods weaken the significance of the pixel representations of the same category, i.e., the semantic-level contextual information. To address this, this paper proposes to augment the pixel representations by aggregating the image-level and semantic-level contextual information, respectively. First, an image-level context module is designed to capture the contextual information for each pixel in the whole image. Second, we aggregate the representations of the same category for each pixel where the category regions are learned under the supervision of the ground-truth segmentation. Third, we compute the similarities between each pixel representation and the image-level contextual information, the semantic-level contextual information, respectively. At last, a pixel representation is augmented by weighted aggregating both the image-level contextual information and the semantic-level contextual information with the similarities as the weights. Integrating the image-level and semantic-level context allows this paper to report state-of-the-art accuracy on four benchmarks, i.e., ADE20K, LIP, COCOStuff and Cityscapes.
Gigapixel medical images provide massive data, both morphological textures and spatial information, to be mined. Due to the large data scale in histology, deep learning methods play an increasingly significant role as feature extractors. Existing solutions heavily rely on convolutional neural networks (CNNs) for global pixel-level analysis, leaving the underlying local geometric structure such as the interaction between cells in the tumor microenvironment unexplored. The topological structure in medical images, as proven to be closely related to tumor evolution, can be well characterized by graphs. To obtain a more comprehensive representation for downstream oncology tasks, we propose a fusion framework for enhancing the global image-level representation captured by CNNs with the geometry of cell-level spatial information learned by graph neural networks (GNN). The fusion layer optimizes an integration between collaborative features of global images and cell graphs. Two fusion strategies have been developed: one with MLP which is simple but turns out efficient through fine-tuning, and the other with Transformer gains a champion in fusing multiple networks. We evaluate our fusion strategies on histology datasets curated from large patient cohorts of colorectal and gastric cancers for three biomarker prediction tasks. Both two models outperform plain CNNs or GNNs, reaching a consistent AUC improvement of more than 5% on various network backbones. The experimental results yield the necessity for combining image-level morphological features with cell spatial relations in medical image analysis. Codes are available at https://github.com/yiqings/HEGnnEnhanceCnn.
The fetal cortical plate (CP) undergoes drastic morphological changes during the in utero development. Therefore, CP growth and folding patterns are key indicator in the assessment of the brain development and maturation. Magnetic resonance imaging (MRI) offers specific insights for the analysis of quantitative imaging biomarkers. Nonetheless, accurate and, more importantly, topologically correct MR image segmentation remains the key baseline to such analysis. In this study, we propose a deep learning segmentation framework for automatic and morphologically consistent segmentation of the CP in fetal brain MRI. Our contribution is two fold. First, we generalized a multi-dimensional topological loss function in order to enhance the topological accuracy. Second, we introduced hole ratio, a new topology-based validation measure that quantifies the size of the topological defects taking into account the size of the structure of interest. Using two publicly available datasets, we quantitatively evaluated our proposed method based on three complementary metrics which are overlap-, distance- and topology-based on 27 fetal brains. Our results evidence that our topology-integrative framework outperforms state-of-the-art training loss functions on super-resolution reconstructed clinical MRI, not only in shape correctness but also in the classical evaluation metrics. Furthermore, results on additional 31 out-of-domain SR reconstructions from clinical acquisitions were qualitatively assessed by three experts. The experts' consensus ranked our TopoCP method as the best segmentation in 100\% of the cases with a high inter-expert agreement. Overall, both quantitative and qualitative results, on a wide range of gestational ages and number of cases, support the generalizability and added value of our topology-guided framework for fetal CP segmentation.
We explore the use of machine learning techniques to remove the response of large volume $\gamma$-ray detectors from experimental spectra. Segmented $\gamma$-ray total absorption spectrometers (TAS) allow for the simultaneous measurement of individual $\gamma$-ray energy (E$_\gamma$) and total excitation energy (E$_x$). Analysis of TAS detector data is complicated by the fact that the E$_x$ and E$_\gamma$ quantities are correlated, and therefore, techniques that simply unfold using E$_x$ and E$_\gamma$ response functions independently are not as accurate. In this work, we investigate the use of conditional generative adversarial networks (cGANs) to simultaneously unfold $E_{x}$ and $E_{\gamma}$ data in TAS detectors. Specifically, we employ a Pix2Pix cGAN, a generative modeling technique based on recent advances in deep learning, to treat $(E_x, E_{\gamma})$ matrix unfolding as an image-to-image translation problem. We present results for simulated and experimental matrices of single-$\gamma$ and double-$\gamma$ decay cascades. Our model demonstrates characterization capabilities within detector resolution limits for upwards of $90\%$ of simulated test cases.
Automated segmentation of pathological regions of interest has been shown to aid prognosis and follow up treatment. However, accurate pathological segmentations require high quality of annotated data that can be both cost and time intensive to generate. In this work, we propose an automated two-step method that evaluates the quality of medical images from 3D image stacks using a U-net++ model, such that images that can aid further training of the U-net++ model can be detected based on the disagreement in segmentations produced from the final two layers. Images thus detected can then be used to further fine tune the U-net++ model for semantic segmentation. The proposed QU-net++ model isolates around 10\% of images per 3D stack and can scale across imaging modalities to segment cysts in OCT images and ground glass opacity in Lung CT images with Dice cores in the range 0.56-0.72. Thus, the proposed method can be applied for multi-modal binary segmentation of pathology.
This paper focuses on hyperspectral image (HSI) super-resolution that aims to fuse a low-spatial-resolution HSI and a high-spatial-resolution multispectral image to form a high-spatial-resolution HSI (HR-HSI). Existing deep learning-based approaches are mostly supervised that rely on a large number of labeled training samples, which is unrealistic. The commonly used model-based approaches are unsupervised and flexible but rely on hand-craft priors. Inspired by the specific properties of model, we make the first attempt to design a model inspired deep network for HSI super-resolution in an unsupervised manner. This approach consists of an implicit autoencoder network built on the target HR-HSI that treats each pixel as an individual sample. The nonnegative matrix factorization (NMF) of the target HR-HSI is integrated into the autoencoder network, where the two NMF parts, spectral and spatial matrices, are treated as decoder parameters and hidden outputs respectively. In the encoding stage, we present a pixel-wise fusion model to estimate hidden outputs directly, and then reformulate and unfold the model's algorithm to form the encoder network. With the specific architecture, the proposed network is similar to a manifold prior-based model, and can be trained patch by patch rather than the entire image. Moreover, we propose an additional unsupervised network to estimate the point spread function and spectral response function. Experimental results conducted on both synthetic and real datasets demonstrate the effectiveness of the proposed approach.
Image editing using a pretrained StyleGAN generator has emerged as a powerful paradigm for facial editing, providing disentangled controls over age, expression, illumination, etc. However, the approach cannot be directly adopted for video manipulations. We hypothesize that the main missing ingredient is the lack of fine-grained and disentangled control over face location, face pose, and local facial expressions. In this work, we demonstrate that such a fine-grained control is indeed achievable using pretrained StyleGAN by working across multiple (latent) spaces (namely, the positional space, the W+ space, and the S space) and combining the optimization results across the multiple spaces. Building on this enabling component, we introduce Video2StyleGAN that takes a target image and driving video(s) to reenact the local and global locations and expressions from the driving video in the identity of the target image. We evaluate the effectiveness of our method over multiple challenging scenarios and demonstrate clear improvements over alternative approaches.
Unsupervised domain adaptation is critical in various computer vision tasks, such as object detection, instance segmentation, etc. They attempt to reduce domain bias-induced performance degradation while also promoting model application speed. Previous works in domain adaptation object detection attempt to align image-level and instance-level shifts to eventually minimize the domain discrepancy, but they may align single-class features to mixed-class features in image-level domain adaptation because each image in the object detection task may be more than one class and object. In order to achieve single-class with single-class alignment and mixed-class with mixed-class alignment, we treat the mixed-class of the feature as a new class and propose a mixed-classes $H-divergence$ for object detection to achieve homogenous feature alignment and reduce negative transfer. Then, a Semantic Consistency Feature Alignment Model (SCFAM) based on mixed-classes $H-divergence$ was also presented. To improve single-class and mixed-class semantic information and accomplish semantic separation, the SCFAM model proposes Semantic Prediction Models (SPM) and Semantic Bridging Components (SBC). And the weight of the pix domain discriminator loss is then changed based on the SPM result to reduce sample imbalance. Extensive unsupervised domain adaption experiments on widely used datasets illustrate our proposed approach's robust object detection in domain bias settings.
Visual grounding localizes regions (boxes or segments) in the image corresponding to given referring expressions. In this work we address image segmentation from referring expressions, a problem that has so far only been addressed in a fully-supervised setting. A fully-supervised setup, however, requires pixel-wise supervision and is hard to scale given the expense of manual annotation. We therefore introduce a new task of weakly-supervised image segmentation from referring expressions and propose Text grounded semantic SEGgmentation (TSEG) that learns segmentation masks directly from image-level referring expressions without pixel-level annotations. Our transformer-based method computes patch-text similarities and guides the classification objective during training with a new multi-label patch assignment mechanism. The resulting visual grounding model segments image regions corresponding to given natural language expressions. Our approach TSEG demonstrates promising results for weakly-supervised referring expression segmentation on the challenging PhraseCut and RefCOCO datasets. TSEG also shows competitive performance when evaluated in a zero-shot setting for semantic segmentation on Pascal VOC.
Navigating off-road with a fast autonomous vehicle depends on a robust perception system that differentiates traversable from non-traversable terrain. Typically, this depends on a semantic understanding which is based on supervised learning from images annotated by a human expert. This requires a significant investment in human time, assumes correct expert classification, and small details can lead to misclassification. To address these challenges, we propose a method for predicting high- and low-risk terrains from only past vehicle experience in a self-supervised fashion. First, we develop a tool that projects the vehicle trajectory into the front camera image. Second, occlusions in the 3D representation of the terrain are filtered out. Third, an autoencoder trained on masked vehicle trajectory regions identifies low- and high-risk terrains based on the reconstruction error. We evaluated our approach with two models and different bottleneck sizes with two different training and testing sites with a fourwheeled off-road vehicle. Comparison with two independent test sets of semantic labels from similar terrain as training sites demonstrates the ability to separate the ground as low-risk and the vegetation as high-risk with 81.1% and 85.1% accuracy.