With the development of natural language processing techniques(NLP), automatic diagnosis of eye diseases using ophthalmology electronic medical records (OEMR) has become possible. It aims to evaluate the condition of both eyes of a patient respectively, and we formulate it as a particular multi-label classification task in this paper. Although there are a few related studies in other diseases, automatic diagnosis of eye diseases exhibits unique characteristics. First, descriptions of both eyes are mixed up in OEMR documents, with both free text and templated asymptomatic descriptions, resulting in sparsity and clutter of information. Second, OEMR documents contain multiple parts of descriptions and have long document lengths. Third, it is critical to provide explainability to the disease diagnosis model. To overcome those challenges, we present an effective automatic eye disease diagnosis framework, NEEDED. In this framework, a preprocessing module is integrated to improve the density and quality of information. Then, we design a hierarchical transformer structure for learning the contextualized representations of each sentence in the OEMR document. For the diagnosis part, we propose an attention-based predictor that enables traceable diagnosis by obtaining disease-specific information. Experiments on the real dataset and comparison with several baseline models show the advantage and explainability of our framework.

To build Video Question Answering (VideoQA) systems capable of assisting humans in daily activities, seeking answers from long-form videos with diverse and complex events is a must. Existing multi-modal VQA models achieve promising performance on images or short video clips, especially with the recent success of large-scale multi-modal pre-training. However, when extending these methods to long-form videos, new challenges arise. On the one hand, using a dense video sampling strategy is computationally prohibitive. On the other hand, methods relying on sparse sampling struggle in scenarios where multi-event and multi-granularity visual reasoning are required. In this work, we introduce a new model named Multi-modal Iterative Spatial-temporal Transformer (MIST) to better adapt pre-trained models for long-form VideoQA. Specifically, MIST decomposes traditional dense spatial-temporal self-attention into cascaded segment and region selection modules that adaptively select frames and image regions that are closely relevant to the question itself. Visual concepts at different granularities are then processed efficiently through an attention module. In addition, MIST iteratively conducts selection and attention over multiple layers to support reasoning over multiple events. The experimental results on four VideoQA datasets, including AGQA, NExT-QA, STAR, and Env-QA, show that MIST achieves state-of-the-art performance and is superior at computation efficiency and interpretability.

The number of international benchmarking competitions is steadily increasing in various fields of machine learning (ML) research and practice. So far, however, little is known about the common practice as well as bottlenecks faced by the community in tackling the research questions posed. To shed light on the status quo of algorithm development in the specific field of biomedical imaging analysis, we designed an international survey that was issued to all participants of challenges conducted in conjunction with the IEEE ISBI 2021 and MICCAI 2021 conferences (80 competitions in total). The survey covered participants' expertise and working environments, their chosen strategies, as well as algorithm characteristics. A median of 72% challenge participants took part in the survey. According to our results, knowledge exchange was the primary incentive (70%) for participation, while the reception of prize money played only a minor role (16%). While a median of 80 working hours was spent on method development, a large portion of participants stated that they did not have enough time for method development (32%). 25% perceived the infrastructure to be a bottleneck. Overall, 94% of all solutions were deep learning-based. Of these, 84% were based on standard architectures. 43% of the respondents reported that the data samples (e.g., images) were too large to be processed at once. This was most commonly addressed by patch-based training (69%), downsampling (37%), and solving 3D analysis tasks as a series of 2D tasks. K-fold cross-validation on the training set was performed by only 37% of the participants and only 50% of the participants performed ensembling based on multiple identical models (61%) or heterogeneous models (39%). 48% of the respondents applied postprocessing steps.

Human modeling and relighting are two fundamental problems in computer vision and graphics, where high-quality datasets can largely facilitate related research. However, most existing human datasets only provide multi-view human images captured under the same illumination. Although valuable for modeling tasks, they are not readily used in relighting problems. To promote research in both fields, in this paper, we present UltraStage, a new 3D human dataset that contains more than 2K high-quality human assets captured under both multi-view and multi-illumination settings. Specifically, for each example, we provide 32 surrounding views illuminated with one white light and two gradient illuminations. In addition to regular multi-view images, gradient illuminations help recover detailed surface normal and spatially-varying material maps, enabling various relighting applications. Inspired by recent advances in neural representation, we further interpret each example into a neural human asset which allows novel view synthesis under arbitrary lighting conditions. We show our neural human assets can achieve extremely high capture performance and are capable of representing fine details such as facial wrinkles and cloth folds. We also validate UltraStage in single image relighting tasks, training neural networks with virtual relighted data from neural assets and demonstrating realistic rendering improvements over prior arts. UltraStage will be publicly available to the community to stimulate significant future developments in various human modeling and rendering tasks.

The geographically weighted regression (GWR) is an essential tool for estimating the spatial variation of relationships between dependent and independent variables in geographical contexts. However, GWR suffers from the problem that classical linear regressions, which compose the GWR model, are more prone to be underfitting, especially for significant volume and complex nonlinear data, causing inferior comparative performance. Nevertheless, some advanced models, such as the decision tree and the support vector machine, can learn features from complex data more effectively while they cannot provide explainable quantification for the spatial variation of localized relationships. To address the above issues, we propose a geographically gradient boosting weighted regression model, GWRBoost, that applies the localized additive model and gradient boosting optimization method to alleviate underfitting problems and retains explainable quantification capability for spatially-varying relationships between geographically located variables. Furthermore, we formulate the computation method of the Akaike information score for the proposed model to conduct the comparative analysis with the classic GWR algorithm. Simulation experiments and the empirical case study are applied to prove the efficient performance and practical value of GWRBoost. The results show that our proposed model can reduce the RMSE by 18.3\% in parameter estimation accuracy and AICc by 67.3\% in the goodness of fit.

Cross-view geo-localization aims to estimate the location of a query ground image by matching it to a reference geo-tagged aerial images database. As an extremely challenging task, its difficulties root in the drastic view changes and different capturing time between two views. Despite these difficulties, recent works achieve outstanding progress on cross-view geo-localization benchmarks. However, existing methods still suffer from poor performance on the cross-area benchmarks, in which the training and testing data are captured from two different regions. We attribute this deficiency to the lack of ability to extract the spatial configuration of visual feature layouts and models' overfitting on low-level details from the training set. In this paper, we propose GeoDTR which explicitly disentangles geometric information from raw features and learns the spatial correlations among visual features from aerial and ground pairs with a novel geometric layout extractor module. This module generates a set of geometric layout descriptors, modulating the raw features and producing high-quality latent representations. In addition, we elaborate on two categories of data augmentations, (i) Layout simulation, which varies the spatial configuration while keeping the low-level details intact. (ii) Semantic augmentation, which alters the low-level details and encourages the model to capture spatial configurations. These augmentations help to improve the performance of the cross-view geo-localization models, especially on the cross-area benchmarks. Moreover, we propose a counterfactual-based learning process to benefit the geometric layout extractor in exploring spatial information. Extensive experiments show that GeoDTR not only achieves state-of-the-art results but also significantly boosts the performance on same-area and cross-area benchmarks.

The security of artificial intelligence (AI) is an important research area towards safe, reliable, and trustworthy AI systems. To accelerate the research on AI security, the Artificial Intelligence Security Competition (AISC) was organized by the Zhongguancun Laboratory, China Industrial Control Systems Cyber Emergency Response Team, Institute for Artificial Intelligence, Tsinghua University, and RealAI as part of the Zhongguancun International Frontier Technology Innovation Competition (https://www.zgc-aisc.com/en). The competition consists of three tracks, including Deepfake Security Competition, Autonomous Driving Security Competition, and Face Recognition Security Competition. This report will introduce the competition rules of these three tracks and the solutions of top-ranking teams in each track.

Cross-modality magnetic resonance (MR) image synthesis aims to produce missing modalities from existing ones. Currently, several methods based on deep neural networks have been developed using both source- and target-modalities in a supervised learning manner. However, it remains challenging to obtain a large amount of completely paired multi-modal training data, which inhibits the effectiveness of existing methods. In this paper, we propose a novel Self-supervised Learning-based Multi-scale Transformer Network (SLMT-Net) for cross-modality MR image synthesis, consisting of two stages, \ie, a pre-training stage and a fine-tuning stage. During the pre-training stage, we propose an Edge-preserving Masked AutoEncoder (Edge-MAE), which preserves the contextual and edge information by simultaneously conducting the image reconstruction and the edge generation. Besides, a patch-wise loss is proposed to treat the input patches differently regarding their reconstruction difficulty, by measuring the difference between the reconstructed image and the ground-truth. In this case, our Edge-MAE can fully leverage a large amount of unpaired multi-modal data to learn effective feature representations. During the fine-tuning stage, we present a Multi-scale Transformer U-Net (MT-UNet) to synthesize the target-modality images, in which a Dual-scale Selective Fusion (DSF) module is proposed to fully integrate multi-scale features extracted from the encoder of the pre-trained Edge-MAE. Moreover, we use the pre-trained encoder as a feature consistency module to measure the difference between high-level features of the synthesized image and the ground truth one. Experimental results show the effectiveness of the proposed SLMT-Net, and our model can reliably synthesize high-quality images when the training set is partially unpaired. Our code will be publicly available at https://github.com/lyhkevin/SLMT-Net.

Camouflaged object detection (COD) aims to detect/segment camouflaged objects embedded in the environment, which has attracted increasing attention over the past decades. Although several COD methods have been developed, they still suffer from unsatisfactory performance due to the intrinsic similarities between the foreground objects and background surroundings. In this paper, we propose a novel Feature Aggregation and Propagation Network (FAP-Net) for camouflaged object detection. Specifically, we propose a Boundary Guidance Module (BGM) to explicitly model the boundary characteristic, which can provide boundary-enhanced features to boost the COD performance. To capture the scale variations of the camouflaged objects, we propose a Multi-scale Feature Aggregation Module (MFAM) to characterize the multi-scale information from each layer and obtain the aggregated feature representations. Furthermore, we propose a Cross-level Fusion and Propagation Module (CFPM). In the CFPM, the feature fusion part can effectively integrate the features from adjacent layers to exploit the cross-level correlations, and the feature propagation part can transmit valuable context information from the encoder to the decoder network via a gate unit. Finally, we formulate a unified and end-to-end trainable framework where cross-level features can be effectively fused and propagated for capturing rich context information. Extensive experiments on three benchmark camouflaged datasets demonstrate that our FAP-Net outperforms other state-of-the-art COD models. Moreover, our model can be extended to the polyp segmentation task, and the comparison results further validate the effectiveness of the proposed model in segmenting polyps. The source code and results will be released at https://github.com/taozh2017/FAPNet.

Neural Radiance Fields (NeRF) methods have proved effective as compact, high-quality and versatile representations for 3D scenes, and enable downstream tasks such as editing, retrieval, navigation, etc. Various neural architectures are vying for the core structure of NeRF, including the plain Multi-Layer Perceptron (MLP), sparse tensors, low-rank tensors, hashtables and their compositions. Each of these representations has its particular set of trade-offs. For example, the hashtable-based representations admit faster training and rendering but their lack of clear geometric meaning hampers downstream tasks like spatial-relation-aware editing. In this paper, we propose Progressive Volume Distillation (PVD), a systematic distillation method that allows any-to-any conversions between different architectures, including MLP, sparse or low-rank tensors, hashtables and their compositions. PVD consequently empowers downstream applications to optimally adapt the neural representations for the task at hand in a post hoc fashion. The conversions are fast, as distillation is progressively performed on different levels of volume representations, from shallower to deeper. We also employ special treatment of density to deal with its specific numerical instability problem. Empirical evidence is presented to validate our method on the NeRF-Synthetic, LLFF and TanksAndTemples datasets. For example, with PVD, an MLP-based NeRF model can be distilled from a hashtable-based Instant-NGP model at a 10X~20X faster speed than being trained the original NeRF from scratch, while achieving a superior level of synthesis quality. Code is available at https://github.com/megvii-research/AAAI2023-PVD.