Medical vision-and-language pre-training (Med-VLP) has received considerable attention owing to its applicability to extracting generic vision-and-language representations from medical images and texts. Most existing methods mainly contain three elements: uni-modal encoders (i.e., a vision encoder and a language encoder), a multi-modal fusion module, and pretext tasks, with few studies considering the importance of medical domain expert knowledge and explicitly exploiting such knowledge to facilitate Med-VLP. Although there exist knowledge-enhanced vision-and-language pre-training (VLP) methods in the general domain, most require off-the-shelf toolkits (e.g., object detectors and scene graph parsers), which are unavailable in the medical domain. In this paper, we propose a systematic and effective approach to enhance Med-VLP by structured medical knowledge from three perspectives. First, considering knowledge can be regarded as the intermediate medium between vision and language, we align the representations of the vision encoder and the language encoder through knowledge. Second, we inject knowledge into the multi-modal fusion model to enable the model to perform reasoning using knowledge as the supplementation of the input image and text. Third, we guide the model to put emphasis on the most critical information in images and texts by designing knowledge-induced pretext tasks. To perform a comprehensive evaluation and facilitate further research, we construct a medical vision-and-language benchmark including three tasks. Experimental results illustrate the effectiveness of our approach, where state-of-the-art performance is achieved on all downstream tasks. Further analyses explore the effects of different components of our approach and various settings of pre-training.
Medical vision-and-language pre-training provides a feasible solution to extract effective vision-and-language representations from medical images and texts. However, few studies have been dedicated to this field to facilitate medical vision-and-language understanding. In this paper, we propose a self-supervised learning paradigm with multi-modal masked autoencoders (M$^3$AE), which learn cross-modal domain knowledge by reconstructing missing pixels and tokens from randomly masked images and texts. There are three key designs to make this simple approach work. First, considering the different information densities of vision and language, we adopt different masking ratios for the input image and text, where a considerably larger masking ratio is used for images. Second, we use visual and textual features from different layers to perform the reconstruction to deal with different levels of abstraction in visual and language. Third, we develop different designs for vision and language decoders (i.e., a Transformer for vision and a multi-layer perceptron for language). To perform a comprehensive evaluation and facilitate further research, we construct a medical vision-and-language benchmark including three tasks. Experimental results demonstrate the effectiveness of our approach, where state-of-the-art results are achieved on all downstream tasks. Besides, we conduct further analysis to better verify the effectiveness of different components of our approach and various settings of pre-training. The source code is available at~\url{https://github.com/zhjohnchan/M3AE}.
Existing visual question answering methods tend to capture the spurious correlations from visual and linguistic modalities, and fail to discover the true casual mechanism that facilitates reasoning truthfully based on the dominant visual evidence and the correct question intention. Additionally, the existing methods usually ignore the complex event-level understanding in multi-modal settings that requires a strong cognitive capability of causal inference to jointly model cross-modal event temporality, causality, and dynamics. In this work, we focus on event-level visual question answering from a new perspective, i.e., cross-modal causal relational reasoning, by introducing causal intervention methods to mitigate the spurious correlations and discover the true causal structures for the integration of visual and linguistic modalities. Specifically, we propose a novel event-level visual question answering framework named Cross-Modal Causal RelatIonal Reasoning (CMCIR), to achieve robust casuality-aware visual-linguistic question answering. To uncover the causal structures for visual and linguistic modalities, the novel Causality-aware Visual-Linguistic Reasoning (CVLR) module is proposed to collaboratively disentangle the visual and linguistic spurious correlations via elaborately designed front-door and back-door causal intervention modules. To discover the fine-grained interactions between linguistic semantics and spatial-temporal representations, we build a novel Spatial-Temporal Transformer (STT) that builds the multi-modal co-occurrence interactions between visual and linguistic content. Extensive experiments on large-scale event-level urban dataset SUTD-TrafficQA and three benchmark real-world datasets TGIF-QA, MSVD-QA, and MSRVTT-QA demonstrate the effectiveness of our CMCIR for discovering visual-linguistic causal structures.
Learning with noisy labels (LNL) aims at designing strategies to improve model performance and generalization by mitigating the effects of model overfitting to noisy labels. The key success of LNL lies in identifying as many clean samples as possible from massive noisy data, while rectifying the wrongly assigned noisy labels. Recent advances employ the predicted label distributions of individual samples to perform noise verification and noisy label correction, easily giving rise to confirmation bias. To mitigate this issue, we propose Neighborhood Collective Estimation, in which the predictive reliability of a candidate sample is re-estimated by contrasting it against its feature-space nearest neighbors. Specifically, our method is divided into two steps: 1) Neighborhood Collective Noise Verification to separate all training samples into a clean or noisy subset, 2) Neighborhood Collective Label Correction to relabel noisy samples, and then auxiliary techniques are used to assist further model optimization. Extensive experiments on four commonly used benchmark datasets, i.e., CIFAR-10, CIFAR-100, Clothing-1M and Webvision-1.0, demonstrate that our proposed method considerably outperforms state-of-the-art methods.
Recently deep neural networks (DNNs) have achieved significant success in real-world image super-resolution (SR). However, adversarial image samples with quasi-imperceptible noises could threaten deep learning SR models. In this paper, we propose a robust deep learning framework for real-world SR that randomly erases potential adversarial noises in the frequency domain of input images or features. The rationale is that on the SR task clean images or features have a different pattern from the attacked ones in the frequency domain. Observing that existing adversarial attacks usually add high-frequency noises to input images, we introduce a novel random frequency mask module that blocks out high-frequency components possibly containing the harmful perturbations in a stochastic manner. Since the frequency masking may not only destroys the adversarial perturbations but also affects the sharp details in a clean image, we further develop an adversarial sample classifier based on the frequency domain of images to determine if applying the proposed mask module. Based on the above ideas, we devise a novel real-world image SR framework that combines the proposed frequency mask modules and the proposed adversarial classifier with an existing super-resolution backbone network. Experiments show that our proposed method is more insensitive to adversarial attacks and presents more stable SR results than existing models and defenses.
Deep models trained with noisy labels are prone to over-fitting and struggle in generalization. Most existing solutions are based on an ideal assumption that the label noise is class-conditional, i.e., instances of the same class share the same noise model, and are independent of features. While in practice, the real-world noise patterns are usually more fine-grained as instance-dependent ones, which poses a big challenge, especially in the presence of inter-class imbalance. In this paper, we propose a two-stage clean samples identification method to address the aforementioned challenge. First, we employ a class-level feature clustering procedure for the early identification of clean samples that are near the class-wise prediction centers. Notably, we address the class imbalance problem by aggregating rare classes according to their prediction entropy. Second, for the remaining clean samples that are close to the ground truth class boundary (usually mixed with the samples with instance-dependent noises), we propose a novel consistency-based classification method that identifies them using the consistency of two classifier heads: the higher the consistency, the larger the probability that a sample is clean. Extensive experiments on several challenging benchmarks demonstrate the superior performance of our method against the state-of-the-art.
Thyroid nodule classification aims at determining whether the nodule is benign or malignant based on a given ultrasound image. However, the label obtained by the cytological biopsy which is the golden standard in clinical medicine is not always consistent with the ultrasound imaging TI-RADS criteria. The information difference between the two causes the existing deep learning-based classification methods to be indecisive. To solve the Inconsistent Label problem, we propose an Adaptive Curriculum Learning (ACL) framework, which adaptively discovers and discards the samples with inconsistent labels. Specifically, ACL takes both hard sample and model certainty into account, and could accurately determine the threshold to distinguish the samples with Inconsistent Label. Moreover, we contribute TNCD: a Thyroid Nodule Classification Dataset to facilitate future related research on the thyroid nodules. Extensive experimental results on TNCD based on three different backbone networks not only demonstrate the superiority of our method but also prove that the less-is-more principle which strategically discards the samples with Inconsistent Label could yield performance gains. Source code and data are available at https://github.com/chenghui-666/ACL/.
CT-based bronchial tree analysis plays an important role in the computer-aided diagnosis for respiratory diseases, as it could provide structured information for clinicians. The basis of airway analysis is bronchial tree reconstruction, which consists of bronchus segmentation and classification. However, there remains a challenge for accurate bronchial analysis due to the individual variations and the severe class imbalance. In this paper, we propose a region and structure prior embedded framework named BronchusNet to achieve accurate segmentation and classification of bronchial regions in CT images. For bronchus segmentation, we propose an adaptive hard region-aware UNet that incorporates multi-level prior guidance of hard pixel-wise samples in the general Unet segmentation network to achieve better hierarchical feature learning. For the classification of bronchial branches, we propose a hybrid point-voxel graph learning module to fully exploit bronchial structure priors and to support simultaneous feature interactions across different branches. To facilitate the study of bronchial analysis, we contribute~\textbf{BRSC}: an open-access benchmark of \textbf{BR}onchus imaging analysis with high-quality pixel-wise \textbf{S}egmentation masks and the \textbf{C}lass of bronchial segments. Experimental results on BRSC show that our proposed method not only achieves the state-of-the-art performance for binary segmentation of bronchial region but also exceeds the best existing method on bronchial branches classification by 6.9\%.