Image-to-image translation plays a vital role in tackling various medical imaging tasks such as attenuation correction, motion correction, undersampled reconstruction, and denoising. Generative adversarial networks have been shown to achieve the state-of-the-art in generating high fidelity images for these tasks. However, the state-of-the-art GAN-based frameworks do not estimate the uncertainty in the predictions made by the network that is essential for making informed medical decisions and subsequent revision by medical experts and has recently been shown to improve the performance and interpretability of the model. In this work, we propose an uncertainty-guided progressive learning scheme for image-to-image translation. By incorporating aleatoric uncertainty as attention maps for GANs trained in a progressive manner, we generate images of increasing fidelity progressively. We demonstrate the efficacy of our model on three challenging medical image translation tasks, including PET to CT translation, undersampled MRI reconstruction, and MRI motion artefact correction. Our model generalizes well in three different tasks and improves performance over state of the art under full-supervision and weak-supervision with limited data. Code is released here: https://github.com/ExplainableML/UncerGuidedI2I
The class activation mapping, or CAM, has been the cornerstone of feature attribution methods for multiple vision tasks. Its simplicity and effectiveness have led to wide applications in the explanation of visual predictions and weakly-supervised localization tasks. However, CAM has its own shortcomings. The computation of attribution maps relies on ad-hoc calibration steps that are not part of the training computational graph, making it difficult for us to understand the real meaning of the attribution values. In this paper, we improve CAM by explicitly incorporating a latent variable encoding the location of the cue for recognition in the formulation, thereby subsuming the attribution map into the training computational graph. The resulting model, class activation latent mapping, or CALM, is trained with the expectation-maximization algorithm. Our experiments show that CALM identifies discriminative attributes for image classifiers more accurately than CAM and other visual attribution baselines. CALM also shows performance improvements over prior arts on the weakly-supervised object localization benchmarks. Our code is available at https://github.com/naver-ai/calm.
Recently, an increasing number of works have introduced models capable of generating natural language explanations (NLEs) for their predictions on vision-language (VL) tasks. Such models are appealing because they can provide human-friendly and comprehensive explanations. However, there is still a lack of unified evaluation approaches for the explanations generated by these models. Moreover, there are currently only few datasets of NLEs for VL tasks. In this work, we introduce e-ViL, a benchmark for explainable vision-language tasks that establishes a unified evaluation framework and provides the first comprehensive comparison of existing approaches that generate NLEs for VL tasks. e-ViL spans four models and three datasets. Both automatic metrics and human evaluation are used to assess model-generated explanations. We also introduce e-SNLI-VE, the largest existing VL dataset with NLEs (over 430k instances). Finally, we propose a new model that combines UNITER, which learns joint embeddings of images and text, and GPT-2, a pre-trained language model that is well-suited for text generation. It surpasses the previous state-of-the-art by a large margin across all datasets.
We consider the task of retrieving audio using free-form natural language queries. To study this problem, which has received limited attention in the existing literature, we introduce challenging new benchmarks for text-based audio retrieval using text annotations sourced from the Audiocaps and Clotho datasets. We then employ these benchmarks to establish baselines for cross-modal audio retrieval, where we demonstrate the benefits of pre-training on diverse audio tasks. We hope that our benchmarks will inspire further research into cross-modal text-based audio retrieval with free-form text queries.
Explaining the decision of a multi-modal decision-maker requires to determine the evidence from both modalities. Recent advances in XAI provide explanations for models trained on still images. However, when it comes to modeling multiple sensory modalities in a dynamic world, it remains underexplored how to demystify the mysterious dynamics of a complex multi-modal model. In this work, we take a crucial step forward and explore learnable explanations for audio-visual recognition. Specifically, we propose a novel space-time attention network that uncovers the synergistic dynamics of audio and visual data over both space and time. Our model is capable of predicting the audio-visual video events, while justifying its decision by localizing where the relevant visual cues appear, and when the predicted sounds occur in videos. We benchmark our model on three audio-visual video event datasets, comparing extensively to multiple recent multi-modal representation learners and intrinsic explanation models. Experimental results demonstrate the clear superior performance of our model over the existing methods on audio-visual video event recognition. Moreover, we conduct an in-depth study to analyze the explainability of our model based on robustness analysis via perturbation tests and pointing games using human annotations.
Compositional Zero-Shot learning (CZSL) aims to recognize unseen compositions of state and object visual primitives seen during training. A problem with standard CZSL is the assumption of knowing which unseen compositions will be available at test time. In this work, we overcome this assumption operating on the open world setting, where no limit is imposed on the compositional space at test time, and the search space contains a large number of unseen compositions. To address this problem, we propose a new approach, Compositional Cosine Graph Embeddings (Co-CGE), based on two principles. First, Co-CGE models the dependency between states, objects and their compositions through a graph convolutional neural network. The graph propagates information from seen to unseen concepts, improving their representations. Second, since not all unseen compositions are equally feasible, and less feasible ones may damage the learned representations, Co-CGE estimates a feasibility score for each unseen composition, using the scores as margins in a cosine similarity-based loss and as weights in the adjacency matrix of the graphs. Experiments show that our approach achieves state-of-the-art performances in standard CZSL while outperforming previous methods in the open world scenario.
Having access to multi-modal cues (e.g. vision and audio) empowers some cognitive tasks to be done faster compared to learning from a single modality. In this work, we propose to transfer knowledge across heterogeneous modalities, even though these data modalities may not be semantically correlated. Rather than directly aligning the representations of different modalities, we compose audio, image, and video representations across modalities to uncover richer multi-modal knowledge. Our main idea is to learn a compositional embedding that closes the cross-modal semantic gap and captures the task-relevant semantics, which facilitates pulling together representations across modalities by compositional contrastive learning. We establish a new, comprehensive multi-modal distillation benchmark on three video datasets: UCF101, ActivityNet, and VGGSound. Moreover, we demonstrate that our model significantly outperforms a variety of existing knowledge distillation methods in transferring audio-visual knowledge to improve video representation learning. Code is released here: https://github.com/yanbeic/CCL.
Being able to segment unseen classes not observed during training is an important technical challenge in deep learning, because of its potential to reduce the expensive annotation required for semantic segmentation. Prior zero-label semantic segmentation works approach this task by learning visual-semantic embeddings or generative models. However, they are prone to overfitting on the seen classes because there is no training signal for them. In this paper, we study the challenging generalized zero-label semantic segmentation task where the model has to segment both seen and unseen classes at test time. We assume that pixels of unseen classes could be present in the training images but without being annotated. Our idea is to capture the latent information on unseen classes by supervising the model with self-produced pseudo-labels for unlabeled pixels. We propose a consistency regularizer to filter out noisy pseudo-labels by taking the intersections of the pseudo-labels generated from different augmentations of the same image. Our framework generates pseudo-labels and then retrain the model with human-annotated and pseudo-labelled data. This procedure is repeated for several iterations. As a result, our approach achieves the new state-of-the-art on PascalVOC12 and COCO-stuff datasets in the challenging generalized zero-label semantic segmentation setting, surpassing other existing methods addressing this task with more complex strategies.
Unpaired image-to-image translation refers to learning inter-image-domain mapping in an unsupervised manner. Existing methods often learn deterministic mappings without explicitly modelling the robustness to outliers or predictive uncertainty, leading to performance degradation when encountering unseen out-of-distribution (OOD) patterns at test time. To address this limitation, we propose a novel probabilistic method called Uncertainty-aware Generalized Adaptive Cycle Consistency (UGAC), which models the per-pixel residual by generalized Gaussian distribution, capable of modelling heavy-tailed distributions. We compare our model with a wide variety of state-of-the-art methods on two challenging tasks: unpaired image denoising in the natural image and unpaired modality prorogation in medical image domains. Experimental results demonstrate that our model offers superior image generation quality compared to recent methods in terms of quantitative metrics such as signal-to-noise ratio and structural similarity. Our model also exhibits stronger robustness towards OOD test data.
In compositional zero-shot learning, the goal is to recognize unseen compositions (e.g. old dog) of observed visual primitives states (e.g. old, cute) and objects (e.g. car, dog) in the training set. This is challenging because the same state can for example alter the visual appearance of a dog drastically differently from a car. As a solution, we propose a novel graph formulation called Compositional Graph Embedding (CGE) that learns image features, compositional classifiers, and latent representations of visual primitives in an end-to-end manner. The key to our approach is exploiting the dependency between states, objects, and their compositions within a graph structure to enforce the relevant knowledge transfer from seen to unseen compositions. By learning a joint compatibility that encodes semantics between concepts, our model allows for generalization to unseen compositions without relying on an external knowledge base like WordNet. We show that in the challenging generalized compositional zero-shot setting our CGE significantly outperforms the state of the art on MIT-States and UT-Zappos. We also propose a new benchmark for this task based on the recent GQA dataset.