Related papers: ProtoPShare: Prototype Sharing for Interpretable I…
Deep imitation learning requires many expert demonstrations, which can be hard to obtain, especially when many tasks are involved. However, different tasks often share similarities, so learning them jointly can greatly benefit them and…
Attribute based knowledge transfer has proven very successful in visual object analysis and learning previously unseen classes. However, the common approach learns and transfers attributes without taking into consideration the embedded…
In this work, we propose the novel Prototypical Graph Regression Self-explainable Trees (ProGReST) model, which combines prototype learning, soft decision trees, and Graph Neural Networks. In contrast to other works, our model can be used…
Model-based clustering is a powerful tool that is often used to discover hidden structure in data by grouping observational units that exhibit similar response values. Recently, clustering methods have been developed that permit…
Unsupervised instance segmentation aims to segment distinct object instances in an image without relying on human-labeled data. This field has recently seen significant advancements, partly due to the strong local correspondences afforded…
In daily life, graphic symbols, such as traffic signs and brand logos, are ubiquitously utilized around us due to its intuitive expression beyond language boundary. We tackle an open-set graphic symbol recognition problem by one-shot…
Deep learning methods have shown great success in several domains as they process a large amount of data efficiently, capable of solving complex classification, forecast, segmentation, and other tasks. However, they come with the inherent…
From the beginning of zero-shot learning research, visual attributes have been shown to play an important role. In order to better transfer attribute-based knowledge from known to unknown classes, we argue that an image representation with…
Self-supervised learning methods learn high-quality visual representations, yet recent studies show that these representations often capture demographic biases present in the training data. Existing fairness-aware methods address this by…
Semantic segmentation algorithms that can robustly segment objects across multiple camera viewpoints are crucial for assuring navigation and safety in emerging applications such as autonomous driving. Existing algorithms treat each image in…
The lack of explainability of deep learning models limits the adoption of such models in clinical practice. Prototype-based models can provide inherent explainable predictions, but these have predominantly been designed for classification…
We present an unsupervised learning framework for decomposing images into layers of automatically discovered object models. Contrary to recent approaches that model image layers with autoencoder networks, we represent them as explicit…
Explaining predictions of black-box neural networks is crucial when applied to decision-critical tasks. Thus, attribution maps are commonly used to identify important image regions, despite prior work showing that humans prefer explanations…
We develop techniques for refining representations for fine-grained classification and segmentation tasks in a self-supervised manner. We find that fine-tuning methods based on instance-discriminative contrastive learning are not as…
Optimized sensing is important for computational imaging in low-resource environments, when images must be recovered from severely limited measurements. In this paper, we propose a physics-constrained, fully differentiable, autoencoder that…
We propose a novel perspective to understand deep neural networks in an interpretable disentanglement form. For each semantic class, we extract a class-specific functional subnetwork from the original full model, with compressed structure…
Data scarcity remains a fundamental challenge in robot learning. While human demonstrations benefit from abundant motion capture data and vast internet resources, robotic manipulation suffers from limited training examples. To bridge this…
A common method to study deep learning systems is to use simplified model representations--for example, using singular value decomposition to visualize the model's hidden states in a lower dimensional space. This approach assumes that the…
In several applications, input samples are more naturally represented in terms of similarities between each other, rather than in terms of feature vectors. In these settings, machine-learning algorithms can become very computationally…
Explaining artificial intelligence (AI) predictions is increasingly important and even imperative in many high-stakes applications where humans are the ultimate decision-makers. In this work, we propose two novel architectures of…