Related papers: Learning Debiased and Disentangled Representations…

We propose and study a method for learning interpretable representations for the task of regression. Features are represented as networks of multi-type expression trees comprised of activation functions common in neural networks in addition…

Scene labeling is a challenging classification problem where each input image requires a pixel-level prediction map. Recently, deep-learning-based methods have shown their effectiveness on solving this problem. However, we argue that the…

Neural Disjunctive Normal Form (DNF) based models are powerful and interpretable approaches to neuro-symbolic learning and have shown promising results in classification and reinforcement learning settings without prior knowledge of the…

Representation learning, and interpreting learned representations, are key areas of focus in machine learning and neuroscience. Both fields generally use representations as a means to understand or improve a system's computations. In this…

Extracting structured representations from raw visual data is an important and long-standing challenge in machine learning. Recently, techniques for unsupervised learning of object-centric representations have raised growing interest. In…

The rise of deep neural networks has led to several breakthroughs for semantic segmentation. In spite of this, a model trained on source domain often fails to work properly in new challenging domains, that is directly concerned with the…

Deep learning architectures exhibit a critical drop of performance due to catastrophic forgetting when they are required to incrementally learn new tasks. Contemporary incremental learning frameworks focus on image classification and object…

Adversarial vulnerability remains a major obstacle to constructing reliable NLP systems. When imperceptible perturbations are added to raw input text, the performance of a deep learning model may drop dramatically under attacks. Recent work…

Motion artifacts caused by prolonged acquisition time are a significant challenge in Magnetic Resonance Imaging (MRI), hindering accurate tissue segmentation. These artifacts appear as blurred images that mimic tissue-like appearances,…

Although disentangled representations are often said to be beneficial for downstream tasks, current empirical and theoretical understanding is limited. In this work, we provide evidence that disentangled representations coupled with sparse…

While deep learning models often achieve strong task performance, their successes are hampered by their inability to disentangle spurious correlations from causative factors, such as when they use protected attributes (e.g., race, gender,…

How to handle domain shifts when recognizing or segmenting visual data across domains has been studied by learning and vision communities. In this paper, we address domain generalized semantic segmentation, in which the segmentation model…

We propose a novel weakly-supervised semantic segmentation algorithm based on Deep Convolutional Neural Network (DCNN). Contrary to existing weakly-supervised approaches, our algorithm exploits auxiliary segmentation annotations available…

Semantic segmentation is the task of assigning a label to each pixel in the image.In recent years, deep convolutional neural networks have been driving advances in multiple tasks related to cognition. Although, DCNNs have resulted in…

While representation learning aims to derive interpretable features for describing visual data, representation disentanglement further results in such features so that particular image attributes can be identified and manipulated. However,…

Despite their effectiveness in a wide range of tasks, deep architectures suffer from some important limitations. In particular, they are vulnerable to catastrophic forgetting, i.e. they perform poorly when they are required to update their…

Neural networks have greatly boosted performance in computer vision by learning powerful representations of input data. The drawback of end-to-end training for maximal overall performance are black-box models whose hidden representations…

Existing deep learning approaches for learning visual features tend to overlearn and extract more information than what is required for the task at hand. From a privacy preservation perspective, the input visual information is not protected…

Unsupervised domain adaptation in semantic segmentation has been raised to alleviate the reliance on expensive pixel-wise annotations. It leverages a labeled source domain dataset as well as unlabeled target domain images to learn a…

Representation learning is a widely adopted framework for learning in data-scarce environments, aiming to extract common features from related tasks. While centralized approaches have been extensively studied, decentralized methods remain…