Related papers: Conterfactual Generative Zero-Shot Semantic Segmen…
Zero-shot learning provides models for targets for which instances are not available, commonly called unobserved targets. The availability of target side information becomes crucial in this context in order to properly induce models for…
Zero-shot learning methods rely on fixed visual and semantic embeddings, extracted from independent vision and language models, both pre-trained for other large-scale tasks. This is a weakness of current zero-shot learning frameworks as…
Few-shot semantic segmentation aims to segment novel-class objects in a query image with only a few annotated examples in support images. Most of advanced solutions exploit a metric learning framework that performs segmentation through…
Motivated by the burgeoning interest in cross-domain learning, we present a novel generative modeling challenge: generating counterfactual samples in a target domain based on factual observations from a source domain. Our approach operates…
We propose a method for semi-supervised semantic segmentation using an adversarial network. While most existing discriminators are trained to classify input images as real or fake on the image level, we design a discriminator in a fully…
Counterfactuals can explain classification decisions of neural networks in a human interpretable way. We propose a simple but effective method to generate such counterfactuals. More specifically, we perform a suitable diffeomorphic…
Zero-shot graph embedding is a major challenge for supervised graph learning. Although a recent method RECT has shown promising performance, its working mechanisms are not clear and still needs lots of training data. In this paper, we give…
Counterfactuals are a popular framework for interpreting machine learning predictions. These what if explanations are notoriously challenging to create for computer vision models: standard gradient-based methods are prone to produce…
Low-shot learning methods for image classification support learning from sparse data. We extend these techniques to support dense semantic image segmentation. Specifically, we train a network that, given a small set of annotated images,…
Zero-shot learning uses semantic attributes to connect the search space of unseen objects. In recent years, although the deep convolutional network brings powerful visual modeling capabilities to the ZSL task, its visual features have…
Counterfactual reasoning -- the practice of asking ``what if'' by varying inputs and observing changes in model behavior -- has become central to interpretable and fair AI. This thesis develops frameworks that use counterfactuals to…
We present a generative framework for generalized zero-shot learning where the training and test classes are not necessarily disjoint. Built upon a variational autoencoder based architecture, consisting of a probabilistic encoder and a…
Zero-Shot Classification (ZSC) equips the learned model with the ability to recognize the visual instances from the novel classes via constructing the interactions between the visual and the semantic modalities. In contrast to the…
Semantic image segmentation is a principal problem in computer vision, where the aim is to correctly classify each individual pixel of an image into a semantic label. Its widespread use in many areas, including medical imaging and…
Zero-shot learning has been actively studied for image classification task to relieve the burden of annotating image labels. Interestingly, semantic segmentation task requires more labor-intensive pixel-wise annotation, but zero-shot…
Zero-Shot Learning (ZSL) targets at recognizing unseen categories by leveraging auxiliary information, such as attribute embedding. Despite the encouraging results achieved, prior ZSL approaches focus on improving the discriminant power of…
Counterfactual instances are a powerful tool to obtain valuable insights into automated decision processes, describing the necessary minimal changes in the input space to alter the prediction towards a desired target. Most previous…
Zero shot learning in Image Classification refers to the setting where images from some novel classes are absent in the training data but other information such as natural language descriptions or attribute vectors of the classes are…
Counterfactual explanations for machine learning models are used to find minimal interventions to the feature values such that the model changes the prediction to a different output or a target output. A valid counterfactual explanation…
Despite progress in automated fact-checking, most systems require a significant amount of labeled training data, which is expensive. In this paper, we propose a novel zero-shot method, which instead of operating directly on the claim and…