Related papers: Towards Context-Agnostic Learning Using Synthetic …
There is extensive interest in metric learning methods for image retrieval. Many metric learning loss functions focus on learning a correct ranking of training samples, but strongly overfit semantically inconsistent labels and require a…
We present a method for synthesizing naturally looking images of multiple people interacting in a specific scenario. These images benefit from the advantages of synthetic data: being fully controllable and fully annotated with any type of…
The need for large amounts of training and validation data is a huge concern in scaling AI algorithms for autonomous driving. Semantic Image Synthesis (SIS), or label-to-image translation, promises to address this issue by translating…
Recently, contrastive self-supervised learning has become a key component for learning visual representations across many computer vision tasks and benchmarks. However, contrastive learning in the context of domain adaptation remains…
Real-world datasets collected with sensor networks often contain incomplete and uncertain labels as well as artefacts arising from the system environment. Complete and reliable labeling is often infeasible for large-scale and long-term…
Learning methods using synthetic data have attracted attention as an effective approach for increasing the diversity of training data while reducing collection costs, thereby improving the robustness of model discrimination. However, many…
Learning on synthetic data and transferring the resulting properties to their real counterparts is an important challenge for reducing costs and increasing safety in machine learning. In this work, we focus on autoencoder architectures and…
Mitigating bias in machine learning models is a critical endeavor for ensuring fairness and equity. In this paper, we propose a novel approach to address bias by leveraging pixel image attributions to identify and regularize regions of…
The natural world is long-tailed: rare classes are observed orders of magnitudes less frequently than common ones, leading to highly-imbalanced data where rare classes can have only handfuls of examples. Learning from few examples is a…
Domain adaptation is of huge interest as labeling is an expensive and error-prone task, especially when labels are needed on pixel-level like in semantic segmentation. Therefore, one would like to be able to train neural networks on…
Semantic segmentation is still a challenging task for parsing diverse contexts in different scenes, thus the fixed classifier might not be able to well address varying feature distributions during testing. Different from the mainstream…
Visual Domain Adaptation is a problem of immense importance in computer vision. Previous approaches showcase the inability of even deep neural networks to learn informative representations across domain shift. This problem is more severe…
We describe a new approach that improves the training of generative adversarial nets (GANs) for synthesizing diverse images from a text input. Our approach is based on the conditional version of GANs and expands on previous work leveraging…
Authentication is the task of confirming the matching relationship between a data instance and a given identity. Typical examples of authentication problems include face recognition and person re-identification. Data-driven authentication…
Coupling the high-fidelity generation capabilities of label-conditional image synthesis methods with the flexibility of unconditional generative models, we propose a semantic bottleneck GAN model for unconditional synthesis of complex…
We study agnostic active learning, where the goal is to learn a classifier in a pre-specified hypothesis class interactively with as few label queries as possible, while making no assumptions on the true function generating the labels. The…
Dataset bias is a well-known problem in the field of computer vision. The presence of implicit bias in any image collection hinders a model trained and validated on a particular dataset to yield similar accuracies when tested on other…
To address semi-supervised learning from both labeled and unlabeled data, we present a novel meta-learning scheme. We particularly consider that labeled and unlabeled data share disjoint ground truth label sets, which can be seen tasks like…
In few-shot learning, a machine learning system learns from a small set of labelled examples relating to a specific task, such that it can generalize to new examples of the same task. Given the limited availability of labelled examples in…
Deep learning-based scene text detection can achieve preferable performance, powered with sufficient labeled training data. However, manual labeling is time consuming and laborious. At the extreme, the corresponding annotated data are…