Related papers: Intrinsic Self-Supervision for Data Quality Audits

While deep learning has been incredibly successful in modeling tasks with large, carefully curated labeled datasets, its application to problems with limited labeled data remains a challenge. The aim of the present work is to improve the…

We present a novel data-efficient semi-supervised framework to improve the generalization of image captioning models. Constructing a large-scale labeled image captioning dataset is an expensive task in terms of labor, time, and cost. In…

Unsupervised person re-identification (Re-ID) aims to retrieve person images across cameras without any identity labels. Most clustering-based methods roughly divide image features into clusters and neglect the feature distribution noise…

Published research highlights the presence of demographic bias in automated facial attribute classification. The proposed bias mitigation techniques are mostly based on supervised learning, which requires a large amount of labeled training…

This paper presents one-bit supervision, a novel setting of learning from incomplete annotations, in the scenario of image classification. Instead of training a model upon the accurate label of each sample, our setting requires the model to…

When a deep learning model is deployed in the wild, it can encounter test data drawn from distributions different from the training data distribution and suffer drop in performance. For safe deployment, it is essential to estimate the…

Self-training is a simple semi-supervised learning approach: Unlabelled examples that attract high-confidence predictions are labelled with their predictions and added to the training set, with this process being repeated multiple times.…

This paper focuses on webly supervised learning (WSL), where datasets are built by crawling samples from the Internet and directly using search queries as web labels. Although WSL benefits from fast and low-cost data collection, noises in…

Semi-supervised learning, i.e. jointly learning from labeled and unlabeled samples, is an active research topic due to its key role on relaxing human supervision. In the context of image classification, recent advances to learn from…

In this work, we for the first time present a method for detecting label errors in image datasets with semantic segmentation, i.e., pixel-wise class labels. Annotation acquisition for semantic segmentation datasets is time-consuming and…

Continual learning aims to learn new tasks incrementally using less computation and memory resources instead of retraining the model from scratch whenever new task arrives. However, existing approaches are designed in supervised fashion…

The task of large-scale retrieval-based image localization is to estimate the geographical location of a query image by recognizing its nearest reference images from a city-scale dataset. However, the general public benchmarks only provide…

Constructing fine-grained image datasets typically requires domain-specific expert knowledge, which is not always available for crowd-sourcing platform annotators. Accordingly, learning directly from web images becomes an alternative method…

Music source separation (MSS) faces challenges due to the limited availability of correctly-labeled individual instrument tracks. With the push to acquire larger datasets to improve MSS performance, the inevitability of encountering…

Image classification benchmark datasets such as CIFAR, MNIST, and ImageNet serve as critical tools for model evaluation. However, despite the cleaning efforts, these datasets still suffer from pervasive noisy labels and often contain…

Feature matching and finding correspondences between endoscopic images is a key step in many clinical applications such as patient follow-up and generation of panoramic image from clinical sequences for fast anomalies localization.…

Pseudo-labeling is a popular semi-supervised learning technique to leverage unlabeled data when labeled samples are scarce. The generation and selection of pseudo-labels heavily rely on labeled data. Existing approaches implicitly assume…

Class imbalance and noisy labels are the norm rather than the exception in many large-scale classification datasets. Nevertheless, most works in machine learning typically assume balanced and clean data. There have been some recent attempts…

Auto-annotation by ensemble of models is an efficient method of learning on unlabeled data. Wrong or inaccurate annotations generated by the ensemble may lead to performance degradation of the trained model. To deal with this problem we…

For many computer vision problems, the deep neural networks are trained and validated based on the assumption that the input images are pristine (i.e., artifact-free). However, digital images are subject to a wide range of distortions in…