Related papers: Efficient Algorithms for Learning from Coarse Labe…
We present a simple yet efficient approach capable of training deep neural networks on large-scale weakly-supervised web images, which are crawled raw from the Internet by using text queries, without any human annotation. We develop a…
The rapid development of deep learning has made a great progress in image segmentation, one of the fundamental tasks of computer vision. However, the current segmentation algorithms mostly rely on the availability of pixel-level…
Supervised learning, especially supervised deep learning, requires large amounts of labeled data. One approach to collect large amounts of labeled data is by using a crowdsourcing platform where numerous workers perform the annotation…
Annotating multi-class instances is a crucial task in the field of machine learning. Unfortunately, identifying the correct class label from a long sequence of candidate labels is time-consuming and laborious. To alleviate this problem, we…
Instance-level image classification tasks have traditionally relied on single-instance labels to train models, e.g., few-shot learning and transfer learning. However, set-level coarse-grained labels that capture relationships among…
Few-shot learning aims at rapidly adapting to novel categories with only a handful of samples at test time, which has been predominantly tackled with the idea of meta-learning. However, meta-learning approaches essentially learn across a…
Counterfactual learning from observational data involves learning a classifier on an entire population based on data that is observed conditioned on a selection policy. This work considers this problem in an active setting, where the…
Deep neural networks (DNNs) trained on large-scale datasets have exhibited significant performance in image classification. Many large-scale datasets are collected from websites, however they tend to contain inaccurate labels that are…
In the problem of learning with label proportions, which we call LLP learning, the training data is unlabeled, and only the proportions of examples receiving each label are given. The goal is to learn a hypothesis that predicts the…
Deep learning approaches often require huge datasets to achieve good generalization. This complicates its use in tasks like image-based medical diagnosis, where the small training datasets are usually insufficient to learn appropriate data…
Graph-based semi-supervised learning has been shown to be one of the most effective approaches for classification tasks from a wide range of domains, such as image classification and text classification, as they can exploit the connectivity…
State-of-the-art results on image recognition tasks are achieved using over-parameterized learning algorithms that (nearly) perfectly fit the training set and are known to fit well even random labels. This tendency to memorize the labels of…
Collecting labeled data for the task of semantic segmentation is expensive and time-consuming, as it requires dense pixel-level annotations. While recent Convolutional Neural Network (CNN) based semantic segmentation approaches have…
Inherent risk scoring is an important function in anti-money laundering, used for determining the riskiness of an individual during onboarding $\textit{before}$ fraudulent transactions occur. It is, however, often fraught with two…
Fine-grained annotations---e.g. dense image labels, image segmentation and text tagging---are useful in many ML applications but they are labor-intensive to generate. Moreover there are often systematic, structured errors in these…
Label noise in real-world datasets encodes wrong correlation patterns and impairs the generalization of deep neural networks (DNNs). It is critical to find efficient ways to detect corrupted patterns. Current methods primarily focus on…
Deep learning has achieved great success in recent years with the aid of advanced neural network structures and large-scale human-annotated datasets. However, it is often costly and difficult to accurately and efficiently annotate…
This manuscript presents a series of my selected contributions to the topic of label-efficient learning in computer vision and remote sensing. The central focus of this research is to develop and adapt methods that can learn effectively…
Fine-grained image recognition is a longstanding computer vision challenge that focuses on differentiating objects belonging to multiple subordinate categories within the same meta-category. Since images belonging to the same meta-category…
There has been much interest in recent years in learning good classifiers from data with noisy labels. Most work on learning from noisy labels has focused on standard loss-based performance measures. However, many machine learning problems…