相关论文: GOGGLES: Automatic Image Labeling with Affinity Co…

Weakly supervised learning with scribble annotations uses sparse user-drawn strokes to indicate segmentation labels on a small subset of pixels. This annotation reduces the cost of dense pixel-wise labeling, but suffers inherently from…

Providing ground truth supervision to train visual models has been a bottleneck over the years, exacerbated by domain shifts which degenerate the performance of such models. This was the case when visual tasks relied on handcrafted features…

Supervised machine learning based state-of-the-art computer vision techniques are in general data hungry and pose the challenges of not having adequate computing resources and of high costs involved in human labeling efforts. Training data…

Semi-supervised semantic segmentation methods leverage unlabeled data by pseudo-labeling them. Thus the success of these methods hinges on the reliablility of the pseudo-labels. Existing methods mostly choose high-confidence pixels in an…

While there are novel point cloud semantic segmentation schemes that continuously surpass state-of-the-art results, the success of learning an effective model usually rely on the availability of abundant labeled data. However, data…

State-of-the-art, high capacity deep neural networks not only require large amounts of labelled training data, they are also highly susceptible to label errors in this data, typically resulting in large efforts and costs and therefore…

Constructing an organized dataset comprised of a large number of images and several captions for each image is a laborious task, which requires vast human effort. On the other hand, collecting a large number of images and sentences…

Data labeling in supervised learning is considered an expensive and infeasible tool in some conditions. The self-supervised learning method is proposed to tackle the learning effectiveness with fewer labeled data, however, there is a lack…

Fine-grained classification remains a very challenging problem, because of the absence of well-labeled training data caused by the high cost of annotating a large number of fine-grained categories. In the extreme case, given a set of test…

Image forgery is a topic that has been studied for many years. Before the breakthrough of deep learning, forged images were detected using handcrafted features that did not require training. These traditional methods failed to perform…

Labelling of data for supervised learning can be costly and time-consuming and the risk of incorporating label noise in large data sets is imminent. When training a flexible discriminative model using a strictly proper loss, such noise will…

Collecting large training datasets, annotated with high-quality labels, is costly and time-consuming. This paper proposes a novel framework for training deep convolutional neural networks from noisy labeled datasets that can be obtained…

Weakly-supervised semantic segmentation (WSSS) with image-level labels is an important and challenging task. Due to the high training efficiency, end-to-end solutions for WSSS have received increasing attention from the community. However,…

Improper or erroneous labelling can pose a hindrance to reliable generalization for supervised learning. This can have negative consequences, especially for critical fields such as healthcare. We propose an effective new approach for…

Recent studies highlight that deep learning models often learn spurious features mistakenly linked to labels, compromising their reliability in real-world scenarios where such correlations do not hold. Despite the increasing research…

We propose a novel setting for learning, where the input domain is the image of a map defined on the product of two sets, one of which completely determines the labels. We derive a new risk bound for this setting that decomposes into a bias…

We propose techniques to incorporate coarse taxonomic labels to train image classifiers in fine-grained domains. Such labels can often be obtained with a smaller effort for fine-grained domains such as the natural world where categories are…

Machine learning for remote sensing imaging relies on up-to-date and accurate labels for model training and testing. Labelling remote sensing imagery is time and cost intensive, requiring expert analysis. Previous labelling tools rely on…

Domain shift poses a significant challenge in Cross-Domain Facial Expression Recognition (CD-FER) due to the distribution variation across different domains. Current works mainly focus on learning domain-invariant features through global…

Recently, fairness-aware learning have become increasingly crucial, but most of those methods operate by assuming the availability of fully annotated demographic group labels. We emphasize that such assumption is unrealistic for real-world…