Related papers: Are Labels Needed for Incremental Instance Learnin…
Learning with the \textit{instance-dependent} label noise is challenging, because it is hard to model such real-world noise. Note that there are psychological and physiological evidences showing that we humans perceive instances by…
Multiple instance learning (MIL) can reduce the need for costly annotation in tasks such as semantic segmentation by weakening the required degree of supervision. We propose a novel MIL formulation of multi-class semantic segmentation…
A major obstacle in instance segmentation is that existing methods often need many per-pixel labels in order to be effective. These labels require large human effort and for certain applications, such labels are not readily available. To…
The goal of this paper is to bypass the need for labelled examples in few-shot video understanding at run time. While proven effective, in many practical video settings even labelling a few examples appears unrealistic. This is especially…
Neural net classifiers trained on data with annotated class labels can also capture apparent visual similarity among categories without being directed to do so. We study whether this observation can be extended beyond the conventional…
In a real-world setting, object instances from new classes can be continuously encountered by object detectors. When existing object detectors are applied to such scenarios, their performance on old classes deteriorates significantly. A few…
Food instance segmentation is essential to estimate the serving size of dishes in a food image. The recent cutting-edge techniques for instance segmentation are deep learning networks with impressive segmentation quality and fast…
Multiple instance learning (MIL) is concerned with learning from sets (bags) of objects (instances), where the individual instance labels are ambiguous. In this setting, supervised learning cannot be applied directly. Often, specialized MIL…
Deep learning models rely heavily on large volumes of labeled data to achieve high performance. However, real-world datasets often contain noisy labels due to human error, ambiguity, or resource constraints during the annotation process.…
Multi-view learning (MVL) has gained great success in integrating information from multiple perspectives of a dataset to improve downstream task performance. To make MVL methods more practical in an open-ended environment, this paper…
Multiple instance learning (MIL) problem is currently solved from either bag-classification or instance-classification perspective, both of which ignore important information contained in some instances and result in limited performance.…
Weakly supervised instance labeling using only image-level labels, in lieu of expensive fine-grained pixel annotations, is crucial in several applications including medical image analysis. In contrast to conventional instance segmentation…
We present cVIL, a class-centric approach to visual interactive labeling, which facilitates human annotation of large and complex image data sets. cVIL uses different property measures to support instance labeling for labeling difficult…
Real-world tabular learning production scenarios typically involve evolving data streams, where data arrives continuously and its distribution may change over time. In such a setting, most studies in the literature regarding supervised…
Multi-Class Incremental Learning (MCIL) aims to learn new concepts by incrementally updating a model trained on previous concepts. However, there is an inherent trade-off to effectively learning new concepts without catastrophic forgetting…
Multi-task learns multiple tasks, while sharing knowledge and computation among them. However, it suffers from catastrophic forgetting of previous knowledge when learned incrementally without access to the old data. Most existing object…
Deep learning architectures exhibit a critical drop of performance due to catastrophic forgetting when they are required to incrementally learn new tasks. Contemporary incremental learning frameworks focus on image classification and object…
Instance segmentation is a computer vision task where separate objects in an image are detected and segmented. State-of-the-art deep neural network models require large amounts of labeled data in order to perform well in this task. Making…
Instance segmentation is an active topic in computer vision that is usually solved by using supervised learning approaches over very large datasets composed of object level masks. Obtaining such a dataset for any new domain can be very…
Most person re-identification methods, being supervised techniques, suffer from the burden of massive annotation requirement. Unsupervised methods overcome this need for labeled data, but perform poorly compared to the supervised…