Related papers: Multi-Task Learning with Multi-Annotation Triplet …
As an effective way of metric learning, triplet loss has been widely used in many deep learning tasks, including face recognition and person-ReID, leading to many states of the arts. The main innovation of triplet loss is using feature map…
Despite the recent advances in the field of object detection, common architectures are still ill-suited to incrementally detect new categories over time. They are vulnerable to catastrophic forgetting: they forget what has been already…
Traditional image annotation tasks rely heavily on human effort for object selection and label assignment, making the process time-consuming and prone to decreased efficiency as annotators experience fatigue after extensive work. This paper…
Incremental Task learning (ITL) is a category of continual learning that seeks to train a single network for multiple tasks (one after another), where training data for each task is only available during the training of that task. Neural…
Complementary-label learning (CLL) is widely used in weakly supervised classification, but it faces a significant challenge in real-world datasets when confronted with class-imbalanced training samples. In such scenarios, the number of…
Task-driven features learned by modern object detectors optimize end task loss yet often capture shortcut correlations that fail to reflect underlying annotation structure. Such representations limit transfer, interpretability, and…
Learning algorithms normally assume that there is at most one annotation or label per data point. However, in some scenarios, such as medical diagnosis and on-line collaboration,multiple annotations may be available. In either case,…
We present several methods to improve the generalisation of language identification (LID) systems to new speakers and to new domains. These methods involve Spectral augmentation, where spectrograms are masked in the frequency or time bands…
In multi-task learning, difficulty levels of different tasks are varying. There are many works to handle this situation and we classify them into five categories, including the direct sum approach, the weighted sum approach, the maximum…
In multi-task learning, a learner is given a collection of prediction tasks and needs to solve all of them. In contrast to previous work, which required that annotated training data is available for all tasks, we consider a new setting, in…
Despite the recent progress in speech emotion recognition (SER), state-of-the-art systems lack generalisation across different conditions. A key underlying reason for poor generalisation is the scarcity of emotion datasets, which is a…
Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse domains, but developing high-performing models for specialized applications often requires substantial human annotation -- a process that is…
Multi-atlas segmentation is a widely used tool in medical image analysis, providing robust and accurate results by learning from annotated atlas datasets. However, the availability of fully annotated atlas images for training is limited due…
Multi-task learning (MTL) is a supervised learning paradigm in which the prediction models for several related tasks are learned jointly to achieve better generalization performance. When there are only a few training examples per task, MTL…
Supervised 3D Object Detection models have been displaying increasingly better performance in single-domain cases where the training data comes from the same environment and sensor as the testing data. However, in real-world scenarios data…
In a typical multi-label setting, a picture contains on average few positive labels, and many negative ones. This positive-negative imbalance dominates the optimization process, and can lead to under-emphasizing gradients from positive…
The comparative losses (typically, triplet loss) are appealing choices for learning person re-identification (ReID) features. However, the triplet loss is computationally much more expensive than the (practically more popular)…
Multi-task learning (MTL) trains deep neural networks to optimize several objectives simultaneously using a shared backbone, which leads to reduced computational costs, improved data efficiency, and enhanced performance through cross-task…
When faced with learning a set of inter-related tasks from a limited amount of usable data, learning each task independently may lead to poor generalization performance. Multi-Task Learning (MTL) exploits the latent relations between tasks…
Traditional supervised learning heavily relies on human-annotated datasets, especially in data-hungry neural approaches. However, various tasks, especially multi-label tasks like document-level relation extraction, pose challenges in fully…