相关论文: Curriculum Learning for Multi-Task Classification …

Visual perceptual tasks aim to predict human judgment of images (e.g., emotions invoked by images, image quality assessment). Unlike objective tasks such as object/scene recognition, perceptual tasks rely on subjective human assessments,…

In the paradigm of multi-task learning, mul- tiple related prediction tasks are learned jointly, sharing information across the tasks. We propose a framework for multi-task learn- ing that enables one to selectively share the information…

For many computer vision applications, such as image description and human identification, recognizing the visual attributes of humans is an essential yet challenging problem. Its challenges originate from its multi-label nature, the large…

Curriculum learning in reinforcement learning is used to shape exploration by presenting the agent with increasingly complex tasks. The idea of curriculum learning has been largely applied in both animal training and pedagogy. In…

Learning skills by imitation is a promising concept for the intuitive teaching of robots. A common way to learn such skills is to learn a parametric model by maximizing the likelihood given the demonstrations. Yet, human demonstrations are…

Curriculum learning provides a systematic approach to training. It refines training progressively, tailors training to task requirements, and improves generalization through exposure to diverse examples. We present a curriculum learning…

Matching individuals across non-overlapping camera networks, known as person re-identification, is a fundamentally challenging problem due to the large visual appearance changes caused by variations of viewpoints, lighting, and occlusion.…

Curriculum Learning is the presentation of samples to the machine learning model in a meaningful order instead of a random order. The main challenge of Curriculum Learning is determining how to rank these samples. The ranking of the samples…

In practical applications, computer vision tasks often need to be addressed simultaneously. Multitask learning typically achieves this by jointly training a single deep neural network to learn shared representations, providing efficiency…

Image-caption pretraining has been quite successfully used for downstream vision tasks like zero-shot image classification and object detection. However, image-caption pretraining is still a hard problem -- it requires multiple concepts…

Learning paradigms involving varying levels of supervision have received a lot of interest within the computer vision and machine learning communities. The supervisory information is typically considered to come from a human supervisor -- a…

Curriculum learning is a training strategy that sorts the training examples by some measure of their difficulty and gradually exposes them to the learner to improve the network performance. Motivated by our insights from implicit curriculum…

In this paper, we consider the problem of simultaneously detecting objects and inferring their visual attributes in an image, even for those with no manual annotations provided at the training stage, resembling an open-vocabulary scenario.…

Many computer vision tasks address the problem of scene understanding and are naturally interrelated e.g. object classification, detection, scene segmentation, depth estimation, etc. We show that we can leverage the inherent relationships…

While Curriculum Learning (CL) has recently gained traction in Natural language Processing Tasks, it is still not adequately analyzed. Previous works only show their effectiveness but fail short to explain and interpret the internal…

Attributes, or semantic features, have gained popularity in the past few years in domains ranging from activity recognition in video to face verification. Improving the accuracy of attribute classifiers is an important first step in any…

Humans can progressively learn visual concepts from easy to hard questions. To mimic this efficient learning ability, we propose a competence-aware curriculum for visual concept learning in a question-answering manner. Specifically, we…

Research in child development has shown that embodied experience handling physical objects contributes to many cognitive abilities, including visual learning. One characteristic of such experience is that the learner sees the same object…

Image classification, which classifies images by pre-defined categories, has been the dominant approach to visual representation learning over the last decade. Visual learning through image-text alignment, however, has emerged to show…

Existing self-supervised learning methods learn representation by means of pretext tasks which are either (1) discriminating that explicitly specify which features should be separated or (2) aligning that precisely indicate which features…