Related papers: Curriculum Learning Meets Weakly Supervised Modali…

This paper proposes a novel training scheme for fast matching models in Search Ads, which is motivated by the real challenges in model training. The first challenge stems from the pursuit of high throughput, which prohibits the deployment…

Weakly supervised learning has drawn considerable attention recently to reduce the expensive time and labor consumption of labeling massive data. In this paper, we investigate a novel weakly supervised learning problem of learning from…

Weakly supervised object detection has recently received much attention, since it only requires image-level labels instead of the bounding-box labels consumed in strongly supervised learning. Nevertheless, the save in labeling expense is…

Self-paced curriculum learning (SCL) has demonstrated its great potential in computer vision, natural language processing, etc. During training, it implements easy-to-hard sampling based on online estimation of data difficulty. Most SCL…

Neural Encoders are frequently used in the NLP domain to perform dense retrieval tasks, for instance, to generate the candidate documents for a given query in question-answering tasks. However, sparse annotation and label noise in the…

Curriculum learning-organizing training data from easy to hard-has improved efficiency across machine learning domains, yet remains underexplored for language model pretraining. We present the first systematic investigation of curriculum…

Class activation maps (CAMs) are commonly employed in weakly supervised semantic segmentation (WSSS) to produce pseudo-labels. Due to incomplete or excessive class activation, existing studies often resort to offline CAM refinement,…

Self-training is an effective approach to semi-supervised learning. The key idea is to let the learner itself iteratively generate "pseudo-supervision" for unlabeled instances based on its current hypothesis. In combination with consistency…

We propose a meta-learning method for semi-supervised learning that learns from multiple tasks with heterogeneous attribute spaces. The existing semi-supervised meta-learning methods assume that all tasks share the same attribute space,…

Recent semi-supervised learning (SSL) methods are commonly based on pseudo labeling. Since the SSL performance is greatly influenced by the quality of pseudo labels, mutual learning has been proposed to effectively suppress the noises in…

Learning from positive and unlabeled data is known as positive-unlabeled (PU) learning in literature and has attracted much attention in recent years. One common approach in PU learning is to sample a set of pseudo-negatives from the…

Since the rise of deep learning, many computer vision tasks have seen significant advancements. However, the downside of deep learning is that it is very data-hungry. Especially for segmentation problems, training a deep neural net requires…

Like humans, deep networks have been shown to learn better when samples are organized and introduced in a meaningful order or curriculum. Conventional curriculum learning schemes introduce samples in their order of difficulty. This forces…

Curriculum Learning emphasizes the order of training instances in a computational learning setup. The core hypothesis is that simpler instances should be learned early as building blocks to learn more complex ones. Despite its usefulness,…

Given data with label noise (i.e., incorrect data), deep neural networks would gradually memorize the label noise and impair model performance. To relieve this issue, curriculum learning is proposed to improve model performance and…

Machine learning techniques applied to the Natural Language Processing (NLP) component of conversational agent development show promising results for improved accuracy and quality of feedback that a conversational agent can provide. The…

Most existing policy learning solutions require the learning agents to receive high-quality supervision signals such as well-designed rewards in reinforcement learning (RL) or high-quality expert demonstrations in behavioral cloning (BC).…

Multimodal deep learning systems which employ multiple modalities like text, image, audio, video, etc., are showing better performance in comparison with individual modalities (i.e., unimodal) systems. Multimodal machine learning involves…

Sequential recommenders that are trained on implicit feedback are usually learned as a multi-class classification task through softmax-based loss functions on one-hot class labels. However, one-hot training labels are sparse and may lead to…

Existing adversarial training (AT) methods often suffer from incomplete perturbation, meaning that not all non-robust features are perturbed when generating adversarial examples (AEs). This results in residual correlations between…