Related papers: Pseudo-Convolutional Policy Gradient for Sequence-…

Lipreading refers to understanding and further translating the speech of a speaker in the video into natural language. State-of-the-art lipreading methods excel in interpreting overlap speakers, i.e., speakers appear in both training and…

Reinforcement learning (RL) is about sequential decision making and is traditionally opposed to supervised learning (SL) and unsupervised learning (USL). In RL, given the current state, the agent makes a decision that may influence the next…

Semantic segmentation takes pivotal roles in various applications such as autonomous driving and medical image analysis. When deploying segmentation models in practice, it is critical to test their behaviors in varied and complex scenes in…

Learning a goal-oriented dialog policy is generally performed offline with supervised learning algorithms or online with reinforcement learning (RL). Additionally, as companies accumulate massive quantities of dialog transcripts between…

Prompt-based pre-trained language models (PLMs) paradigm have succeeded substantially in few-shot natural language processing (NLP) tasks. However, prior discrete prompt optimization methods require expert knowledge to design the base…

This paper looks at semi-supervised learning (SSL) for image-based text recognition. One of the most popular SSL approaches is pseudo-labeling (PL). PL approaches assign labels to unlabeled data before re-training the model with a…

CLIP (Contrastive Language-Image Pretraining) is well-developed for open-vocabulary zero-shot image-level recognition, while its applications in pixel-level tasks are less investigated, where most efforts directly adopt CLIP features…

Constrained Reinforcement Learning (CRL) addresses sequential decision-making problems where agents are required to achieve goals by maximizing the expected return while meeting domain-specific constraints. In this setting, policy-based…

Vision model have gained increasing attention due to their simplicity and efficiency in Scene Text Recognition (STR) task. However, due to lacking the perception of linguistic knowledge and information, recent vision models suffer from two…

Speech recognition systems have achieved high recognition performance for several tasks. However, the performance of such systems is dependent on the tremendously costly development work of preparing vast amounts of task-matched transcribed…

Diffusion model, a new generative modelling paradigm, has achieved great success in image, audio, and video generation. However, considering the discrete categorical nature of text, it is not trivial to extend continuous diffusion models to…

Policy gradient (PG) methods are successful approaches to deal with continuous reinforcement learning (RL) problems. They learn stochastic parametric (hyper)policies by either exploring in the space of actions or in the space of parameters.…

The increasingly stringent requirement on quality-of-experience in 5G/B5G communication systems has led to the emerging neural speech enhancement techniques, which however have been developed in isolation from the existing expert-rule based…

Neural sequence-to-sequence models are currently the dominant approach in several natural language processing tasks, but require large parallel corpora. We present a sequence-to-sequence-to-sequence autoencoder (SEQ^3), consisting of two…

To facilitate efficient learning, policy gradient approaches to deep reinforcement learning (RL) are typically paired with variance reduction measures and strategies for making large but safe policy changes based on a batch of experiences.…

This paper introduces a novel causal framework for multi-stage decision-making in natural language action spaces where outcomes are only observed after a sequence of actions. While recent approaches like Proximal Policy Optimization (PPO)…

Continual learning (CL) is crucial for language models to dynamically adapt to the evolving real-world demands. To mitigate the catastrophic forgetting problem in CL, data replay has been proven a simple and effective strategy, and the…

Pseudo-Labeling is a simple and effective approach to semi-supervised learning. It requires criteria that guide the selection of pseudo-labeled data. The latter have been shown to crucially affect pseudo-labeling's generalization…

This paper presents a novel machine learning framework to consistently detect, localize and rate congenital cleft lip anomalies in human faces. The goal is to provide a universal, objective measure of facial differences and reconstructive…

In conventional supervised pattern recognition tasks, model selection is typically accomplished by minimizing the classification error rate on a set of so-called development data, subject to ground-truth labeling by human experts or some…