相关论文: Streaming Anchor Loss: Augmenting Supervision with…

This paper introduces an active learning (AL) framework for anomalous sound detection (ASD) in machine condition monitoring system. Typically, ASD models are trained solely on normal samples due to the scarcity of anomalous data, leading to…

Standard deep learning relies on Backpropagation (BP), which is constrained by biologically implausible weight symmetry and suffers from significant gradient interference within dense representations. To mitigate these bottlenecks, we…

This paper proposes a novel active boundary loss for semantic segmentation. It can progressively encourage the alignment between predicted boundaries and ground-truth boundaries during end-to-end training, which is not explicitly enforced…

Structured output prediction problems are ubiquitous in machine learning. The prominent approach leverages neural networks as powerful feature extractors, otherwise assuming the independence of the outputs. These outputs, however, jointly…

The aim of speech enhancement is to improve speech signal quality and intelligibility from a noisy microphone signal. In many applications, it is crucial to enable processing with small computational complexity and minimal requirements…

Streaming ASR with strict latency constraints is required in many speech recognition applications. In order to achieve the required latency, streaming ASR models sacrifice accuracy compared to non-streaming ASR models due to lack of future…

Spatiotemporal predictive learning offers a self-supervised learning paradigm that enables models to learn both spatial and temporal patterns by predicting future sequences based on historical sequences. Mainstream methods are dominated by…

Neural networks are very effective when trained on large datasets for a large number of iterations. However, when they are trained on non-stationary streams of data and in an online fashion, their performance is reduced (1) by the online…

Recent years have witnessed growing interests in online incremental learning. However, there are three major challenges in this area. The first major difficulty is concept drift, that is, the probability distribution in the streaming data…

Recently, a few novel streaming attention-based sequence-to-sequence (S2S) models have been proposed to perform online speech recognition with linear-time decoding complexity. However, in these models, the decisions to generate tokens are…

In recent years, deep neural networks have shown remarkable progress in dense disparity estimation from dynamic scenes in monocular structured light systems. However, their performance significantly drops when applied in unseen…

Robot locomotion learning using reinforcement learning suffers from training sample inefficiency and exhibits the non-understandable/black-box nature. Thus, this work presents a novel SME-AGOL to address such problems. Firstly, Sequential…

Recent advances have demonstrated the potential of decoderonly large language models (LLMs) for automatic speech recognition (ASR). However, enabling streaming recognition within this framework remains a challenge. In this work, we propose…

Video frame transmission delay is critical in real-time applications such as online video gaming, live show, etc. The receiving deadline of a new frame must catch up with the frame rendering time. Otherwise, the system will buffer a while,…

An underlying assumption in conventional multi-view learning algorithms is that all views can be simultaneously accessed. However, due to various factors when collecting and pre-processing data from different views, the streaming view…

While deep feature learning has revolutionized techniques for static-image understanding, the same does not quite hold for video processing. Architectures and optimization techniques used for video are largely based off those for static…

Future mobile ad hoc networks will share spectrum between many users. Channels will be assigned on the fly to guarantee signal and interference power requirements for requested links. Channel losses must be re-estimated between many pairs…

In this work, we introduce a learning model designed to meet the needs of applications in which computational resources are limited, and robustness and interpretability are prioritized. Learning problems can be formulated as constrained…

Developing effective predictive models becomes challenging in dynamic environments that continuously produce data and constantly change. Continual Learning (CL) and Streaming Machine Learning (SML) are two research areas that tackle this…

One of the challenges in deploying a machine learning model is that the model's performance degrades as the operating environment changes. To maintain the performance, streaming active learning is used, in which the model is retrained by…