相关论文: Rethinking Robust Representation Learning Under Fi…

Training triplet networks with large-scale data is challenging in face recognition. Due to the number of possible triplets explodes with the number of samples, previous studies adopt the online hard negative mining(OHNM) to handle it.…

Noise ubiquitously exists in signals due to numerous factors including physical, electronic, and environmental effects. Traditional methods of symbolic regression, such as genetic programming or deep learning models, aim to find the most…

By considering the spatial correspondence, dense self-supervised representation learning has achieved superior performance on various dense prediction tasks. However, the pixel-level correspondence tends to be noisy because of many similar…

Label noise is emerging as a pressing issue in sound event classification. This arises as we move towards larger datasets that are difficult to annotate manually, but it is even more severe if datasets are collected automatically from…

Noisy labels severely hinder the accuracy and generalization of machine learning models, especially when ambiguous instance features make reliable annotation difficult. Existing approaches, including transition-matrix-based label…

Recently, many unsupervised deep learning methods have been proposed to learn clustering with unlabelled data. By introducing data augmentation, most of the latest methods look into deep clustering from the perspective that the original…

The study of Dynamic Facial Expression Recognition (DFER) is a nascent field of research that involves the automated recognition of facial expressions in video data. Although existing research has primarily focused on learning…

Classical machine learning implicitly assumes that labels of the training data are sampled from a clean distribution, which can be too restrictive for real-world scenarios. However, statistical-learning-based methods may not train deep…

Feature noise and label noise are ubiquitous in practical scenarios, which pose great challenges for training a robust machine learning model. Most previous approaches usually deal with only a single problem of either feature noise or label…

Robustness is essential for deep neural networks, especially in security-sensitive applications. To this end, randomized smoothing provides theoretical guarantees for certifying robustness against adversarial perturbations. Recently,…

An important goal in deep learning is to learn versatile, high-level feature representations of input data. However, standard networks' representations seem to possess shortcomings that, as we illustrate, prevent them from fully realizing…

Latent representation learned from multi-layered neural networks via hierarchical feature abstraction enables recent success of deep learning. Under the deep learning framework, generalization performance highly depends on the learned…

Recent multimodal embedding approaches leveraging multimodal large language models (MLLMs) fine-tuned with contrastive learning (CL) have shown promising results, yet the underlying reasons behind their superiority remain underexplored.…

Robustness of deep neural networks to input noise remains a critical challenge, as naive noise injection often degrades accuracy on clean (uncorrupted) data. We propose a novel training framework that addresses this trade-off through two…

Self-supervised contrastive learning (CL) effectively learns transferable representations from unlabeled data containing images or image-text pairs but suffers vulnerability to data poisoning backdoor attacks (DPCLs). An adversary can…

Face clustering can provide pseudo-labels to the massive unlabeled face data and improve the performance of different face recognition models. The existing clustering methods generally aggregate the features within subgraphs that are often…

There is an emerging trend to leverage noisy image datasets in many visual recognition tasks. However, the label noise among the datasets severely degenerates the \mbox{performance of deep} learning approaches. Recently, one mainstream is…

Contrastive learning is among the most successful methods for visual representation learning, and its performance can be further improved by jointly performing clustering on the learned representations. However, existing methods for joint…

Environmental sound classification (ESC) is an important and challenging problem. In contrast to speech, sound events have noise-like nature and may be produced by a wide variety of sources. In this paper, we propose to use a novel deep…

Face clustering is an essential tool for exploiting the unlabeled face data, and has a wide range of applications including face annotation and retrieval. Recent works show that supervised clustering can result in noticeable performance…