Related papers: Free Lunch for Domain Adversarial Training: Enviro…

Since deep neural networks are over-parameterized, they can memorize noisy examples. We address such a memorization issue in the presence of label noise. From the fact that deep neural networks cannot generalize to neighborhoods of…

ConvNets achieve good results when training from clean data, but learning from noisy labels significantly degrades performances and remains challenging. Unlike previous works constrained by many conditions, making them infeasible to real…

Deep neural networks trained with standard cross-entropy loss memorize noisy labels, which degrades their performance. Most research to mitigate this memorization proposes new robust classification loss functions. Conversely, we propose a…

Semantic segmentation of SAR images has garnered significant attention in remote sensing due to the immunity of SAR sensors to cloudy weather and light conditions. Nevertheless, SAR imagery lacks detailed information and is plagued by…

We show that variational learning naturally induces an adaptive label smoothing where label noise is specialized for each example. Such label-smoothing is useful to handle examples with labeling errors and distribution shifts, but designing…

Domain adversarial training has shown its effective capability for finding domain invariant feature representations and been successfully adopted for various domain adaptation tasks. However, recent advances of large models (e.g., vision…

Traditional methods for learning with the presence of noisy labels have successfully handled datasets with artificially injected noise but still fall short of adequately handling real-world noise. With the increasing use of meta-learning in…

Anomalous sound detection (ASD) in the wild requires robustness to distribution shifts such as unseen low-SNR input mixtures of machine and noise types. State-of-the-art systems extract embeddings from an adapted audio encoder and detect…

Learning from noisy labels (LNL) is a challenge that arises in many real-world scenarios where collected training data can contain incorrect or corrupted labels. Most existing solutions identify noisy labels and adopt active learning to…

A recent technique of randomized smoothing has shown that the worst-case (adversarial) $\ell_2$-robustness can be transformed into the average-case Gaussian-robustness by "smoothing" a classifier, i.e., by considering the averaged…

When modeling dynamical systems from real-world data samples, the distribution of data often changes according to the environment in which they are captured, and the dynamics of the system itself vary from one environment to another.…

Object recognition is a key enabler across industry and defense. As technology changes, algorithms must keep pace with new requirements and data. New modalities and higher resolution sensors should allow for increased algorithm robustness.…

The open source of large amounts of image data promotes the development of deep learning techniques. Along with this comes the privacy risk of these open-source image datasets being exploited by unauthorized third parties to train deep…

Regularization techniques are crucial to improving the generalization performance and training efficiency of deep neural networks. Many deep learning algorithms rely on weight decay, dropout, batch/layer normalization to converge faster and…

Today's available datasets in the wild, e.g., from social media and open platforms, present tremendous opportunities and challenges for deep learning, as there is a significant portion of tagged images, but often with noisy, i.e. erroneous,…

Label noise is a pervasive problem in deep learning that often compromises the generalization performance of trained models. Recently, leveraging privileged information (PI) -- information available only during training but not at test time…

Softmax Loss (SL) is being increasingly adopted for recommender systems (RS) as it has demonstrated better performance, robustness and fairness. Yet in implicit-feedback, a single global temperature and equal treatment of uniformly sampled…

Despite rapid advances in speech recognition, current models remain brittle to superficial perturbations to their inputs. Small amounts of noise can destroy the performance of an otherwise state-of-the-art model. To harden models against…

The problem of domain generalization concerns learning predictive models that are robust to distribution shifts when deployed in new, previously unseen environments. Existing methods typically require labeled data from multiple training…

Foundation models are usually pre-trained on large-scale datasets and then adapted to downstream tasks through tuning. However, the large-scale pre-training datasets, often inaccessible or too expensive to handle, can contain label noise…