相关论文: Limitations of Post-Hoc Feature Alignment for Robu…

To tackle the scarcity and privacy issues associated with domain-specific datasets, the integration of federated learning in conjunction with fine-tuning has emerged as a practical solution. However, our findings reveal that federated…

The empirical fact that classifiers, trained on given data collections, perform poorly when tested on data acquired in different settings is theoretically explained in domain adaptation through a shift among distributions of the source and…

In this study, we focus on the unsupervised domain adaptation problem where an approximate inference model is to be learned from a labeled data domain and expected to generalize well to an unlabeled data domain. The success of unsupervised…

Deep neural networks often produce miscalibrated probability estimates, leading to overconfident predictions. A common approach for calibration is fitting a post-hoc calibration map on unseen validation data that transforms predicted…

Despite the significant success of deep learning in computer vision tasks, cross-domain tasks still present a challenge in which the model's performance will degrade when the training set and the test set follow different distributions.…

Neural network interpretation methods, particularly feature attribution methods, are known to be fragile with respect to adversarial input perturbations. To address this, several methods for enhancing the local smoothness of the gradient…

Image-conditioned Video diffusion models achieve impressive visual realism but often suffer from weakened motion fidelity, e.g., reduced motion dynamics or degraded long-term temporal coherence, especially after fine-tuning. We study the…

Several techniques for domain adaptation have been proposed to account for differences in the distribution of the data used for training and testing. The majority of this work focuses on a binary domain label. Similar problems occur in a…

Covariate shift has been shown to sharply degrade both predictive accuracy and the calibration of uncertainty estimates for deep learning models. This is worrying, because covariate shift is prevalent in a wide range of real world…

Deep learning requires regularization mechanisms to reduce overfitting and improve generalization. We address this problem by a new regularization method based on distributional robust optimization. The key idea is to modify the…

Robust fine-tuning aims to achieve competitive in-distribution (ID) performance while maintaining the out-of-distribution (OOD) robustness of a pre-trained model when transferring it to a downstream task. To remedy this, most robust…

Few-shot image classification, where the goal is to generalize to tasks with limited labeled data, has seen great progress over the years. However, the classifiers are vulnerable to adversarial examples, posing a question regarding their…

The success of Reinforcement Learning from Human Feedback (RLHF) in language model alignment is critically dependent on the capability of the reward model (RM). However, as the training process progresses, the output distribution of the…

We propose a method for unsupervised domain adaptation that trains a shared embedding to align the joint distributions of inputs (domain) and outputs (classes), making any classifier agnostic to the domain. Joint alignment ensures that not…

Research in machine learning is making progress in fixing its own reproducibility crisis. Reinforcement learning (RL), in particular, faces its own set of unique challenges. Comparison of point estimates, and plots that show successful…

Distribution alignment has many applications in deep learning, including domain adaptation and unsupervised image-to-image translation. Most prior work on unsupervised distribution alignment relies either on minimizing simple non-parametric…

Despite the high performance achieved by deep neural networks on various tasks, extensive studies have demonstrated that small tweaks in the input could fail the model predictions. This issue of deep neural networks has led to a number of…

Instance-level alignment is widely exploited for person re-identification, e.g. spatial alignment, latent semantic alignment and triplet alignment. This paper probes another feature alignment modality, namely cluster-level feature alignment…

Despite extensive research on neural network calibration, existing methods typically apply global transformations that treat all predictions uniformly, overlooking the heterogeneous reliability of individual predictions. Furthermore, the…

Though remarkable progress has been achieved in various vision tasks, deep neural networks still suffer obvious performance degradation when tested in out-of-distribution scenarios. We argue that the feature statistics (mean and standard…