Related papers: Feed Two Birds with One Scone: Exploiting Function…
Although prior work in computer vision has shown strong correlations between in-distribution (ID) and out-of-distribution (OOD) accuracies, such relationships remain underexplored in audio-based models. In this study, we investigate how…
Recent studies on transfer learning have shown that selectively fine-tuning a subset of layers or customizing different learning rates for each layer can greatly improve robustness to out-of-distribution (OOD) data and retain generalization…
Out-of-distribution (OOD) detection remains challenging for deep learning models, particularly when test-time OOD samples differ significantly from training outliers. We propose OODD, a novel test-time OOD detection method that dynamically…
Standard deep learning models that employ the categorical cross-entropy loss are known to perform well at image classification tasks. However, many standard models thus obtained often exhibit issues like feature redundancy, low…
A recent trend in deep learning algorithms has been towards training large scale models, having high parameter count and trained on big dataset. However, robustness of such large scale models towards real-world settings is still a…
Systematics contaminate observables, leading to distribution shifts relative to theoretically simulated signals-posing a major challenge for using pre-trained models to label such observables. Since systematics are often poorly understood…
Large-scale image-text pre-trained models enable zero-shot classification and provide consistent accuracy across various data distributions. Nonetheless, optimizing these models in downstream tasks typically requires fine-tuning, which…
Deep networks have achieved impressive results on a range of well-curated benchmark datasets. Surprisingly, their performance remains sensitive to perturbations that have little effect on human performance. In this work, we propose a novel…
In the field of computer vision, fine-tuning pre-trained models has become a prevalent strategy for out-of-distribution (OOD) generalization tasks. Different from most prior work that has focused on advancing learning algorithms, we…
As neural networks become deeper, the redundancy within their parameters increases. This phenomenon has led to several methods that attempt to reduce the correlation between convolutional filters. We propose a computationally efficient…
Bootstrapping is behind much of the successes of deep Reinforcement Learning. However, learning the value function via bootstrapping often leads to unstable training due to fast-changing target values. Target Networks are employed to…
Generalizing deep learning models to unknown target domain distribution with low latency has motivated research into test-time training/adaptation (TTT/TTA). Existing approaches often focus on improving test-time training performance under…
Among the reasons hindering reinforcement learning (RL) applications to real-world problems, two factors are critical: limited data and the mismatch between the testing environment (real environment in which the policy is deployed) and the…
Regularization and data augmentation methods have been widely used and become increasingly indispensable in deep learning training. Researchers who devote themselves to this have considered various possibilities. But so far, there has been…
Detecting Out-of-distribution (OOD) inputs have been a critical issue for neural networks in the open world. However, the unstable behavior of OOD detection along the optimization trajectory during training has not been explored clearly. In…
Out-of-distribution (OOD) detection is essential for ensuring the robustness of machine learning models by identifying samples that deviate from the training distribution. While traditional OOD detection has primarily focused on…
In this paper, we propose Selective Output Smoothing Regularization, a novel regularization method for training the Convolutional Neural Networks (CNNs). Inspired by the diverse effects on training from different samples, Selective Output…
Recently, we have witnessed generative retrieval increasingly gaining attention in the information retrieval (IR) field, which retrieves documents by directly generating their identifiers. So far, much effort has been devoted to developing…
Feature shaping refers to a family of methods that exhibit state-of-the-art performance for out-of-distribution (OOD) detection. These approaches manipulate the feature representation, typically from the penultimate layer of a pre-trained…
Machine learning models deployed in the open world may encounter observations that they were not trained to recognize, and they risk misclassifying such observations with high confidence. Therefore, it is essential that these models are…