相关论文: Breaking Inter-Layer Co-Adaptation by Classifier A…

Deep neural network based object detection hasbecome the cornerstone of many real-world applications. Alongwith this success comes concerns about its vulnerability tomalicious attacks. To gain more insight into this issue, we proposea…

Provider exposure fairness is crucial for sustaining a healthy content ecosystem and preventing monopolization in recommender systems. Yet, most existing methods either incorporate fairness constraints during model training, requiring…

In machine learning and computer vision, input images are often filtered to increase data discriminability. In some situations, however, one may wish to purposely decrease discriminability of one classification task (a "distractor" task),…

We propose an extended framework for marginalized domain adaptation, aimed at addressing unsupervised, supervised and semi-supervised scenarios. We argue that the denoising principle should be extended to explicitly promote domain-invariant…

Continual learning with vision-language models like CLIP offers a pathway toward scalable machine learning systems by leveraging its transferable representations. Existing CLIP-based methods adapt the pre-trained image encoder by adding…

In this study, we propose a feature extraction framework based on contrastive learning with adaptive positive and negative samples (CL-FEFA) that is suitable for unsupervised, supervised, and semi-supervised single-view feature extraction.…

As foundation models gain prominence, Federated Foundation Models (FedFM) have emerged as a privacy-preserving approach to collaboratively fine-tune models in federated learning (FL) frameworks using distributed datasets across clients. A…

Multi-omics data present significant challenges for statistical inference due to the complex interdependencies among biological layers. In this paper, we introduce a novel Multi-Omics Factor-Adjusted Cox (MOFA-Cox) model for analyzing…

We present a general approach for collaborative filtering (CF) using spectral regularization to learn linear operators from "users" to the "objects" they rate. Recent low-rank type matrix completion approaches to CF are shown to be special…

Domain generalization involves learning a classifier from a heterogeneous collection of training sources such that it generalizes to data drawn from similar unknown target domains, with applications in large-scale learning and personalized…

Open-vocabulary camouflaged object segmentation requires models to segment camouflaged objects of arbitrary categories unseen during training, placing extremely high demands on generalization capabilities. Through analysis of existing…

We present LOWA, a novel method for localizing objects with attributes effectively in the wild. It aims to address the insufficiency of current open-vocabulary object detectors, which are limited by the lack of instance-level attribute…

While Low-Rank Adaptation (LoRA) has proven beneficial for efficiently fine-tuning large models, LoRA fine-tuned text-to-image diffusion models lack diversity in the generated images, as the model tends to copy data from the observed…

Federated learning, while being a promising approach for collaborative model training, is susceptible to backdoor attacks due to its decentralized nature. Backdoor attacks have shown remarkable stealthiness, as they compromise model…

We propose two algorithms for boosting random Fourier feature models for approximating high-dimensional functions. These methods utilize the classical and generalized analysis of variance (ANOVA) decomposition to learn low-order functions,…

Domain generalization (DG) task aims to learn a robust model from source domains that could handle the out-of-distribution (OOD) issue. In order to improve the generalization ability of the model in unseen domains, increasing the diversity…

Existing point cloud learning methods aggregate features from neighbouring points relying on constructing graph in the spatial domain, which results in feature update for each point based on spatially-fixed neighbours throughout layers. In…

In real-world scenarios, different features have different acquisition costs at test-time which necessitates cost-aware methods to optimize the cost and performance trade-off. This paper introduces a novel and scalable approach for…

Test-Time Adaptation (TTA) aims to mitigate distributional shifts between training and test domains during inference time. However, existing TTA methods fall short in the realistic scenario where models face both continually changing…

It is a central challenge in deep learning to understand how neural networks learn representations. A leading approach is the Neural Feature Ansatz (NFA) (Radhakrishnan et al. 2024), a conjectured mechanism for how feature learning occurs.…