English
Related papers

Related papers: Biased Mixtures Of Experts: Enabling Computer Visi…

200 papers

Conventional inverse optimization inputs a solution and finds the parameters of an optimization model that render a given solution optimal. The literature mostly focuses on inferring the objective function in linear problems when accepted…

Optimization and Control · Mathematics 2024-10-10 Houra Mahmoudzadeh , Kimia Ghobadi

A useful strategy to deal with complex classification scenarios is the "divide and conquer" approach. The mixture of experts (MOE) technique makes use of this strategy by joinly training a set of classifiers, or experts, that are…

Machine Learning · Computer Science 2014-05-30 Billy Peralta

We propose an approach to self-supervised representation learning based on maximizing mutual information between features extracted from multiple views of a shared context. For example, one could produce multiple views of a local…

Machine Learning · Computer Science 2019-07-09 Philip Bachman , R Devon Hjelm , William Buchwalter

Bias mitigation in image classification has been widely researched, and existing methods have yielded notable results. However, most of these methods implicitly assume that a given image contains only one type of known or unknown bias,…

Computer Vision and Pattern Recognition · Computer Science 2023-08-22 Jiaxuan Li , Duc Minh Vo , Hideki Nakayama

The Mixture of Experts (MoE) is a widely known neural architecture where an ensemble of specialized sub-models optimizes overall performance with a constant computational cost. However, conventional MoEs pose challenges at scale due to the…

Computation and Language · Computer Science 2023-09-12 Ted Zadouri , Ahmet Üstün , Arash Ahmadian , Beyza Ermiş , Acyr Locatelli , Sara Hooker

Mixup is a data augmentation technique that relies on training using random convex combinations of data points and their labels. In recent years, Mixup has become a standard primitive used in the training of state-of-the-art image…

Machine Learning · Computer Science 2024-11-06 Muthu Chidambaram , Xiang Wang , Chenwei Wu , Rong Ge

Mixture-of-Experts (MoE) models have gained popularity as a means of scaling the capacity of large language models (LLMs) while maintaining sparse activations and reduced per-token compute. However, in memory-constrained inference settings,…

Machine Learning · Computer Science 2026-03-23 Vivan Madan , Prajwal Singhania , Abhinav Bhatele , Tom Goldstein , Ashwinee Panda

Mixture-of-Experts (MoE) models have gained popularity in achieving state-of-the-art performance in a wide range of tasks in computer vision and natural language processing. They effectively expand the model capacity while incurring a…

Distributed, Parallel, and Cluster Computing · Computer Science 2023-06-21 Haiyang Huang , Newsha Ardalani , Anna Sun , Liu Ke , Hsien-Hsin S. Lee , Anjali Sridhar , Shruti Bhosale , Carole-Jean Wu , Benjamin Lee

Visual saliency models have recently begun to incorporate deep learning to achieve predictive capacity much greater than previous unsupervised methods. However, most existing models predict saliency using local mechanisms limited to the…

Computer Vision and Pattern Recognition · Computer Science 2018-07-04 Samuel Dodge , Lina Karam

Mixture-of-Experts (MoE) models improve transformer efficiency but lack a unified theoretical explanation, especially when both feed-forward and attention layers are allowed to specialize. To this end, we study the Mixture-of-Transformers…

Machine Learning · Computer Science 2025-11-03 Hongbo Li , Qinhang Wu , Sen Lin , Yingbin Liang , Ness B. Shroff

Learning with limited data is one of the biggest problems of machine learning. Current approaches to this issue consist in learning general representations from huge amounts of data before fine-tuning the model on a small dataset of…

Machine Learning · Computer Science 2023-02-22 Grégoire Mialon

Sparse Mixture of Experts (sMoE) has become a pivotal approach for scaling large vision-language models, offering substantial capacity while maintaining computational efficiency through dynamic, sparse activation of experts. However,…

Machine Learning · Computer Science 2025-10-21 Yongxiang Hua , Haoyu Cao , Zhou Tao , Bocheng Li , Zihao Wu , Chaohu Liu , Linli Xu

We study deep neural networks for classification of images with quality distortions. We first show that networks fine-tuned on distorted data greatly outperform the original networks when tested on distorted data. However, fine-tuned…

Computer Vision and Pattern Recognition · Computer Science 2017-03-24 Samuel Dodge , Lina Karam

Mixture models, such as Gaussian mixture models, are widely used in machine learning to represent complex data distributions. A key challenge, especially in high-dimensional settings, is to determine the mixture order and estimate the…

Optimization and Control · Mathematics 2025-09-30 Srećko Đurašinović , Jean-Bernard Lasserre , Victor Magron

The traditional viewpoint on Sparse Mixture of Experts (MoE) models is that instead of training a single large expert, which is computationally expensive, we can train many small experts. The hope is that if the total parameter count of the…

Machine Learning · Computer Science 2024-09-04 Youngseog Chung , Dhruv Malik , Jeff Schneider , Yuanzhi Li , Aarti Singh

In the domain of intelligent transportation systems (ITS), collaborative perception has emerged as a promising approach to overcome the limitations of individual perception by enabling multiple agents to exchange information, thus enhancing…

Multiagent Systems · Computer Science 2023-05-04 Ahmed N. Ahmed , Siegfried Mercelis , Ali Anwar

In recent years, several unsupervised, "contrastive" learning algorithms in vision have been shown to learn representations that perform remarkably well on transfer tasks. We show that this family of algorithms maximizes a lower bound on…

Machine Learning · Computer Science 2020-06-08 Mike Wu , Chengxu Zhuang , Milan Mosse , Daniel Yamins , Noah Goodman

The Mixture-of-Experts (MoE) model uses a set of expert networks that specialize on subsets of a dataset under the supervision of a gating network. A common issue in MoE architectures is ``expert collapse'' where overlapping class…

Neural and Evolutionary Computing · Computer Science 2026-03-31 Abien Fred Agarap , Arnulfo P. Azcarraga

We introduce a learning framework called learning using privileged information (LUPI) to the computer vision field. We focus on the prototypical computer vision problem of teaching computers to recognize objects in images. We want the…

Computer Vision and Pattern Recognition · Computer Science 2014-10-03 Viktoriia Sharmanska , Novi Quadrianto , Christoph H. Lampert

The success of monocular depth estimation relies on large and diverse training sets. Due to the challenges associated with acquiring dense ground-truth depth across different environments at scale, a number of datasets with distinct…

Computer Vision and Pattern Recognition · Computer Science 2020-08-26 René Ranftl , Katrin Lasinger , David Hafner , Konrad Schindler , Vladlen Koltun