paper-with-me

홈 › Papers

Mixture of Nested Experts: Adaptive Processing of Visual Tokens

2024-07-29 · Gagan Jain, Nidhi Hegde, Aditya Kusupati, Arsha Nagrani, Shyamal Buch, Prateek Jain, Anurag Arnab, Sujoy Paul

The visual medium (images and videos) naturally contains a large amount of information redundancy, thereby providing a great opportunity for leveraging efficiency in processing. While Vision Transformer (ViT) based models scale effectively to large data regimes, they fail to capitalize on this inherent redundancy, leading to higher computational costs. Mixture of Experts (MoE) networks demonstrate scalability while maintaining same inference-time costs, but they come with a larger parameter footprint. We present Mixture of Nested Experts (MoNE), which utilizes a nested structure for experts, wherein individual experts fall on an increasing compute-accuracy curve. Given a compute budget, MoNE learns to dynamically choose tokens in a priority order, and thus redundant tokens are processed through cheaper nested experts. Using this framework, we achieve equivalent performance as the baseline models, while reducing inference time compute by over two-fold. We validate our approach on standard image and video datasets - ImageNet-21K, Kinetics400, and Something-Something-v2. We further highlight MoNE$'$s adaptability by showcasing its ability to maintain strong performance across different inference-time compute budgets on videos, using only a single trained model.

📄 PDF Abstract BibTeX arXiv:2407.19985

Code (1)

usryokousha/mone-pytorch pytorch

Tasks

Mixture-of-Experts

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Adam 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Position-Wise Feed-Forward Layer 설명 없음

Similar Papers 제목 키워드 기반

MoSE: Mixture of Slimmable Experts for Efficient and Adaptive Language Models

2026-02-05 · Nurbek Tastan, Stefanos Laskaridis, Karthik Nandakumar, Samuel Horvath arxiv

Mixture-of-Experts (MoE) models scale large language models efficiently by sparsely activating experts, but once an expert is selected, it is executed fully. Hence, the trade-off between accuracy and computation in an Mo…

AdaMoLE: Fine-Tuning Large Language Models with Adaptive Mixture of Low-Rank Adaptation Experts

2024-05-01 · Zefang Liu, Jiahua Luo

We introduce AdaMoLE, a novel method for fine-tuning large language models (LLMs) through an Adaptive Mixture of Low-Rank Adaptation (LoRA) Experts. Moving beyond conventional methods that employ a static top-k strategy …

Multiple Choice Question Answering (MCQA)

MoEMambaMIL: Structure-Aware Selective State Space Modeling for Whole-Slide Image Analysis

2026-03-06 · Dongqing Xie, Yonghuang Wu arxiv

Whole-slide image (WSI) analysis is challenging due to the gigapixel scale of slides and their inherent hierarchical multi-resolution structure. Existing multiple instance learning (MIL) approaches often model WSIs as un…

Multiple Instance Learning

MedMoE: Modality-Specialized Mixture of Experts for Medical Vision-Language Understanding

2025-06-10 · Shivang Chopra, Lingchao Mao, Gabriela Sanchez-Rodriguez, Andrew J Feola 외

Different medical imaging modalities capture diagnostic information at varying spatial resolutions, from coarse global patterns to fine-grained localized structures. However, most existing vision-language frameworks in t…

DiagnosticMixture-of-Experts

Adaptive Mixture of Low-Rank Experts for Robust Audio Spoofing Detection

2025-03-15 · Qixian Chen, Yuxiong Xu, Sara Mandelli, Sheng Li 외

In audio spoofing detection, most studies rely on clean datasets, making models susceptible to real-world post-processing attacks, such as channel compression and noise. To overcome this challenge, we propose the Adaptiv…

Mixture-of-Experts