cs.CVJun 26, 2026

CLEAR-MoE: Shared-Basis Expert Extraction from Frozen Vision Transformers via Calibration-Driven Layer Selection

Authors: Md Irtiza Hossain, Humaira Ayesha, Junaid Ahmed Sifat

Organizations: Brac University

Abstract

We present CLEAR-MoE, a four-phase post-training pipeline that converts a frozen pretrained Vision Transformer (ViT) into a sparse Mixture-of-Experts (MoE) model without updating backbone weights. The pipeline (i) scores feed-forward network (FFN) layers by sparsity, clusterability, and output sensitivity; (ii) decomposes selected layers into a shared low-rank SVD basis and per-cluster residual experts using k-means clustering; (iii) trains lightweight routers supervised by cluster labels; and (iv) dispatches tokens through pluggable CUDA backends. On Imagenette with DeiT-Small, CLEAR-MoE retains 99.9% of the dense model's accuracy (86.70 +/- 0.02% versus 86.73%). Extensive ablation studies reveal a consistent empirical finding: the shared SVD basis is the primary factor responsible for preserving accuracy. Random routing, learned routing, and three different router architectures produce nearly identical performance, with accuracy varying by at most 0.06 percentage points (86.62%-86.68%). Accuracy also remains stable across different SVD ranks, expert counts (2-8), calibration set sizes (50-500), and random seeds. This behavior generalizes across five ViT backbones (DeiT-Tiny, DeiT-Small, DeiT-Base, ViT-Small, and ViT-Base), covering models from 5.7M to 86.6M parameters, with accuracy differences <= 0.10 percentage points from their dense counterparts. On a GTX 960 GPU, routing and scatter-gather overhead make the CLEAR-MoE FFN 1.3-1.7x slower than the dense implementation. A dispatch microbenchmark further shows that routing is an order of magnitude more memory-bound than expert matrix multiplications, identifying fused dispatch kernels as a promising direction for future optimization.

Explore similar work

CardsList
May 15, 2026cs.CV

When Does Sparse MoE Help in Vision? The Role of Backbone Compute Leverage in Sparse Routing

Mixture-of-Experts (MoE) networks promise favorable accuracy-compute trade-offs, yet practical vision deployments are hindered by expert collapse and limited end-to-end efficiency gains. We study when sparse top-kk routing with hard capacity constraints helps in vision classification, evaluated under multi-seed protocols on four benchmarks (CIFAR-10/100, Tiny-ImageNet, ImageNet-1K). We observe a \emph{compute-leverage pattern}: positive accuracy gaps require a substantial fraction ρρ of total FLOPs to be routed; at ImageNet scale this is necessary but not sufficient, as multi-expert routing (k≥2k \geq 2) is additionally required. Two controlled experiments isolate these factors. A hidden-size sweep on CIFAR-10 yields both predicted sign reversals across standard and depthwise backbones, ruling out backbone family as the active variable. An ImageNet-1K ablation that varies only top-kk -- holding architecture, initialization, and ρρ fixed -- reverses the gap from positive to negative across all five seeds. A per-sample variant of Soft MoE that softmaxes over experts rather than the batch rescues CIFAR-100 above the dense baseline, identifying batch-axis dispatch as the dominant failure mode in per-sample CNN settings. Code and aggregate results: https://github.com/libophd/sparse-moe-vision-rho.
Libo Sun, Po-wei Harn, Peixiong He +1
Mixture-Of-Expert RoutingSparsityImagenetTrade-OffRole
AskPDF
May 7, 2026cs.LG

VisMMOE: Exploiting Visual-Expert Affinity for Efficient Visual-Language MoE Offloading

Large-scale vision-language mixture-of-experts (VL-MoE) models provide strong multimodal capability, but efficient deployment on memory-constrained platforms remains difficult. Existing MoE offloading systems are largely designed for text-centric workloads and become much less effective for visual-heavy inputs, where large numbers of visual tokens induce broader and less predictable expert accesses. We present VisMMoE, a VL-MoE offloading system built on a single systems insight: pruning redundant visual tokens can improve offloading not only by reducing computation, but also by reshaping expert demand. We refer to this effect as \textit{visual-expert affinity}: token pruning makes expert accesses more concentrated within layers and more stable across layers, producing a smaller and more predictable expert working set. Guided by this insight, VisMMoE combines affinity-aware token compression, lookahead expert prediction, and cache/pipeline orchestration to improve expert locality and prefetch effectiveness under tight memory budgets. We implement VisMMoE on multiple frameworks and evaluate it on representative VL-MoE models and benchmarks. VisMMoE improves end-to-end inference performance by up to 2.68x and 1.61x, respectively, over strong baselines for today's VL-MoE deployments while maintaining competitive accuracy.
Cheng Xu, Xiaofeng Hou, Jiacheng Liu +1
Topic pending
AskPDF
May 11, 2026cs.LG

DECO: Sparse Mixture-of-Experts with Dense-Comparable Performance on End-Side Devices

While Mixture-of-Experts (MoE) scales model capacity without proportionally increasing computation, its massive total parameter footprint creates significant storage and memory-access bottlenecks, which hinder efficient end-side deployment that simultaneously requires high performance, low computational cost, and small storage overhead. To achieve these properties, we present DECO, a sparse MoE architecture designed to match the performance of dense Transformers under identical total parameter budgets and training tokens. DECO utilizes the differentiable and flexible ReLU-based routing enhanced by learnable expert-wise scaling, which adaptively balances the contributions of routed and shared experts. Furthermore, we introduce NormSiLU, an activation function that normalizes inputs prior to SiLU operators, producing a more stable trend of routed-expert activation ratio and a higher intrinsic sparsity level. We also identify an empirical advantage in using non-gated MLP experts with ReLU-based routing, indicating the possibility of MoE architecture simplification. Experiments demonstrate that DECO, activating only 20% of routed experts, matches dense performance and outperforms established MoE baselines. Our specialized acceleration kernel delivers a 2.93×\times speedup on Jetson AGX Orin compared with dense inference. Code and checkpoints are available at https://github.com/thunlp/DECO.
Chenyang Song, Weilin Zhao, Xu Han +3
Topic pending
AskPDF