Expert specialization in vision MoE models is dominated by a stable animate-inanimate distinction visible from gating to readout, with broader tuning to continuous visual and semantic dimensions rather than narrow categorical preferences.
ViMoE: An Empirical Study of Designing Vision Mixture-of- Experts, November 2024
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 7verdicts
UNVERDICTED 7roles
background 1polarities
background 1representative citing papers
FaceMoE introduces a MoE transformer with top-k routed specialized FFN experts for resolution-aware feature extraction in low-resolution face recognition, outperforming prior methods on eleven datasets.
ExPLoRe turns MoE dispatch weights into per-patch loss coefficients for multi-objective masked image modeling, reporting gains on ImageNet-1K and ADE20K transfer.
Patch-wise sparse MoE layers in CNNs for semantic segmentation yield architecture-dependent gains up to 3.9 mIoU on Cityscapes and BDD100K with low overhead, but show strong design sensitivity.
DoReMi uses self-supervised pre-training on topological and texture variations plus domain-aware experts with spatial-guided routing and entropy-controlled allocation to reach 80.1% mIoU on ScanNet and 77.2% mIoU on S3DIS.
Sparse MoE vision models show positive accuracy gaps only when routing a substantial compute fraction ρ and using k≥2 experts at large scale; batch-axis dispatch is identified as a key failure mode.
Mamoda2.5 is a 25B-parameter DiT-MoE unified AR-Diffusion model that reaches top video generation and editing benchmarks with 4-step inference up to 95.9x faster than baselines.
citing papers explorer
-
Beyond Routing: Characterising Expert Tuning and Representation in Vision Mixture-of-Experts
Expert specialization in vision MoE models is dominated by a stable animate-inanimate distinction visible from gating to readout, with broader tuning to continuous visual and semantic dimensions rather than narrow categorical preferences.
-
FaceMoE: Mixture of Experts for Low-Resolution Face Recognition
FaceMoE introduces a MoE transformer with top-k routed specialized FFN experts for resolution-aware feature extraction in low-resolution face recognition, outperforming prior methods on eleven datasets.
-
ExPLoRe: Expert Patch-Level Loss Routing for Multi-Objective Masked Image Modeling
ExPLoRe turns MoE dispatch weights into per-patch loss coefficients for multi-objective masked image modeling, reporting gains on ImageNet-1K and ADE20K transfer.
-
Design and Behavior of Sparse Mixture-of-Experts Layers in CNN-based Semantic Segmentation
Patch-wise sparse MoE layers in CNNs for semantic segmentation yield architecture-dependent gains up to 3.9 mIoU on Cityscapes and BDD100K with low overhead, but show strong design sensitivity.
-
DoReMi: Bridging 3D Domains via Topology-Aware Domain-Representation Mixture of Experts
DoReMi uses self-supervised pre-training on topological and texture variations plus domain-aware experts with spatial-guided routing and entropy-controlled allocation to reach 80.1% mIoU on ScanNet and 77.2% mIoU on S3DIS.
-
When Does Sparse MoE Help in Vision? The Role of Backbone Compute Leverage in Sparse Routing
Sparse MoE vision models show positive accuracy gaps only when routing a substantial compute fraction ρ and using k≥2 experts at large scale; batch-axis dispatch is identified as a key failure mode.
-
Mamoda2.5: Enhancing Unified Multimodal Model with DiT-MoE
Mamoda2.5 is a 25B-parameter DiT-MoE unified AR-Diffusion model that reaches top video generation and editing benchmarks with 4-step inference up to 95.9x faster than baselines.