ExPLoRe: Expert Patch-Level Loss Routing for Multi-Objective Masked Image Modeling

arXiv:2606.31201 · cs.CV · Submitted 2026-06-30 · Read on arXiv

cs.CV

Submitted: 2026-06-30

Updated: 2026-06-30

Code: https://github.com/aicip/ExPLoRe

Terminology

• Distillation — 25× in this paper · explained in 2 episodes
• Regularization — 21× in this paper · explained in 3 episodes
• Ablation — 17× in this paper · explained in 1 episode
• Linear probe — 15× in this paper · explained in 2 episodes
• Adaptation — 13× in this paper · explained in 1 episode
• Accuracy — 11× in this paper · explained in 1 episode
• Alignment — 9× in this paper · explained in 1 episode
• Freeze Routing — 8× in this paper
• Core — 7× in this paper · explained in 2 episodes
• Freeze Attention — 7× in this paper
• Mixture of Experts — 7× in this paper · explained in 2 episodes
• Embeddings — 6× in this paper · explained in 2 episodes
• Transformer — 6× in this paper · explained in 2 episodes
• Self-Distillation — 5× in this paper · explained in 7 episodes
• Soft Mixture of Experts — 5× in this paper
• Robustness — 4× in this paper · explained in 5 episodes
• Degeneracy — 3× in this paper · explained in 3 episodes
• International Conference on Learning Representations — 3× in this paper
• Self-Supervised Learning — 3× in this paper · explained in 8 episodes
• Adaptive Weighting — 2× in this paper · explained in 1 episode
• Aggregation — 2× in this paper · explained in 1 episode
• Cosine Similarity — 2× in this paper · explained in 3 episodes
• Downstream Tasks — 2× in this paper · explained in 2 episodes
• Mixture of Experts (MoE) — 2× in this paper · explained in 5 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Contrastive Learning — 1× in this paper · explained in 5 episodes
• Feature Extraction — 1× in this paper · explained in 2 episodes
• Gradient Flow — 1× in this paper · explained in 2 episodes
• Knowledge Distillation — 1× in this paper · explained in 11 episodes
• Linear Probing — 1× in this paper · explained in 2 episodes
• Multi-objective Optimization — 1× in this paper · explained in 4 episodes
• Redundancy — 1× in this paper · explained in 2 episodes
• Representation Learning — 1× in this paper · explained in 2 episodes
• Sparsity — 1× in this paper · explained in 4 episodes
• Under Efficient Probing — 1× in this paper

Sources

• ViMoE: An Empirical Study of Designing Vision Mixture-of-Experts
• MILAN: Masked Image Pretraining on Language Assisted Representation
• Reasonable Effectiveness of Random Weighting: A Litmus Test for Multi-Task Learning
• BEiT v2: Masked Image Modeling with Vector-Quantized Visual Tokenizers
• A Unified View of Masked Image Modeling
• MVP: Multimodality-guided Visual Pre-training
• Astrea: A MOE-based Visual Understanding Model with Progressive Alignment
• CAE v2: Context Autoencoder with CLIP Target
• ST-MoE: Designing Stable and Transferable Sparse Expert Models

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models