The Devil is in the Spectrum Bias: Spectrum-Balanced Feature Matching for Robust Representation Distillation

arXiv:2609.34106 · cs.CV, cs.AI · Submitted 2026-09-28 · Read on arXiv

cs.CV, cs.AI

Submitted: 2026-09-28

Updated: 2026-09-28

Terminology

• Feature Matching — 52× in this paper
• Distillation — 39× in this paper · explained in 2 episodes
• Reconstruction Error — 27× in this paper · explained in 2 episodes
• Core — 15× in this paper · explained in 2 episodes
• Downstream Tasks — 14× in this paper · explained in 2 episodes
• Knowledge Distillation — 12× in this paper · explained in 11 episodes
• Benchmark — 9× in this paper · explained in 2 episodes
• Foundation Model — 8× in this paper · explained in 3 episodes
• Generalization — 8× in this paper · explained in 13 episodes
• Accuracy — 7× in this paper · explained in 1 episode
• Foundation Models — 6× in this paper · explained in 7 episodes
• Adaptation — 4× in this paper · explained in 1 episode
• Linear probe — 4× in this paper · explained in 2 episodes
• Computational overhead — 3× in this paper · explained in 2 episodes
• Linear Probing — 3× in this paper · explained in 2 episodes
• Robustness — 3× in this paper · explained in 5 episodes
• Self-Supervised Learning — 3× in this paper · explained in 8 episodes
• AUROC — 2× in this paper · explained in 2 episodes
• Dynamic Weighting — 2× in this paper · explained in 3 episodes
• Embeddings — 2× in this paper · explained in 2 episodes
• Fine-Tuning — 2× in this paper · explained in 5 episodes
• Generative AI — 2× in this paper · explained in 2 episodes
• Ontology — 2× in this paper · explained in 2 episodes
• Transferability — 2× in this paper · explained in 4 episodes
• Adam — 1× in this paper · explained in 2 episodes
• Aggregation — 1× in this paper · explained in 1 episode
• Consistency — 1× in this paper · explained in 3 episodes
• Redundancy — 1× in this paper · explained in 2 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• Representation Learning — 1× in this paper · explained in 2 episodes
• Self-Supervised Learning (SSL) — 1× in this paper · explained in 4 episodes
• Transformer — 1× in this paper · explained in 2 episodes
• Vision-language models — 1× in this paper · explained in 2 episodes

Sources

• PFMBench: Protein Foundation Model Benchmark
• Distilling the Knowledge in a Neural Network
• Understanding Dimensional Collapse in Contrastive Self-supervised Learning
• Fine-Grained Visual Classification of Aircraft
• DINOv2: Learning Robust Visual Features without Supervision
• PHI-S: Distribution Balancing for Label-Free Multi-Teacher Distillation
• FitNets: Hints for Thin Deep Nets
• DINOv3

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