Paper Detail

LoCA: Spatially-Aware Low-Rank Convolutional Adaptation of Vision Foundation Models

Sojung An, Junha Lee, Sujeong You, Nam Ik Cho, Donghyun Kim

Browse

Workflow Queues

arxiv Score 23.5

Published 2026-07-08 · First seen 2026-07-10

Research Track A · General AI

Open paper source

Abstract

Pre-trained Vision Foundation Models (VFMs) provide strong visual representations for diverse downstream tasks. The key challenge of VFM adaptation stems from the prohibitive costs of full fine-tuning and catastrophic forgetting. To address this, Low-Rank Adaptation (LoRA) has emerged as the prevailing paradigm for Parameter-Efficient Fine-Tuning (PEFT). However, LoRA is typically designed for transformer self-attention layers parameterized by 2D matrices. Since convolutional kernels inherently couple spatial and channel information within a 4D tensor, forcing them into a monolithic 2D matrix disrupts the inherent spatial topology. In this paper, we propose Low-Rank Convolutional Adaptation (LoCA), a convolution-aware PEFT framework that addresses spatial-channel entanglement by decoupling channel and spatial adaptation. LoCA introduces a low-rank channel adaptation for dense cross-channel mixing and refines spatial bases extracted from pre-trained kernels via Singular Value Decomposition (SVD). Experimental results show that LoCA preserves pre-trained spatial priors and achieves competitive or state-of-the-art performance across fine-grained classification, domain-generalized semantic segmentation, and generative benchmarks.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
now
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

Similar Papers

Janus-LoRA: A Balanced Low-Rank Adaptation for Continual Learning 2026-05-27 · Score 22.0 Research Track A · General AI On Token's Dilemma: Dynamic MoE with Drift-Aware Token Assignment for Continual Learning of Large Vision Language Models 2026-03-29 · Score 15.5 Research Track A · General AI Pruned Adaptation Modules: A Simple yet Strong Baseline for Continual Foundation Models 2026-03-22 · Score 14.0 Research Track A · General AI Null-Space Constrained Low-Rank Adaptation for Response-Specified Large Language Model Unlearning 2026-06-09 · Score 15.5 Research Track A · General AI How Robust is OCR-Reasoning? Evaluating OCR-Reasoning Robustness of Vision-Language Models under Visual Perturbations 2026-06-24 · Score 11.3 Research Track A · General AI

BibTeX

@article{an2026loca,
  title = {LoCA: Spatially-Aware Low-Rank Convolutional Adaptation of Vision Foundation Models},
  author = {Sojung An and Junha Lee and Sujeong You and Nam Ik Cho and Donghyun Kim},
  year = {2026},
  abstract = {Pre-trained Vision Foundation Models (VFMs) provide strong visual representations for diverse downstream tasks. The key challenge of VFM adaptation stems from the prohibitive costs of full fine-tuning and catastrophic forgetting. To address this, Low-Rank Adaptation (LoRA) has emerged as the prevailing paradigm for Parameter-Efficient Fine-Tuning (PEFT). However, LoRA is typically designed for transformer self-attention layers parameterized by 2D matrices. Since convolutional kernels inherently },
  url = {https://arxiv.org/abs/2607.06918},
  keywords = {cs.CV, cs.AI, cs.LG},
  eprint = {2607.06918},
  archiveprefix = {arXiv},
}

Metadata

{}