Pith. sign in

REVIEW 4 cited by

Convolution Meets LoRA: Parameter Efficient Finetuning for Segment Anything Model

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2401.17868 v1 pith:HMFLAK6F submitted 2024-01-31 cs.CV cs.LG

Zihan Zhong , Zhiqiang Tang , Tong He , Haoyang Fang , Chun Yuan This is my paper · ORCID
classification cs.CVcs.LG
keywords conv-lorasegmentationanythingdomainsimageloramodelsegment
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

The Segment Anything Model (SAM) stands as a foundational framework for image segmentation. While it exhibits remarkable zero-shot generalization in typical scenarios, its advantage diminishes when applied to specialized domains like medical imagery and remote sensing. To address this limitation, this paper introduces Conv-LoRA, a simple yet effective parameter-efficient fine-tuning approach. By integrating ultra-lightweight convolutional parameters into Low-Rank Adaptation (LoRA), Conv-LoRA can inject image-related inductive biases into the plain ViT encoder, further reinforcing SAM's local prior assumption. Notably, Conv-LoRA not only preserves SAM's extensive segmentation knowledge but also revives its capacity of learning high-level image semantics, which is constrained by SAM's foreground-background segmentation pretraining. Comprehensive experimentation across diverse benchmarks spanning multiple domains underscores Conv-LoRA's superiority in adapting SAM to real-world semantic segmentation tasks.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. OpenAlex reports about 12 citations worldwide. Full citation record

  1. CROSS: Cascaded Distillation and Dual-Constraint Grounding for Remote Sensing Referring Segmentation

    cs.CV 2026-08 conditional novelty 6.0 of 10

    CROSS improves remote sensing referring segmentation by combining cascaded SAM distillation with contrastive learning, reporting state-of-the-art cIoU on RefSegRS and RRSIS-D.

  2. Deep Learning-Based Desikan-Killiany Parcellation of the Brain Using Diffusion MRI

    eess.IV 2025-08 unverdicted novelty 5.0 of 10

    A two-stage deep network parcellates the brain into Desikan-Killiany regions directly from diffusion MRI maps, reportedly beating registration-based methods on two public datasets.

  3. Baltimore Atlas: FreqWeaver Adapter for Semi-supervised Ultra-high Spatial Resolution Land Cover Classification

    cs.CV 2025-06 conditional novelty 5.0 of 10

    A SAM2-based land cover classifier with a frequency-splitting adapter and uncertainty-aware semi-supervised training reports gains on a new 0.3 m Baltimore dataset.

  4. PHLoRA: data-free Post-hoc Low-Rank Adapter extraction from full-rank checkpoint

    cs.LG 2025-09 conditional novelty 3.0 of 10

    PHLoRA extracts LoRA-compatible adapters from full-rank fine-tuned models via truncated SVD of the weight delta, matching full-rank performance on several benchmarks with no gradients or training data.

Pith tools