REVIEW 6 cited by
Convolution Meets LoRA: Parameter Efficient Finetuning for Segment Anything Model
Not yet reviewed by Pith; the record is open.
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
Convolution Meets LoRA: Parameter Efficient Finetuning for Segment Anything Model
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.
Forward citations
Cited by 6 Pith papers
-
Affordance2Action: Task-Conditioned Scene-level Affordance Grounding for Real-Time Manipulation
Affordance2Action introduces A2A-Bench, a manipulation-oriented benchmark for scene-level task-conditioned affordance grounding covering single- and multi-region correspondences, plus an annotation pipeline, and repor...
-
Reclaiming Residual Knowledge: A Novel Paradigm to Low-Bit Quantization
CoRa reclaims quantization residuals in pre-trained ConvNets by searching low-rank adapter architectures instead of weights, matching SOTA accuracy on ImageNet in 3-4 bit settings with under 250 iterations on 1600 images.
-
CLIP-Guided SAM: Parameter-Efficient Semantic Conditioning for Promptable Segmentation
CLIP-Guided SAM injects CLIP-derived features into SAM via lightweight adapters for semantic conditioning, supporting text and spatial prompts while remaining parameter-efficient and achieving competitive performance.
-
M$^4$-SAM: Multi-Modal Mixture-of-Experts with Memory-Augmented SAM for RGB-D Video Salient Object Detection
M⁴-SAM equips SAM2 with modality-aware MoE-LoRA, gated multi-level fusion, and pseudo-guided initialization to reach state-of-the-art on RGB-D video salient object detection.
-
Generalized SAM: Efficient Fine-Tuning of SAM for Variable Input Image Sizes
GSAM applies random cropping to enable variable input sizes for efficient SAM fine-tuning, claiming lower compute with comparable or higher accuracy on varied datasets.
-
Dante: An Open Source Model Pre-Training and Fine-Tuning Tool for the Dafne Federated Framework for Medical Image Segmentation
Dante is a new open-source backend for the Dafne ecosystem that implements configurable training from scratch, layer freezing, and channel-wise LoRA for medical image segmentation, with validation showing faster conve...
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.