SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2409.15889 · 2024

CAD: Memory Efficient Convolutional Adapter for Segment Anything

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

The Foundation model for image segmentation, Segment Anything (SAM), has been actively researched in various fields since its proposal. Various researches have been proposed to adapt SAM to specific domains, with one notable approach involving the addition and training of lightweight adapter modules. While adapter-based fine-tuning approaches have reported parameter efficiency and significant performance improvements, they face a often overlooked issue: the excessive consumption of GPU memory relative to the number of trainable parameters. Addressing this issue, this paper proposes a memory-efficient parallel convolutional adapter architecture. This architecture connects in parallel with SAM's image encoder, eliminating the need to store activations and gradients of the image encoder during model training. Our proposed architecture demonstrated competitive experimental results while using less than half the GPU memory compared to SAM Adapter, indicating its value as an alternative to simple decoder fine-tuning when hardware limitations preclude adapter-based learning. Our code implementation is available at our github.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2409.15889")
get_code_for_paper("2409.15889")
have("2409.15889")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2409.15889.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2409.15889.svg)](https://syntology.ai/paper/2409.15889)

Connect an agent — have() is free.