SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.02352 · CVPR · 2024

Region-Based Representations Revisited

Yu-Xiong Wang, Jae Lee, Ansel Blume, Derek Hoiem, Yao Xiao, Heyi Tao, Michal Shlapentokh-Rothman, Yuqun Wu, Wilfredo Torres

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

We investigate whether region-based representations are effective for recognition. Regions were once a mainstay in recognition approaches, but pixel and patch-based features are now used almost exclusively. We show that recent class-agnostic segmenters like SAM can be effectively combined with strong self-supervised representations, like those from DINOv2, and used for a wide variety of tasks, including semantic segmentation, object-based image retrieval, and multi-image analysis. Once the masks and features are extracted, these representations, even with linear decoders, enable competitive performance, making them well suited to applications that require custom queries. The representations' compactness also makes them well-suited to video analysis and other problems requiring inference across many images.

For agents

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

get_harvested_code_for_paper("2402.02352")
get_code_for_paper("2402.02352")
have("2402.02352")

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

curl https://syntology.ai/api/ran/2402.02352.json

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

[![Syntology run record](https://syntology.ai/api/ran/2402.02352.svg)](https://syntology.ai/paper/2402.02352)

Connect an agent — have() is free.