# CRAFT Objects from Images

Source: [CRAFT Objects from Images](<https://www.sota2.com/research/paper/68fa62681e209131ce9f9358>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T20:19:32.265Z

Authors: Bin Yang, Junjie Yan, Zhen Lei, Stan Z. Li

Published: 2016-04-12T03:57:48.000Z

## Abstract

Object detection is a fundamental problem in image understanding. One popular solution is the R-CNN framework and its fast versions. They decompose the object detection problem into two cascaded easier tasks: 1) generating object proposals from images, 2) classifying proposals into various object categories. Despite that we are handling with two relatively easier tasks, they are not solved perfectly and there's still room for improvement. In this paper, we push the "divide and conquer" solution even further by dividing each task into two sub-tasks. We call the proposed method "CRAFT" (Cascade Region-proposal-network And FasT-rcnn), which tackles each task with a carefully designed network cascade. We show that the cascade structure helps in both tasks: in proposal generation, it provides more compact and better localized object proposals; in object classification, it reduces false positives (mainly between ambiguous categories) by capturing both inter- and intra-category variances. CRAFT achieves consistent and considerable improvement over the state-of-the-art on object detection benchmarks like PASCAL VOC 07/12 and ILSVRC.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1604.03239>)

[PDF](<https://arxiv.org/pdf/1604.03239.pdf>)
