點擊上方「CVer」，選擇"星標"和「置頂」
重磅乾貨，第一時間送達
前戲最近出了很多論文，各種SOTA。比如（點擊可訪問）：
今天頭條推送的是目前人臉檢測方向的SOTA論文：改進SRN人臉檢測算法。本文要介紹的是目前(2019-01-26) one-stage目標檢測中最強算法：ExtremeNet。
正文《Bottom-up Object Detection by Grouping Extreme and Center Points》
arXiv: https://arxiv.org/abs/1901.08043
github: https://github.com/xingyizhou/ExtremeNet
作者團隊：UT Austin
註：2019年01月23日剛出爐的paper
Abstract：With the advent of deep learning, object detection drifted from a bottom-up to a top-down recognition problem. State of the art algorithms enumerate a near-exhaustive list of object locations and classify each into: object or not. In this paper, we show that bottom-up approaches still perform competitively. We detect four extreme points (top-most, left-most, bottom-most, right-most) and one center point of objects using a standard keypoint estimation network. We group the five keypoints into a bounding box if they are geometrically aligned. Object detection is then a purely appearance-based keypoint estimation problem, without region classification or implicit feature learning. The proposed method performs on-par with the state-of-the-art region based detection methods, with a bounding box AP of 43.2% on COCO test-dev. In addition, our estimated extreme points directly span a coarse octagonal mask, with a COCO Mask AP of 18.9%, much better than the Mask AP of vanilla bounding boxes. Extreme point guided segmentation further improves this to 34.6% Mask AP.
Illustration of our object detection method
Illustration of our framework
Illustration of our object detection method
基礎工作
創新點
實驗結果
ExtremeNet有多強，看下面的圖示就知道了，在COCO test-dev數據集上，mAP為43.2，在one-stage detector中，排名第一。可惜的是沒有給出時間上的對比，論文中只介紹說測試一幅圖像，耗時322ms（3.1 FPS）。
State-of-the-art comparison on COCO test-dev
想要了解最新最快最好的論文速遞、開源項目和乾貨資料，歡迎加入CVer學術交流群。涉及圖像分類、目標檢測、圖像分割、人臉檢測&識別、目標跟蹤、GANs、學術競賽交流、Re-ID、風格遷移、醫學影像分析、姿態估計、OCR、SLAM、場景文字檢測&識別和超解析度等方向。
掃碼進群
這麼硬的論文速遞，麻煩給我一個好看
▲長按關注我們
麻煩給我一個好看！