寫在前面
- 文章出處： ECCV 2022
- 模型名字： Detic
- 整體概括：這篇文章跟最開始的OVD-Net一樣，都是從pretraining的角度解決open vocabulary的問題桑阶，但是這篇文章的思路更加簡單粗暴柏副，直接加入imagenet的類別作為訓練。本質上不是真正的open vocabulary蚣录，但是能夠囊括2000類別割择；
1. Introduction：
OD has two subtasks: 1) finding boxes (localization); 2) naming the boxes (classification)
Previous works couple these two subtasks;
however, the detection benchmarks are much smaller than the classification benchmark；
as in the fig, both the image number and the category number of LVIS (OD) are much smaller than ImageNet (CLS).
This paper:
propose a detector with image classes (Detic) that uses image-level supervision in addition to detection supervision.
decouple the localization and classification sub-problems;
use image-level labels to train the classifier and broaden the vocabulary of the detector;
illustration:
standard OD: need gt boxes and labels;
weakly supervised od: assign image-level labels to predicted boxes [error-prone]
this paper: assigns image-level labels to the max-size proposals.
2 Method
2.1 preliminary
detection dataset
, with class set
image classification dataset
, with class set
testing dataset with class set
.
,
, and
tradional OD: C_{det}
D_{cls} = \phi $
OVD: allows
2.2 Detic
the whole idea is quite simple.
- use both the detection dataset
sample a batch from both
if image belongs to
if image belongs to
