Semi-DETR: Semi-Supervised Object Detection with Detection Transformers

by   Jiacheng Zhang, et al.
Baidu, Inc.

We analyze the DETR-based framework on semi-supervised object detection (SSOD) and observe that (1) the one-to-one assignment strategy generates incorrect matching when the pseudo ground-truth bounding box is inaccurate, leading to training inefficiency; (2) DETR-based detectors lack deterministic correspondence between the input query and its prediction output, which hinders the applicability of the consistency-based regularization widely used in current SSOD methods. We present Semi-DETR, the first transformer-based end-to-end semi-supervised object detector, to tackle these problems. Specifically, we propose a Stage-wise Hybrid Matching strategy that combines the one-to-many assignment and one-to-one assignment strategies to improve the training efficiency of the first stage and thus provide high-quality pseudo labels for the training of the second stage. Besides, we introduce a Crossview Query Consistency method to learn the semantic feature invariance of object queries from different views while avoiding the need to find deterministic query correspondence. Furthermore, we propose a Cost-based Pseudo Label Mining module to dynamically mine more pseudo boxes based on the matching cost of pseudo ground truth bounding boxes for consistency training. Extensive experiments on all SSOD settings of both COCO and Pascal VOC benchmark datasets show that our Semi-DETR method outperforms all state-of-the-art methods by clear margins. The PaddlePaddle version code1 is at


page 4

page 6

page 12

page 17

page 19

page 20


Ambiguity-Resistant Semi-Supervised Learning for Dense Object Detection

With basic Semi-Supervised Object Detection (SSOD) techniques, one-stage...

Mind the Gap: Polishing Pseudo labels for Accurate Semi-supervised Object Detection

Exploiting pseudo labels (e.g., categories and bounding boxes) of unanno...

Revisiting Class Imbalance for End-to-end Semi-Supervised Object Detection

Semi-supervised object detection (SSOD) has made significant progress wi...

Towards End-to-end Semi-supervised Learning for One-stage Object Detection

Semi-supervised object detection (SSOD) is a research hot spot in comput...

Label, Verify, Correct: A Simple Few Shot Object Detection Method

The objective of this paper is few-shot object detection (FSOD) – the ta...

Cascade-DETR: Delving into High-Quality Universal Object Detection

Object localization in general environments is a fundamental part of vis...

NOTE-RCNN: NOise Tolerant Ensemble RCNN for Semi-Supervised Object Detection

The labeling cost of large number of bounding boxes is one of the main c...

Please sign up or login with your details

Forgot password? Click here to reset