AI Paper Atlas

Research map / Detection and segmentation / Weakly supervised detection and segmentation

Diverse Learner: Exploring Diverse Supervision for Semi-Supervised Object Detection

Linfeng Li, Minyue Jiang, Yue Yu, Wei Zhang, Xiangru Lin, Yingying Li, Xiao Tan, Jingdong Wang, Errui Ding

ECCV 2022 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Pseudo-labeling for semi-supervised detection · 5 citations (OpenAlex)

Read the paper

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add multi-threshold classification loss (MTC) (ablation)STAC baseline with box jitter · MS-COCO val (1% labeled)mAP: 20.6 -> 22.1Improved
add pseudo label-aware erasing (PLAE) on top of MTC (ablation)Baseline + MTC · MS-COCO val (1% labeled)mAP: 22.1 -> 22.7Improved
add diverse learner (two cross-supervised teacher-student pairs) on top of MTC and PLAE (ablation)Baseline + MTC + PLAE · MS-COCO val (1% labeled)mAP: 22.7 -> 23.7Improved
add conventional mutual learning instead of DL (ablation)Baseline + MTC + PLAE · MS-COCO val (1% labeled)mAP: 22.7 -> 19.0Hurt
use KL divergence loss rather than ignoring uncertain pseudo labels (ablation)Baseline + PLAE · MS-COCO val (1% labeled)mAP: 21.2 -> 22.7Improved
use KL divergence loss rather than binary cross entropy for uncertain pseudo labels (ablation)Baseline + PLAE · MS-COCO val (1% labeled)mAP: 22.2 -> 22.7Improved
lower the MTC lower threshold from 0.6 to 0.8 (ablation)Diverse Learner · MS-COCO val (1% labeled)mAP: 23.2 -> 23.7Improved
lower threshold 0.7 versus 0.8 (ablation)Diverse Learner · MS-COCO val (1% labeled)mAP: 23.4 -> 23.7No clear effect
lower threshold 0.8 versus 0.7 without DL (ablation)Ours (w/o DL) · MS-COCO val (1% labeled)mAP: 22.6 -> 23.1 -> 22.7Mixed
add diverse learner to reduce teacher-student parameter similarity (ablation)teacher-student pair · MS-COCO val (1% labeled)layer-wise cosine similarity: 0.9987 -> 0.1498Improved
use Diverse Learner over Soft Teacher with 1% labelsSoft Teacher · MS-COCO val (1% labeled)mAP: 21.62 -> 23.72Improved
use Diverse Learner over Soft Teacher with 5% labelsSoft Teacher · MS-COCO val (5% labeled)mAP: 30.42 -> 31.92Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy