AI Paper Atlas

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

SparseDet: Improving Sparsely Annotated Object Detection with Pseudo-positive Mining

Saksham Suri, Saketh Rambhatla, Rama Chellappa, Abhinav Shrivastava

ICCV 2023 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Pseudo-labeling for semi-supervised detection · 26 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

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 pseudo-positive mining with self-supervised consistency loss instead of pseudo-labels aloneSparseDet · COCO Split-1 70% removedAP: 24.93 -> 32.68Improved
add common RPN (C-RPN) over two views (ablation)SparseDet · VOC07 Split-5 50%AP: 42.67 -> 45.30Improved
add PPM on top of C-RPN without SSL loss (ablation)SparseDet · VOC07 Split-5 50%AP: 45.30 -> 45.44No clear effect
add SSL consistency loss together with PPM (ablation)SparseDet · VOC07 Split-5 50%AP: 45.44 -> 46.00Improved
add pseudo-labeling loss to SSL-based method (ablation)SparseDet · VOC07 Split-5 50%AP: 45.51 -> 46.00Improved
use single set of proposals from original image instead of C-RPN (ablation)SparseDet · VOC07 Split-5 50%AP: 46.00 -> 44.86Hurt
combine two separate proposal sets instead of C-RPN (ablation)SparseDet · VOC07 Split-5 50%AP: 46.00 -> 45.25Hurt
raise PPM objectness threshold to 0.95 (ablation)SparseDet · VOC07 Split-5 50%AP: 46.00 -> 45.30Hurt
use augmented view at inference (ablation)SparseDet · COCO Splits 1-3AP: 38.32 -> 38.22 (Split-1 30%)No clear effect
use FPN instead of C4 backbone (ablation)SparseDet · COCO Splits 1-3AP: 37.67 -> 38.22 (Split-1 30%); 33.16 -> 32.68 (Split-1 70%)Mixed
start PPM after warm-up of 9000 iterations instead of 0 (ablation)SparseDet · COCO-mini ablationAP: 45.51 -> 46.00Improved
add bounding box erase augmentation alone (ablation)SparseDet · VOC07 Split-5 50%AP: 42.76 -> 45.11Improved

Later papers that compared with this method

4 later accepted papers report SparseDet as a baseline in their results tables; 4 of them report a better number on most of the results they share with it.

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