AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Revisiting Computer-Aided Tuberculosis Diagnosis

Yun Liu, Yu-Huan Wu, Shichen Zhang, Li Liu, Min Wu, Ming‐Ming Cheng

TPAMI 2023 · Detection and segmentation › Open-set and few-shot detection · approach: Industrial anomaly detection · 51 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 SymFormer to RetinaNetRetinaNet · TBX11K test, all CXR imagesAP50 bb (%): 52.1 -> 68.0Improved
add SymFormer to Deformable DETRDeformable DETR · TBX11K test, all CXR imagesAP50 bb (%): 51.7 -> 57.0Improved
add SymFormer to RetinaNetRetinaNet · TBX11K test (CXR classification)accuracy (%): 87.4 -> 94.5Improved
add SymFormer to Deformable DETRDeformable DETR · DA+DB test (no fine-tuning)accuracy (%): 68.6 -> 82.4Improved
add SymFormer to RetinaNetRetinaNet · MC+Shenzhen test (no fine-tuning)accuracy (%): 49.3 -> 82.8Improved
use RetinaNet instead of Deformable DETR as the SymFormer baseSymFormer · TBX11K test, all CXR imagesAP50 bb (%): 57.0 -> 68.0Improved
use P2T-Small backbone instead of ResNet-50SymFormer w/ RetinaNet · TBX11K test (CXR classification)accuracy (%): 94.5 -> 94.6; FPS 24.3 -> 17.9No clear effect
add symmetric search attention to SPE (vs vanilla attention) (ablation)SymFormer w/ RetinaNet · TBX11K val, TB imagesAP50 bb (%): 75.7 -> 76.6Improved
add symmetric positional encoding instead of APE under SymAttention (ablation)SymFormer w/ RetinaNet · TBX11K val, TB imagesAP50 bb (%): 74.9 -> 76.6Improved
add STN to SPE (ablation)SymFormer w/ RetinaNet · TBX11K val, TB imagesAP50 bb (%): 75.5 -> 76.6Improved
transfer positional encoding right to left instead of left to right (ablation)SymFormer w/ RetinaNet · TBX11K val, TB imagesAP50 bb (%): 76.3 -> 76.6Improved
add vanilla attention with RPE (ablation)Detector without attention · TBX11K val, TB imagesAP50 bb (%): 72.7 -> 72.7No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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