AI Paper Atlas

Research map / Label-efficient and robust learning / Knowledge distillation

Deep Structured Instance Graph for Distilling Object Detectors

Yixin Chen, Pengguang Chen, Shu Liu, Liwei Wang, Jiaya Jia

ICCV 2021 · Label-efficient and robust learning › Knowledge distillation · approach: Knowledge distillation for detectors · 15 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 edge (pairwise relation) distillation to the student (ablation)Faster R-CNN R18 student · COCO val2017 Faster R-CNN R18-R50 ablation (1x)Box AP: 33.06 -> 33.95Improved
add foreground node distillation on top of edges (ablation)Faster R-CNN R18 student · COCO val2017 Faster R-CNN R18-R50 ablation (1x)Box AP: 33.95 -> 36.64Improved
add background nodes with adaptive loss weight (ablation)Faster R-CNN R18 student · COCO val2017 Faster R-CNN R18-R50 ablation (1x)Box AP: 36.64 -> 37.17Improved
distill the structured instance graph (1x), R18 student from R50 teacherFaster R-CNN · COCO val2017 Faster R-CNN (1x)Box AP: 33.06 -> 37.25Improved
distill the structured instance graph (1x), R50 student from R101 teacherFaster R-CNN · COCO val2017 Faster R-CNN (1x)Box AP: 38.03 -> 40.57Improved
distill the structured instance graph (1x), R101 student from R152 teacherFaster R-CNN · COCO val2017 Faster R-CNN (1x)Box AP: 40.27 -> 41.65Improved
distill the graph into a heterogeneous MobileNetV2 student from R50 teacherFaster R-CNN · COCO val2017 Faster R-CNN (1x)Box AP: 29.47 -> 34.44Improved
distill the graph into RetinaNet R18 studentRetinaNet · COCO val2017 RetinaNet (1x)Box AP: 31.60 -> 34.72Improved
train distilled R18 student for 3x instead of 1x scheduleFaster R-CNN R18 student · COCO val2017 Faster R-CNNBox AP: 37.25 -> 38.68Improved
graph distillation vs pixel-wise pairwise distillation (R18-R50)Mask R-CNN R18 student · COCO val2017 Mask R-CNN R18-R50 (1x)Mask AP: 30.43 -> 33.90Improved
graph distillation vs AttentionGuided at 2x (R50-R101)Faster R-CNN R50 student · COCO val2017 Faster R-CNN R50-R101 (Table 4 comparison, 2x)Box AP: 41.50 -> 41.55No clear effect
graph distillation vs AttentionGuided at 2x (R18-R50)Faster R-CNN R18 student · COCO val2017 Faster R-CNN R18-R50 (Table 4 comparison, 2x)Box AP: 37.00 -> 38.09Improved

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