AI Paper Atlas

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

IDa-Det: An Information Discrepancy-Aware Distillation for 1-Bit Detectors

Sheng Xu, Yanjing Li, Bohan Zeng, Teli Ma, Baochang Zhang, Xianbin Cao, Peng Gao, Jinhu Lü

ECCV 2022 · Label-efficient and robust learning › Knowledge distillation · approach: Knowledge distillation for detectors · 19 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 IDa proposal selection (with entropy loss) over Hint (ablation)1-bit BiRes18 Faster-RCNN · PASCAL VOC test2007 (component ablation)mAP (%): 74.5 -> 76.9Improved
add IDa proposal selection over FGFI (ablation)1-bit BiRes18 Faster-RCNN · PASCAL VOC test2007 (component ablation)mAP (%): 75.0 -> 76.9Improved
add IDa distillation vs no distillation (ablation)1-bit BiRes18 Faster-RCNN · PASCAL VOC test2007 (component ablation)mAP (%): 74.0 -> 76.9Improved
use entropy loss instead of L2 with IDa (ablation)1-bit BiRes18 Faster-RCNN · PASCAL VOC test2007 (component ablation)mAP (%): 76.5 -> 76.9Improved
use entropy loss instead of L2 with Hint (ablation)1-bit BiRes18 Faster-RCNN · PASCAL VOC test2007 (component ablation)mAP (%): 74.1 -> 74.5Improved
use entropy loss instead of L2 with FGFI (ablation)1-bit BiRes18 Faster-RCNN · PASCAL VOC test2007 (component ablation)mAP (%): 74.7 -> 75.0Improved
use entropy loss instead of inner-product with IDa (ablation)1-bit BiRes18 Faster-RCNN · PASCAL VOC test2007 (component ablation)mAP (%): 74.8 -> 76.9Improved
use entropy loss instead of cosine similarity with IDa (ablation)1-bit BiRes18 Faster-RCNN · PASCAL VOC test2007 (component ablation)mAP (%): 76.4 -> 76.9Improved
add IDa-Det distillation to 1-bit Faster-RCNN ResNet-181-bit Faster-RCNN ResNet-18 · COCO minivalmAP@[.5,.95] (%): 26.8 -> 29.3Improved
add IDa-Det distillation to 1-bit SSD VGG-161-bit SSD VGG-16 · PASCAL VOC test2007mAP (%): 69.5 -> 72.5Improved
IDa-Det instead of LWS-Det on 1-bit Faster-RCNN ResNet-181-bit Faster-RCNN ResNet-18 · PASCAL VOC test2007mAP (%): 73.2 -> 76.9Improved
1-bit IDa-Det student versus real-valued Faster-RCNN ResNet-181-bit Faster-RCNN ResNet-18 · PASCAL VOC test2007mAP (%): 76.4 -> 76.9Improved

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