AI Paper Atlas

Research map / Detection and segmentation / CNN features

Adaptive Feeding: Achieving Fast and Accurate Detections by Adaptively Combining Object Detectors

Hong-Yu Zhou, Bin-Bin Gao, Jianxin Wu

ICCV 2017 · Detection and segmentation › CNN features · approach: Region-based and query-based detectors · 38 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
use proposal-based AF features instead of raw VGG-16 image classification (ablation)SSD300+SSD500 AF · VOC07 testmAP: 72.5 -> 75.0Improved
use class histogram (20) instead of per-proposal class probabilities (20-prob) (ablation)SSD300+SSD500 AF · VOC07 testmAP: 74.4 -> 75.0Improved
add bounding box size (4s) features to class histogram and confidence (ablation)SSD300+SSD500 AF · VOC07 testmAP: 74.3 -> 75.0Improved
use box size and position (4s) rather than corner coordinates (4c) (ablation)SSD300+SSD500 AF · VOC07 testmAP: 74.5 -> 75.0Improved
raise number of proposals K from 10 to 25 (ablation)SSD300+SSD500 AF · VOC07 testmAP: 74.7 -> 75.0Improved
use K=25 instead of K=50 proposals (ablation)SSD300+SSD500 AF · VOC07 testmAP: 74.8 -> 75.0Improved
lower hard-image sampling weight from 5.13 to 3 (fast mode) (ablation)SSD300+SSD500 AF · VOC07 testmAP and FPS: 75.0 -> 74.4 mAP, 27 -> 33 FPSMixed
lower hard-image sampling weight from 8.43 to 5 (fast mode) (ablation)SSD300+R-FCN AF · VOC07 testmAP and FPS: 78.3 -> 76.9 mAP, 17 -> 24 FPSMixed
adaptively combine SSD300 with SSD500 (accurate mode) instead of SSD300 alone300-500-A · VOC12 testmAP: 68.9 -> 71.1Improved
adaptively combine SSD300 with R-FCN (accurate mode) instead of SSD300 alone300-R-FCN-A · MS COCO test-devAP: 20.8 -> 27.0Improved
adaptively combine SSD300 with SSD500 instead of simple ensembleSSD300+SSD500 AF · VOC07 testmAP: 73.0 -> 75.0Improved
accurate-mode AF with R-FCN partner instead of R-FCN alone (speed-up at accuracy cost)300-R-FCN-A · VOC07 testmAP and FPS: 79.0 -> 78.3 mAP, 8 -> 17 FPSMixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 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