AI Paper Atlas

Research map / Detection and segmentation / CNN features

DeepProposals: Hunting Objects and Actions by Cascading Deep Convolutional Layers

Amir Ghodrati, Ali Diba, Marco Pedersoli, Tinne Tuytelaars, Luc Van Gool

IJCV 2017 · Detection and segmentation › CNN features · approach: Region-based and query-based detectors · 21 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 a 2x2 spatial pyramid to average-pooled window features (ablation)single-layer sliding window proposals · PASCAL VOC 2007 recallrecall: gain between 2 and 4 percent in recallImproved
use 4x4 instead of 2x2 pyramid (ablation)window representation · PASCAL VOC 2007 recallrecall vs cost: 5 times slower for 2x2 vs 21 times slower for 4x4Mixed
add stage 2 re-scoring on layer 3 with a 2x2 pyramid after layer 5 stage (ablation)DeepProposals cascade · PASCAL VOC 2007 recallrecall: improves the recall of the cascade by 5%Improved
add layer 4 to the cascade (ablation)DeepProposals cascade · PASCAL VOC 2007 Recall@1000recall: 79% -> 79%No clear effect
use layer 2 instead of layer 1 for contour refinement (ablation)stage 3 contour detector · BSDSAP: 0.61 -> 0.72Improved
add stage 3 local refinement on layer 2 contours (ablation)DeepProposals cascade · PASCAL VOC 2007 high IoUrecallImproved
use layer 3 features instead of layer 5 (ablation)single-layer sliding window · PASCAL VOC 2007 IoU 0.5 recall@1000recall: 88% -> 92%Improved
use layer 1 instead of layer 3 (ablation)single-layer sliding window · PASCAL VOC 2007 IoU 0.5 recall@1000recall: 92% -> 73%Hurt
increase number of window sizes (ablation)sliding window proposals · PASCAL VOC 2007recall and costMixed
increase windows per frame from 100 to 300 for action tubes (ablation)action proposals · UCF-Sportsrecall and Viterbi time: 1.3 and 12.1 seconds for N=100 and N=300Mixed
train proposal classifier on only 5 COCO classes instead of more classes (ablation)DeepProposals · COCO recall at IoU 0.5, 1000 proposalsrecall: 56% vs 59%-60%Hurt
use DeepProposals instead of selective search proposals in detector with few proposalsFaster-RCNN detector · VOC 2007 test, 50 proposalsmAP: 28.1 -> superior to 50Improved

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