AI Paper Atlas

Research map / Detection and segmentation / CNN features

DeNet: Scalable Real-Time Object Detection With Directed Sparse Sampling

Lachlan Tychsen-Smith, Lars Petersson

ICCV 2017 · Detection and segmentation › CNN features · approach: Region-based and query-based detectors · 129 citations (OpenAlex)

Read the paper

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
raise corner loss weight lambda_t from 1 to 100 (ablation)DeNet-34 · Pascal VOC 2007 valmAP (%): 49.6 -> 72.8Improved
raise lambda_t further from 100 to 500 (ablation)DeNet-34 · Pascal VOC 2007 valmAP (%): 72.8 -> 70.6Hurt
raise bbox regression weight lambda_b from 1 to 10 at lambda_t=100 (ablation)DeNet-34 · Pascal VOC 2007 valmAP (%): 72.8 -> 72.1Hurt
add skip layers (ablation)DeNet-34 · MSCOCO test-dev2015AP@IoU=0.5:0.95 (%): 29.4 -> 29.5Improved
add skip layers (ablation)DeNet-34 · MSCOCO test-dev2015AP@0.5 (%): 46.2 -> 47.9Improved
add skip layers (ablation)DeNet-101 · MSCOCO test-dev2015AP@IoU=0.5:0.95 (%): 31.9 -> 32.3Improved
use wide variant (128x128 corner maps, N=48) on top of skip (ablation)DeNet-34 · MSCOCO test-dev2015AP@IoU=0.5:0.95 (%): 29.5 -> 30.0Improved
use wide variant on top of skip (ablation)DeNet-101 · MSCOCO test-dev2015AP@IoU=0.5:0.95 (%): 32.3 -> 33.8Improved
use wide variant on top of skip (evaluation rate cost) (ablation)DeNet-101 · MSCOCO test-dev2015evaluation rate (Hz): 33 Hz -> 17 HzHurt
add skip layers (ablation)DeNet-34 · Pascal VOC 2007 testmAP (%): 75.3% -> 75.9%Improved
add skip layers (ablation)DeNet-101 · Pascal VOC 2007 testmAP (%): 77.0% -> 77.1%No clear effect
increase training/testing sample boxes from 64 to 1024 (ablation)DeNet-34 · Pascal VOC 2007coverage (%) and eval rate (Hz): coverage 81 -> 97, rate 96 Hz -> 55 HzMixed

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