AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Hierarchical Shot Detector

Jiale Cao, Yanwei Pang, Jungong Han, Xuelong Li

ICCV 2019 · Detection and segmentation › Open-set and few-shot detection · approach: Few-shot object detection · 85 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
replace simultaneous cls/reg with one ROC module (regress, offset, classify) (ablation)SSD-like baseline · COCO minivalAP: 27.8 -> 30.3Improved
stack a second ROC module (ablation)HSD one ROC · COCO minivalAP: 30.3 -> 32.6Improved
add feature enhanced (FE) module between ROCs (ablation)HSD two ROCs · COCO minivalAP: 32.6 -> 33.3Improved
increase input size from 320x320 to 512x512 (ablation)HSD two ROCs + FE · COCO minivalAP: 33.3 -> 38.5Improved
use classification IoU threshold 0.6 instead of 0.5 for regressed boxes (ablation)ROC · COCO minivalAP: 28.0 -> 29.9Improved
use stricter classification IoU threshold 0.8 instead of 0.6 (ablation)ROC · COCO minivalAP: 29.9 -> 28.2Hurt
use IoU threshold 0.4 or 0.6 for baseline instead of 0.5 (ablation)SSD-like baseline · COCO minivalAP: 27.8 -> 28.4 (0.4); 27.8 -> 27.1 (0.6)Mixed
add feature sampling offsets for classification (ablation)one ROC · COCO minivalAP: 29.9 -> 30.3Improved
add feature sampling offsets for classification (ablation)two ROCs · COCO minivalAP: 31.1 -> 32.6Improved
use two 1x1 convs instead of one to predict sampling offsets (ablation)ROC · COCO minivalAP: 30.2 -> 30.3No clear effect
apply FE module to second ROC instead of first (ablation)HSD two ROCs + FE · COCO minivalAP: 32.7 -> 33.3Improved
add non-local context to FE module (ablation)HSD FE second ROC · COCO minivalAP: 33.0 -> 33.3Improved

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