AI Paper Atlas

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

Recognition in Terra Incognita

Sara Beery, Grant Van Horn, Pietro Perona

ECCV 2018 · Detection and segmentation › Open-set and few-shot detection · approach: Remote sensing segmentation and change · 753 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
test on unseen trans-locations instead of seen cis-locationsInception-v3 image classifier · CCT-20top-1 error: 19.06 -> 41.04Hurt
test on unseen trans-locations instead of seen cis-locationsInception-v3 bbox classifier · CCT-20top-1 error: 8.14 -> 19.56Hurt
remove empty images and train on 15 animal classes only (ablation)Inception-v3 image classifier · CCT-20 trans-locationstop-1 error: 41.08 -> 41.04No clear effect
add most-confident sequence information (ablation)Inception-v3 image classifier · CCT-20 trans-locationstop-1 error: 41.04 -> 34.53Improved
add oracle sequence information (ablation)Inception-v3 image classifier · CCT-20 trans-locationstop-1 error: 41.04 -> 28.69Improved
classify cropped bounding boxes instead of full images (ablation)Inception-v3 · CCT-20 trans-locationstop-1 error: 41.04 -> 19.56Improved
classify cropped bounding boxes instead of full images (ablation)Inception-v3 · CCT-20cis-to-trans error increase: 115% -> 140%Hurt
add oracle sequence information (ablation)Inception-v3 bbox classifier · CCT-20cis-to-trans error increase: 140% -> 118%Improved
require 10,000 instead of 500 training examples for trans-locationsInception-v3 classifier · CCT-20error rate at 5.33% bbox: 500 -> 10,000 examplesHurt
use Inception-ResNet-v2 instead of ResNet-101 backbone (ablation)Faster-RCNN · CCT-20 trans-locationsmAP: 70.17 -> 71.37No clear effect
add most-confident sequence information (ablation)Faster-RCNN ResNet-101 · CCT-20 trans-locationsmAP: 70.17 -> 84.09Improved
add most-confident sequence information (ablation)Faster-RCNN ResNet-101 · CCT-20cis-to-trans error increase: 30% -> 4.5%Improved

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