AI Paper Atlas

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

SMILe: Leveraging Submodular Mutual Information For Robust Few-Shot Object Detection

Anay Majee, Ryan X Sharp, Rishabh Iyer

ECCV 2024 · Detection and segmentation › Open-set and few-shot detection · approach: Few-shot object detection · 9 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 SMILe objective during few-shot adaptationFSCE · PASCAL VOC split 3, 10-shotnovel mAP50: 57.7 -> 59.0Improved
add SMILe objective during few-shot adaptationDiGeo · PASCAL VOC split 3, 10-shotnovel mAP50: 52.9 -> 56.4Improved
add SMILe objectivePDC (imTED, ViT-B) · MS-COCO 30-shotnovel mAP50: 47.3 -> 49.9Improved
add SMILe objectivePDC (imTED, ViT-B) · MS-COCO 10-shotnovel mAP: 23.4 -> 25.8Improved
add SMILe objectivePDC (imTED, ViT-B) · PASCAL VOC split 3, 1-shotnovel mAP50: 18.9 -> 15.1Hurt
add intra-class total-information term L_comb^intra to FSCE (ablation)FSCE · PASCAL VOC split 1, 10-shotbase mAP50: 86.1 -> 89.6Improved
add inter-class SMI term L_comb^inter to FSCE (ablation)FSCE · PASCAL VOC split 1, 10-shotnovel mAP50: 57.8 -> 61.0Improved
add both inter and intra terms vs intra only (ablation)FSCE · PASCAL VOC split 1, 10-shotnovel mAP50: 60.1 -> 61.1Improved
use Facility-Location / FLMI instead of Graph-Cut / GCMI (ablation)DiGeo · PASCAL VOC split 1, 10-shotnovel mAP50: 60.9 -> 62.3Improved
use Facility-Location / FLMI instead of Graph-Cut / GCMI (ablation)FSCE · PASCAL VOC split 1, 10-shotnovel mAP50: 60.3 -> 61.1Improved
add SMILe to AGCMAGCM · base class retentionbase mAP retention: ~3.5% better retentionImproved
add SMILe to AGCMAGCM · confusion matrixclass confusion: 11% lower confusionImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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