AI Paper Atlas

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

SAFE: Sensitivity-Aware Features for Out-of-Distribution Object Detection

Samuel Wilson, Tobias Fischer, Feras Dayoub, Dimity Miller, Niko Sünderhauf

ICCV 2023 · Detection and segmentation › Open-set and few-shot detection · approach: Open-set and unknown object detection · 44 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
use SAFE residual+BatchNorm layers instead of a random subset of 16 other layers (ablation)SAFE-ResNet50 · PASCAL-VOC ID, OpenImages OODFPR95: 66.10 -> 20.06Improved
use the 4 SAFE critical layers instead of all 60 Conv2d layers (ablation)SAFE-ResNet50 · PASCAL-VOC ID, OpenImages OODFPR95: 26.73 -> 20.06Improved
use the 4 SAFE layers instead of all 12 residual connections (ablation)SAFE-ResNet50 · PASCAL-VOC ID, OpenImages OODFPR95: 24.82 -> 20.06Improved
use the 4 SAFE layers instead of all 12 residual connections (ablation)SAFE-ResNet50 · PASCAL-VOC ID, MS-COCO OODAUROC: 81.87 -> 80.30Hurt
train auxiliary MLP on FGSM-perturbed vs clean features instead of retraining the detector with VOSSAFE-ResNet50 vs VOS-ResNet50 · PASCAL-VOC ID, OpenImages OODFPR95: 51.33 -> 20.06Improved
use SAFE instead of VOS with ResNet-50 on MS-COCO OOD (PASCAL-VOC ID)ResNet-50 Faster-RCNN · PASCAL-VOC ID, MS-COCO OODAUROC: 88.70 -> 80.30Hurt
switch backbone from ResNet-50 to RegNetX4.0 for SAFESAFE · BDD100K ID, MS-COCO OODFPR95: 32.56 -> 21.69Improved
vary FGSM magnitude epsilonSAFE-ResNet50 · PASCAL-VOC IDAUROC and FPR95Mixed
use layers without both residual connection and BatchNorm (single random layers) (ablation)SAFE-ResNet50 · PASCAL-VOC ID, OpenImages OODAUROC: 92.28 -> 75.31Hurt

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