AI Paper Atlas

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

Revisit Anything: Visual Place Recognition via Image Segment Retrieval

Kartik Garg, Sai Shubodh, Shishir N Y Kolathaya, Madhava Krishna, Sourav Garg

ECCV 2024 · Detection and segmentation › Open-set and few-shot detection · approach: Object-level representation learning · 23 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 whole-image global aggregation (AnyLoc) with SuperSegment retrieval (SegVLAD-PreT)AnyLoc DINOv2 · Baidu MallRecall@1/5: 75.2/87.6 -> 80.4/94.0Improved
replace whole-image global aggregation (AnyLoc) with SuperSegment retrieval on out-of-distribution InsideOutAnyLoc DINOv2 · InsideOutRecall@1/5: 2.4/8.0 -> 4.2/9.4Improved
replace SALAD global descriptor with SegVLAD-FineT on street-view dataSALAD · Pitts30KRecall@1: 92.6 -> 93.1No clear effect
use segment retrieval on pretrained DINOv2 for Pitts30KAnyLoc · Pitts30KRecall@1/5: 87.7/94.7 -> 86.7/94.2Hurt
add neighborhood aggregation (SuperSegments) to segments (ablation)SegVLAD · Baidu OOI instance retrievalRecall@1: 64.1 -> 92.7Improved
expand segment neighborhood order from 0 to 3 with VLAD (ablation)SegVLAD · Baidu MallRecall@1: 73.1 -> 77.7Improved
expand neighborhood with segment average pooling (ablation)SAP · Baidu MallRecall@1: 74.6 -> 49.8Hurt
use VLAD aggregation instead of segment average pooling at order 3 (ablation)SuperSegments · Baidu MallRecall@1: 49.8 -> 77.7Improved
use segment descriptors instead of random local point features (ablation)SegVLAD · Baidu MallRecall@1: 69.1 -> 78.5Improved
replace SAM with FastSAM for segmentation (ablation)SegVLAD · Baidu MallRecall@1: 78.5 -> 76.2 with 3.5s -> 0.28s segmentationMixed
filter database SuperSegments by IoU threshold 0.4 (ablation)SegVLAD · AmsterTimeRecall@1: 58.9 -> 58.9No clear effect
use soft-assignment NetVLAD instead of hard VLAD (ablation)SegVLAD · AmsterTimeRecall@1: 58.9 -> 60.2No clear effect

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