AI Paper Atlas

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

Simulating Distribution Dynamics: Liquid Temporal Feature Evolution for Single-Domain Generalized Object Detection

Zihao Zhang, Yang Li, Aming Wu, Yahong Han

AAAI 2026 · Detection and segmentation › Open-set and few-shot detection · approach: Domain-adaptive object detection · 0 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 progressive temporal feature evolution (PTFE) alone (ablation)Faster R-CNN · Diverse Weather: Night SunnymAP (%): 35.4 -> 36.8Improved
add temporal dependency modeling and liquid parameter evolution on top of PTFE (ablation)LTFE · Diverse Weather: Night SunnymAP (%): 36.8 -> 42.6Improved
add temporal feature alignment module (TFAM) on top of PTFE (ablation)LTFE · Diverse Weather: Night SunnymAP (%): 36.8 -> 40.2Improved
add TFAM to PTFE + TDM + LPE (full model) (ablation)LTFE · Diverse Weather: Night RainymAP (%): 22.7 -> 24.3Improved
increase training evolution steps T up to 8 (ablation)PTFE · Day Foggy and Dusk RainymAP (%)Improved
use larger T at inference (ablation)LTFE · Diverse WeathermAP (%)Hurt
swap ResNet-101 for Swin-T backboneLTFE · Diverse Weather: Night SunnymAP (%): 43.1 -> 53.1Improved
compare LTFE with test-time adaptation methodsLTFE vs ECPG · Diverse Weather: Night SunnymAP (%): 35.3 -> 43.1Improved
LTFE vs SECOT with ResNet-101 on Real-to-Art ClipartLTFE · Clipart1kmAP (%): 40.2 -> 42.1Mixed
LTFE vs prior methods on Diverse Weather (ResNet-101)LTFE · Diverse Weather: Night Sunny / Night RainymAP (%): Night Sunny 45.0 (G-NAS) vs 43.1; Night Rainy 24.5 (SECOT) vs 24.3Mixed

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