AI Paper Atlas

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

Recognizing Unseen Attribute-Object Pair with Generative Model

Zhixiong Nan, Yang Liu, Nanning Zheng, Song-Chun Zhu

AAAI 2019 · Detection and segmentation › Open-set and few-shot detection · approach: Visual relationship and scene graph detection · 41 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 triplet loss to encoding loss (ablation)encoder-decoder attribute-object model · MIT-Statestop-1 accuracy: 3.6 -> 11.2Improved
add triplet loss to encoding loss (ablation)encoder-decoder attribute-object model · UT-Zappos50Ktop-1 accuracy: 37.8 -> 45.5Improved
add decoding loss (autoencoder reconstruction) to encoding loss (ablation)encoder-decoder attribute-object model · MIT-Statestop-1 accuracy: 3.6 -> 17.2Improved
add decoding loss to encoding loss (ablation)encoder-decoder attribute-object model · UT-Zappos50Ktop-1 accuracy: 37.8 -> 41.3Improved
add discriminative loss to encoding loss (ablation)encoder-decoder attribute-object model · MIT-Statestop-1 accuracy: 3.6 -> 15.3Improved
add discriminative loss to encoding loss (ablation)encoder-decoder attribute-object model · UT-Zappos50Ktop-1 accuracy: 37.8 -> 37.9No clear effect
add decoding loss on top of triplet + discriminative (ablation)encoder-decoder attribute-object model · MIT-Statestop-1 accuracy: 15.7 -> 17.8Improved
use separate projection functions for attribute and object (ablation)encoder-decoder attribute-object model · MIT-Statestop-1 accuracy: 16.5 -> 17.8Improved
use separate projection functions for attribute and object (ablation)encoder-decoder attribute-object model · UT-Zappos50Ktop-1 accuracy: 47.5 -> 48.3Improved
swap ResNet-18 for deeper ResNet-50 featuresencoder-decoder attribute-object model · MIT-Statestop-1 accuracy: 17.8 -> 19.7Improved
swap ResNet-18 for ResNet-101 featuresencoder-decoder attribute-object model · UT-Zappos50Ktop-1 accuracy: 48.3 -> 51.9Improved
use ResNet-18 instead of VGG-16 featuresencoder-decoder attribute-object model · MIT-Statestop-1 accuracy: 15.4 -> 17.8Improved

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