SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2204.04836 · CVPR · 2022

Consistency Learning via Decoding Path Augmentation for Transformers in Human Object Interaction Detection

Hyunwoo Kim, Seungjun Lee, Hyeong Choi, Jihwan Park, Hwan Heo

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Human-Object Interaction detection is a holistic visual recognition task that entails object detection as well as interaction classification. Previous works of HOI detection has been addressed by the various compositions of subset predictions, e.g., Image → HO → I, Image → HI → O. Recently, transformer based architecture for HOI has emerged, which directly predicts the HOI triplets in an endto-end fashion (Image → HOI). Motivated by various inference paths for HOI detection, we propose cross-path consistency learning (CPC), which is a novel end-to-end learning strategy to improve HOI detection for transformers by leveraging augmented decoding paths. CPC learning enforces all the possible predictions from permuted inference sequences to be consistent. This simple scheme makes the model learn consistent representations, thereby improving generalization without increasing model capacity. Our experiments demonstrate the effectiveness of our method, and we achieved significant improvement on V-COCO and HICO-DET compared to the baseline models. Our code is available at https://github.com/mlvlab/CPChoi.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2204.04836")
get_code_for_paper("2204.04836")
have("2204.04836")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2204.04836.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2204.04836.svg)](https://syntology.ai/paper/2204.04836)

Connect an agent — have() is free.