SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2205.08536 · CVPR · 2022

Disentangling Visual Embeddings for Attributes and Objects

Abhinav Shrivastava, Khoi Pham, Nirat Saini

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

We study the problem of compositional zero-shot learning for object-attribute recognition. Prior works use visual features extracted with a backbone network, pre-trained for object classification and thus do not capture the subtly distinct features associated with attributes. To overcome this challenge, these studies employ supervision from the linguistic space, and use pre-trained word embeddings to better separate and compose attribute-object pairs for recognition. Analogous to linguistic embedding space, which already has unique and agnostic embeddings for object and attribute, we shift the focus back to the visual space and propose a novel architecture that can disentangle attribute and object features in the visual space. We use visual decomposed features to hallucinate embeddings that are representative for the seen and novel compositions to better regularize the learning of our model. Extensive experiments show that our method outperforms existing work with significant margin on three datasets: MIT-States, UT-Zappos, and a new benchmark created based on VAW. The code, models, and dataset splits are publicly available at https: //github.com/nirat1606/OADis.

For agents

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

get_harvested_code_for_paper("2205.08536")
get_code_for_paper("2205.08536")
have("2205.08536")

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

curl https://syntology.ai/api/ran/2205.08536.json

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

[![Syntology run record](https://syntology.ai/api/ran/2205.08536.svg)](https://syntology.ai/paper/2205.08536)

Connect an agent — have() is free.