Weakly Supervised Domain-Specific Color Naming Based on Attention

05/11/2018
by   Lu Yu, et al.
0

The majority of existing color naming methods focuses on the eleven basic color terms of the English language. However, in many applications, different sets of color names are used for the accurate description of objects. Labeling data to learn these domain-specific color names is an expensive and laborious task. Therefore, in this article we aim to learn color names from weakly labeled data. For this purpose, we add an attention branch to the color naming network. The attention branch is used to modulate the pixel-wise color naming predictions of the network. In experiments, we illustrate that the attention branch correctly identifies the relevant regions. Furthermore, we show that our method obtains state-of-the-art results for pixel-wise and image-wise classification on the EBAY dataset and is able to learn color names for various domains.

READ FULL TEXT

page 1

page 2

page 3

page 4

page 5

research
06/12/2023

Weakly-Supervised Scientific Document Classification via Retrieval-Augmented Multi-Stage Training

Scientific document classification is a critical task for a wide range o...
research
11/05/2021

SSA: Semantic Structure Aware Inference for Weakly Pixel-Wise Dense Predictions without Cost

The pixel-wise dense prediction tasks based on weakly supervisions curre...
research
09/13/2022

CAIBC: Capturing All-round Information Beyond Color for Text-based Person Retrieval

Given a natural language description, text-based person retrieval aims t...
research
06/30/2014

Pixel-wise Orthogonal Decomposition for Color Illumination Invariant and Shadow-free Image

In this paper, we propose a novel, effective and fast method to obtain a...
research
10/06/2020

CORE: Color Regression for Multiple Colors Fashion Garments

Among all fashion attributes, color is challenging to detect due to its ...
research
10/17/2022

Weakly Supervised Face Naming with Symmetry-Enhanced Contrastive Loss

We revisit the weakly supervised cross-modal face-name alignment task; t...
research
07/07/2017

Learning Efficient Image Representation for Person Re-Identification

Color names based image representation is successfully used in person re...

Please sign up or login with your details

Forgot password? Click here to reset