Category-Adaptive Label Discovery and Noise Rejection for Multi-label Image Recognition with Partial Positive Labels

11/15/2022
by   Tao Pu, et al.
0

As a promising solution of reducing annotation cost, training multi-label models with partial positive labels (MLR-PPL), in which merely few positive labels are known while other are missing, attracts increasing attention. Due to the absence of any negative labels, previous works regard unknown labels as negative and adopt traditional MLR algorithms. To reject noisy labels, recent works regard large loss samples as noise but ignore the semantic correlation different multi-label images. In this work, we propose to explore semantic correlation among different images to facilitate the MLR-PPL task. Specifically, we design a unified framework, Category-Adaptive Label Discovery and Noise Rejection, that discovers unknown labels and rejects noisy labels for each category in an adaptive manner. The framework consists of two complementary modules: (1) Category-Adaptive Label Discovery module first measures the semantic similarity between positive samples and then complement unknown labels with high similarities; (2) Category-Adaptive Noise Rejection module first computes the sample weights based on semantic similarities from different samples and then discards noisy labels with low weights. Besides, we propose a novel category-adaptive threshold updating that adaptively adjusts the threshold, to avoid the time-consuming manual tuning process. Extensive experiments demonstrate that our proposed method consistently outperforms current leading algorithms.

READ FULL TEXT

page 1

page 3

research
12/21/2021

Structured Semantic Transfer for Multi-Label Recognition with Partial Labels

Multi-label image recognition is a fundamental yet practical task becaus...
research
05/23/2022

Heterogeneous Semantic Transfer for Multi-label Recognition with Partial Labels

Multi-label image recognition with partial labels (MLR-PL), in which som...
research
03/04/2022

Semantic-Aware Representation Blending for Multi-Label Image Recognition with Partial Labels

Training the multi-label image recognition models with partial labels, i...
research
06/28/2023

Positive Label Is All You Need for Multi-Label Classification

Multi-label classification (MLC) suffers from the inevitable label noise...
research
10/20/2022

G2NetPL: Generic Game-Theoretic Network for Partial-Label Image Classification

Multi-label image classification aims to predict all possible labels in ...
research
03/09/2023

Open World Classification with Adaptive Negative Samples

Open world classification is a task in natural language processing with ...
research
03/25/2016

Unsupervised Category Discovery via Looped Deep Pseudo-Task Optimization Using a Large Scale Radiology Image Database

Obtaining semantic labels on a large scale radiology image database (215...

Please sign up or login with your details

Forgot password? Click here to reset