Weakly Supervised Image Classification Through Noise Regularization

Hu, Mengying; Han, Hu; Shan, Shiguang; Chen, Xilin

doi:10.1109/cvpr.2019.01178

Cited by 30 publications

(13 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The partially labelled setting is also related to methods that address label noise, e.g. [23,24]. Label noise is also encountered in the related area of image tagging [50,14],…”

Section: Related Workmentioning

confidence: 99%

Multi-Label Learning from Single Positive Labels

Cole

Aodha

Lorieul

et al. 2021

2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

Predicting all applicable labels for a given image is known as multi-label classification. Compared to the standard multi-class case (where each image has only one label), it is considerably more challenging to annotate training data for multi-label classification. When the number of potential labels is large, human annotators find it difficult to mention all applicable labels for each training image. Furthermore, in some settings detection is intrinsically difficult e.g. finding small object instances in high resolution images. As a result, multi-label training data is often plagued by false negatives. We consider the hardest version of this problem, where annotators provide only one relevant label for each image. As a result, training sets will have only one positive label per image and no confirmed negatives. We explore this special case of learning from missing labels across four different multi-label image classification datasets for both linear classifiers and end-to-end finetuned deep networks. We extend existing multi-label losses to this setting and propose novel variants that constrain the number of expected positive labels during training. Surprisingly, we show that in some cases it is possible to approach the performance of fully labeled classifiers despite training with significantly fewer confirmed labels.

show abstract

“…The partially labelled setting is also related to methods that address label noise, e.g. [23,24]. Label noise is also encountered in the related area of image tagging [50,14],…”

Section: Related Workmentioning

confidence: 99%

Multi-Label Learning from Single Positive Labels

Cole

Aodha

Lorieul

et al. 2021

2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

show abstract

“…These techniques weigh training samples according to the predictions confidence (Dehghani et al, 2017), one-sided noise assumption (Zhang et al, 2019), a clean set (Ren et al, 2018) or the similarity of their descent directions . Recently, a few studies (Veit et al, 2017;Hu et al, 2019) have also explored designing denoising modules for neural networks. However, our method differs from them in that: (1) our method learns conditional reliability scores for multiple sources; and (2) these methods still require clean data for denoising, while ours does not.…”

Section: Related Workmentioning

confidence: 99%

Denoising Multi-Source Weak Supervision for Neural Text Classification

Ren¹,

Li²,

Su³

et al. 2020

Findings of the Association for Computational Linguistics: EMNLP 2020

View full text Add to dashboard Cite

We study the problem of learning neural text classifiers without using any labeled data, but only easy-to-provide rules as multiple weak supervision sources. This problem is challenging because rule-induced weak labels are often noisy and incomplete. To address these two challenges, we design a label denoiser, which estimates the source reliability using a conditional soft attention mechanism and then reduces label noise by aggregating rule-annotated weak labels. The denoised pseudo labels then supervise a neural classifier to predicts soft labels for unmatched samples, which address the rule coverage issue. We evaluate our model on five benchmarks for sentiment, topic, and relation classifications.The results show that our model outperforms state-of-the-art weakly-supervised and semi-supervised methods consistently, and achieves comparable performance with fully-supervised methods even without any labeled data. Our code can be found at https://github.com/weakrules/ Denoise-multi-weak-sources.

show abstract

“…Therefore, our goal is to separate the correct supervision information from pseudo labels and use the correct labeled pixels as auxiliary supervised information to train a segmentation network with strong labels. Inspired by a semisupervised classification method [12], we expect that the proposed method can enhance the utilization of supervised information in pseudo-labels,and use it as a supplement of strong labels to improve the performance of semantic segmentation. The proposed model called Digging into Pseudo Label(DIPL) has been utilized to replace the segmentation network g ϕ in step 3 of Figure 1, ensuring that the reliable information of pseudo labels can be fully utilized during the training process.…”

Section: Figurementioning

confidence: 99%

Digging Into Pseudo Label: A Low-Budget Approach for Semi-Supervised Semantic Segmentation

Chen

Zhang

et al. 2020

IEEE Access

View full text Add to dashboard Cite

The capability to understand visual scenes with limited labeled data has been widely concerned in the field of computer vision. Although semi-supervised learning for image classification has been extensively studied in some cases, semantic segmentation with limited data has only recently gained attention. In this work, we follow the standard semi-supervised segmentation pipeline for image classification and propose a two-branch network that can encode strong and pseudo label spaces respectively, extracting reliable supervision information from pseudo-labels to assist in training network with strong labels. Our method outperforms previous semi-supervised methods with limited annotation cost. On standard benchmark PASCAL VOC 2012 for semi-supervised semantic segmentation, the proposed approach gains fresh state-of-the-art performance.

show abstract

Weakly Supervised Image Classification Through Noise Regularization

Cited by 30 publications

References 24 publications

Multi-Label Learning from Single Positive Labels

Multi-Label Learning from Single Positive Labels

Denoising Multi-Source Weak Supervision for Neural Text Classification

Digging Into Pseudo Label: A Low-Budget Approach for Semi-Supervised Semantic Segmentation

Contact Info

Product

Resources

About