Exploiting Negative Evidence for Deep Latent Structured Models - Archive ouverte HAL
Journal Articles IEEE Transactions on Pattern Analysis and Machine Intelligence Year : 2019

Exploiting Negative Evidence for Deep Latent Structured Models

Abstract

The abundance of image-level labels and the lack of large scale detailed annotations (e.g. bounding boxes, segmentation masks) promotes the development of weakly supervised learning (WSL) models. In this work, we propose a novel framework for WSL of deep convolutional neural networks dedicated to learn localized features from global image-level annotations. The core of the approach is a new latent structured output model equipped with a pooling function which explicitly models negative evidence, e.g. a cow detector should strongly penalize the prediction of the bedroom class. We show that our model can be trained end-to-end for different visual recognition tasks: multi-class and multi-label classification, and also structured average precision (AP) ranking. Extensive experiments highlight the relevance of the proposed method: our model outperforms state-of-the art results on six datasets. We also show that our framework can be used to improve the performance of state-of-the-art deep models for large scale image classification on ImageNet. Finally, we evaluate our model for weakly supervised tasks: in particular, a direct adaptation for weakly supervised segmentation provides a very competitive model.
Fichier principal
Vignette du fichier
2018PAMIcord_sans marque.pdf (4.05 Mo) Télécharger le fichier
Origin Files produced by the author(s)
Loading...

Dates and versions

hal-01969819 , version 1 (04-01-2019)

Identifiers

Cite

Thibaut Durand, Nicolas Thome, Matthieu Cord. Exploiting Negative Evidence for Deep Latent Structured Models. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2019, 41 (2), pp.337-351. ⟨10.1109/TPAMI.2017.2788435⟩. ⟨hal-01969819⟩
130 View
366 Download

Altmetric

Share

More