WILDCAT: Weakly Supervised Learning of Deep ConvNets for Image Classification, Pointwise Localization and Segmentation

Durand, Thibaut; Mordan, Taylor; Thome, Nicolas; Cord, Matthieu

doi:10.1109/cvpr.2017.631

Cited by 304 publications

(287 citation statements)

References 57 publications

Supporting

Mentioning

285

Contrasting

Order By: Relevance

“…whereM ck is the instance-wise CAMs of class c and instance k. Each instance-wise CAM is refined individually by propagating its attention scores to relevant areas. Specifically, the propagation is done by random walk, whose transition probability matrix is derived from the semantic affinity matrix A = [a ij ] ∈ R wh×wh as follows: (12) and A •β is A to the Hadamard power of β and S is a diagonal matrix for row-normalization of A •β . Also, β > 1 is a hyper-parameter for smoothing out affinity values in A.…”

Section: Synthesizing Instance Segmentation Labelsmentioning

confidence: 99%

Weakly Supervised Learning of Instance Segmentation With Inter-Pixel Relations

Ahn

Cho

Kwak

2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

442

585

View full text Add to dashboard Cite

This paper presents a novel approach for learning instance segmentation with image-level class labels as supervision. Our approach generates pseudo instance segmentation labels of training images, which are used to train a fully supervised model. For generating the pseudo labels, we first identify confident seed areas of object classes from attention maps of an image classification model, and propagate them to discover the entire instance areas with accurate boundaries. To this end, we propose IRNet, which estimates rough areas of individual instances and detects boundaries between different object classes. It thus enables to assign instance labels to the seeds and to propagate them within the boundaries so that the entire areas of instances can be estimated accurately. Furthermore, IRNet is trained with interpixel relations on the attention maps, thus no extra supervision is required. Our method with IRNet achieves an outstanding performance on the PASCAL VOC 2012 dataset, surpassing not only previous state-of-the-art trained with the same level of supervision, but also some of previous models relying on stronger supervision.

show abstract

Section: Synthesizing Instance Segmentation Labelsmentioning

confidence: 99%

Weakly Supervised Learning of Instance Segmentation With Inter-Pixel Relations

Ahn

Cho

Kwak

2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

442

585

View full text Add to dashboard Cite

show abstract

“…An aggregation function f agg (A c ) : R h,w → [0, 1] is designed to map the SM for each class c into a predictionŷ c loc . The design of f agg (A c ) has been extensively studied [4]. Global Average Pooling (GAP) would dilute the prediction as most of the spatial locations in A c correspond to background and provide little training signal.…”

Section: Trainingmentioning

confidence: 99%

Globally-Aware Multiple Instance Classifier for Breast Cancer Screening

Shen

Phang

et al. 2019

Machine Learning in Medical Imaging

View full text Add to dashboard Cite

Deep learning models designed for visual classification tasks on natural images have become prevalent in medical image analysis. However, medical images differ from typical natural images in many ways, such as significantly higher resolutions and smaller regions of interest. Moreover, both the global structure and local details play important roles in medical image analysis tasks. To address these unique properties of medical images, we propose a neural network that is able to classify breast cancer lesions utilizing information from both a global saliency map and multiple local patches. The proposed model outperforms the ResNet-based baseline and achieves radiologist-level performance in the interpretation of screening mammography. Although our model is trained only with image-level labels, it is able to generate pixel-level saliency maps that provide localization of possible malignant findings.

show abstract

“…This study (Kolesnikov & Lampert, 2016) proposes a new composite loss function to train FCNs directly from image-level labels. Another study (Durand, Mordan, Thome, & Cord, 2017) proposes a two-step approach: first, teach a CNN classification model trained on imagelevel labels to learn good representations and, then, use the learned feature maps to get the segmentation result.…”

Section: Models For Weakly Labeled Datamentioning

confidence: 99%

CoralSeg: Learning coral segmentation from sparse annotations

Alonso

Yuval

Eyal

et al. 2019

Journal of Field Robotics

View full text Add to dashboard Cite

Robotic advances and developments in sensors and acquisition systems facilitate the collection of survey data in remote and challenging scenarios. Semantic segmentation, which attempts to provide per‐pixel semantic labels, is an essential task when processing such data. Recent advances in deep learning approaches have boosted this task's performance. Unfortunately, these methods need large amounts of labeled data, which is usually a challenge in many domains. In many environmental monitoring instances, such as the coral reef example studied here, data labeling demands expert knowledge and is costly. Therefore, many data sets often present scarce and sparse image annotations or remain untouched in image libraries. This study proposes and validates an effective approach for learning semantic segmentation models from sparsely labeled data. Based on augmenting sparse annotations with the proposed adaptive superpixel segmentation propagation, we obtain similar results as if training with dense annotations, significantly reducing the labeling effort. We perform an in‐depth analysis of our labeling augmentation method as well as of different neural network architectures and loss functions for semantic segmentation. We demonstrate the effectiveness of our approach on publicly available data sets of different real domains, with the emphasis on underwater scenarios—specifically, coral reef semantic segmentation. We release new labeled data as well as an encoder trained on half a million coral reef images, which is shown to facilitate the generalization to new coral scenarios.

show abstract

WILDCAT: Weakly Supervised Learning of Deep ConvNets for Image Classification, Pointwise Localization and Segmentation

Cited by 304 publications

References 57 publications

Weakly Supervised Learning of Instance Segmentation With Inter-Pixel Relations

Weakly Supervised Learning of Instance Segmentation With Inter-Pixel Relations

Globally-Aware Multiple Instance Classifier for Breast Cancer Screening

CoralSeg: Learning coral segmentation from sparse annotations

Contact Info

Product

Resources

About