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

By Thibaut Durand, Taylor Mordan, Nicolas Thomé, Matthieu Cord. Computer Vision and Pattern Recognition, 2017

336 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/c1e714a9ec329629798a88ebff8657c349fec739

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

MUREL: Multimodal Relational Reasoning for Visual Question Answering (2019, methodology): “classification or detection [14], deep ConvNets have also been successfully used for new artificial intelligence tasks like Visual Question Answering (VQA) [4, 17, 23].”
Global Weighted Average Pooling Bridges Pixel-level Localization and Image-level Classification (2018, methodology): “[31], [32] proposed methods to select multiple high and low scoring regions instead of a single highest scoring region.”
Weakly Supervised Object Localization and Detection: A Survey (2021, positive): “Built on CAM [216], Durand et al. [32] introduce the multi-map transfer layer and the WILDCAT pooling layer to facilitate the more accurate deep MIL process.”
Weakly Supervised Complementary Parts Models for Fine-Grained Image Classification From the Bottom Up (2019, methodology): “In [7, 6], the object detection is solved as a classification problem by specific pooling layers in CNNs.”
Vision Transformers are Good Mask Auto-Labelers (2023, background): “In addition, FAN [52] shows that such emerging properties in ViTs are linked to their robustness.”
Large-Scale Weakly-Supervised Pre-Training for Video Action Recognition (2019, background): “Learning from weak supervision: Given the known challenges in gathering exhaustive annotations for various image and video tasks, leveraging object labels and other meta information to supply weak supervision [7, 15, 19, 22, 30, 31, 39, 40, 50, 52, 53, 54, 55, 56, 59] is a widely-adopted approach.”
Weakly Supervised Learning of Instance Segmentation With Inter-Pixel Relations (2019, background): “In particular, imagelevel class labels have been widely used as weak labels since they require minimal or no effort for annotation [1, 11, 19, 20, 36, 39, 40, 45, 50].”
Weakly-Supervised Semantic Segmentation by Iteratively Mining Common Object Features (2018, methodology): “Multi-instance learning (MIL) based methods [21, 22, 13, 25, 5] formulate weakly-supervised learning as a MIL framework in which each image is known to have at least one pixel belonging to a certain class, and the task is to find these pixels.”
W-TALC: Weakly-supervised Temporal Activity Localization and Classification (2018, background): “On the other hand, end-to-end learning with categorical loss functions are presented in [15,16,13,47] and recently, the authors in [71] incorporated the proposal generation network in an end-to-end manner.”
Decoupling Category-wise Independence and Relevance with Self-attention for Multi-label Image Classification (2019, methodology): “Spatial Pooling To integrate the capabilities of max-pooling and global average pooling, a spatial pooling method was proposed in [12], where optional hyper-parameters are used to average both positive and negative pixels in each feature map,”
Attention-Based Dropout Layer for Weakly Supervised Object Localization (2019, background): “Existing approaches mine and track discriminative features of each class for object detection [45, 36, 37, 9, 45, 25, 21, 41, 19, 2, 39, 15, 63, 7, 5, 4, 48, 14, 65, 32, 31, 58, 62, 8, 6] and segmentation [33, 29, 18, 16, 24, 52, 50].”
DiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence from Box Supervision (2021, positive): “A number of methods have been proposed to learn semantic segmentation with image-level class labels [69–73], points [74,75], scribbles [76–79] and bounding boxes [46,80–83].”
A Survey of Deep Learning Techniques for Weed Detection from Images (2021, background): “, 2019) or weakly supervised (Durand et al., 2017; Zhou, 2018) approaches could be employed to address this problem.”
Unsupervised Object Segmentation by Redrawing (2019, methodology): “For instance, WILDCAT [13] uses a Conditional Random Field (CRF) for spatial prediction in order to post-process class saliency maps for semantic segmentation.”
3rd Continual Learning Workshop Challenge on Egocentric Category and Instance Level Object Understanding (2022, background): “Research does not only cover the advancement of performance under classic learning paradigms (supervised, offline training) [20, 21, 22, 23, 24, 25, 26, 27], but also encompasses areas such as weakly-supervised learning [28, 29, 30, 31], few-shot learning [32, 33, 34, 35, 36, 37, 38], and semi-super”
SIXray: A Large-Scale Security Inspection X-Ray Benchmark for Prohibited Item Discovery in Overlapping Images (2019, background): “This is related to the research in weakly-supervised object localization [3] [6] [33], or a series of work in localizing objects using top-down class activation [8] [7] [40].”
Multi-evidence Filtering and Fusion for Multi-label Classification, Object Detection and Semantic Segmentation Based on Weakly Supervised Learning (2018, methodology): “Methods in [28, 10, 9] treat the weakly supervised localization problem as an image classification problem, and obtain object locations in specific pooling layers of their networks.”