Harvesting Mid-level Visual Concepts from Large-Scale Internet Images

By Quannan Li, Jiajun Wu, Zhuowen Tu. 2013

153 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Representation & Self-Supervised Learning

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

In Representation & Self-Supervised Learning

Citations in the corpus

Learning Visual Features from Large Weakly Supervised Data (2015, methodology): “Li et al. [28] learn mid-level representations by training a multiple-instance learning variant of SVMs on hand-crafted low-level features extracted from images downloaded using Google Image search.”
Webly Supervised Learning of Convolutional Networks (2015, background): “So, what we want is an approach that can learn visual representation from Flickr-like images.”
Unsupervised Visual Representation Learning by Context Prediction (2015, background): “Finally, our work is related to a line of research on discriminative patch mining [13, 47, 26, 34, 49, 11], which has emphasized weak supervision as a means of object discovery.”
CNN Features Off-the-Shelf: An Astounding Baseline for Recognition (2014, background): “26.05 DPM[28] 30.40 Object Bank[23] 37.60 RBow[29] 37.93 BoP[20] 46.10 miSVM[24] 46.40 D-Parts[38] 51.40 IFV[20] 60.77 MLrep[10] 64.03 CNN-SVM 58.44 points are annotated with their ground truth and estimated labels.”
Context as Supervisory Signal: Discovering Objects with Predictable Context (2014, background): “A number of recent works have argued that weak supervision can be an effective way to get more visually meaningful clusters [14,15,16,17,18,19,20,21,22,23].”
Multiple Instance Detection Network with Online Instance Classifier Refinement (2017, background): “However, collecting such accurate annotations can be very labor-intensive and time-consuming, whereas achieving only image-level annotations ( i.e ., image tags) is much easier, as these annotations are often available at the Internet ( e.g ., image search queries [21]).”
Information Bottleneck Learning Using Privileged Information for Visual Recognition (2016, background): “Similarly, [37, 23] learn to extract mid-level features by training data from additionally annotated concepts.”
Action Recognition with Actons (2013, methodology): “The very recent work of [14, 29] exploit the MIL methods to learn multiple mid-level visual concepts for each class in a weakly-supervised manner.”
Contractive Rectifier Networks for Nonlinear Maximum Margin Classification (2015, unknown): “1% VC + VQ [23] 52.”
PCL: Proposal Cluster Learning for Weakly Supervised Object Detection (2018, background): “image classification [26], [27], weakly supervised semantic segmentation [28], [29], object detection [30], object tracking [31], etc.”
Weakly Supervised Object Localization with Latent Category Learning (2014, background): “Many studies in unsupervised learning have attempted to discover the latent categories in object-centered conditions [4, 18, 19, 27, 30].”
Unsupervised Joint Mining of Deep Features and Image Labels for Large-Scale Radiology Image Categorization and Scene Recognition (2017, methodology): “A variety of mid-level visual elements can be harvested, e.g., image patches [53, 13, 34, 60], parts/segments [27, 54, 2], prototypes [11], attributes [51, 7] through different learning and mining techniques, e.g., iterative optimization [53, 27], classification and co-segmentation [54], Multiple In”
Learning coarse-to-fine sparselets for efficient object detection and scene classification (2015, methodology): “In recent years, since the seminal work of [4, 5] and with the success of deformable part models (DPMs) [6, 7], part model-based methods have demonstrated impressive performance for object detection [6-13] and scene classification [14-21].”
Mid-level Visual Element Discovery as Discriminative Mode Seeking (2013, methodology): “, scene categories [12] or GPS coordinates [5] (but can also run unsupervised [23]), and have been recently used for tasks including image classification [12, 23, 27], object detection [6], visual data mining [5, 15], action recognition [11], and geometry estimation [7].”
ConceptMap: Mining Noisy Web Data for Concept Learning (2014, methodology): “As shown in Table1, our method for scene recognition with learned attributes (CMAP-A), performs competitively with [34] while using shorter feature vectors in relatively cheaper environment, and outperforms the others.”