Unsupervised object class discovery via saliency-guided multiple class learning

By Jun-Yan Zhu, Jiajun Wu, Yan Xu, Eric I-Chao Chang, Zhuowen Tu. 2012

160 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

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

Self-Supervised Training Enhances Online Continual Learning (2021, background): “Our work could also facilitate downstream open world learning [7] or automatic class discovery [64, 75], where an agent must identify samples outside of its training distribution as unknown and then learn them.”
Deep multiple instance learning for image classification and auto-annotation (2015, background): “[49] also studied multiple instance learning with salient windows, but with a focus on unsupervised object discovery and without learning deep representations.”
Salient Object Detection in the Deep Learning Era: An In-Depth Survey (2019, unknown): “In computer vision, sampled applications of SOD include image understanding [1], [2], image cap-tioning [3]–[5], object detection [6], [7], un-supervised video object segmentation [8], [9], semantic segmentation [10]– [12], person re-identiﬁcation [13], [14], etc .”
Category Modeling from Just a Single Labeling: Use Depth Information to Guide the Learning of 2D Models (2013, methodology): “Most methods used bag-of-words models [5] for category representation, and others [25, 26, 27, 28] detected repetitive objects with the similar appearance in the environment.”
Harvesting Mid-level Visual Concepts from Large-Scale Internet Images (2013, methodology): “In [37], saliency detection is utilized to create bags of image patches, but only one object is assumed in each image for the task of object discovery.”
Deep Level Sets for Salient Object Detection (2017, methodology): “Inspired by this biological capability, visual saliency computation is introduced into the field of computer vision for its potential to enhance tasks like image processing [4, 12], image understanding [58, 63], video analysis and compression [13, 45].”
Bayesian Joint Modelling for Object Localisation in Weakly Labelled Images (2015, background): “This is mainly due to the unique joint modelling approach taken by our method, and its ability to integrate prior spatial and appearance knowledge in a principled Method Initialisation Refined by detector 6×2 14 20 6×2 14 20 Deselaers et al [11] a. single feature 35 21 - 40 24 - b. all four features”
Co-Saliency Detection via a Self-Paced Multiple-Instance Learning Framework (2017, methodology): “Nowadays, it is of great interest to automatically co-localize the common objects in images obtained from the internet [15], [16], [69].”
Cluster-based Co-saliency Detection (2013, unknown): “Existing approaches discover possible regions of object instances and output a set of windows containing the common object [50]–[52].”
Unconstrained Salient Object Detection via Proposal Subset Optimization (2016, background): “Furthermore, individuating each salient object (or reporting that no salient object is present) can critically alleviate the ambiguity in the weakly supervised or unsupervised learning scenario [10, 26, 55], where object appearance models are to be learned with no instance level annotation.”
Salient Object Detection: A Benchmark (2015, background): “In many computer vision and graphics applications, segmenting regions of interest is of great practical importance [37], [46], [49]–[51], [114], [115].”
Salient object detection: A survey (2014, background): “This allows the filtering of images for the purposes of reliability and accuracy, running applications robustly [84, 174, 175, 177, 179, 233], and unsupervised learning [176].”
Stream-51: Streaming Classification and Novelty Detection from Videos (2020, background): “The ability of an agent to recognize inputs outside of its training distribution could facilitate automatic class discovery [39, 44] or open world learning [3].”
A Stagewise Refinement Model for Detecting Salient Objects in Images (2017, background): “Salient object detection models have gained broad interest recently due to their applications in several fields such as tracking [19], image understanding [54, 45], person re-identification [4], image captioning [51, 13, 12], visual question answering [32], and object proposal generation [2].”
Global Contrast Based Salient Region Detection (2015, background): “object of interest regions is powerful to explore this big data for image composition [82], semantic colorization [83], information discovery [84], [85], image”