Unsupervised object discovery and localization in the wild: Part-based matching with bottom-up region proposals

By Minsu Cho, Suha Kwak, Cordelia Schmid, Jean Ponce. 2015

288 citations recorded by the source corpus.

This paper addresses unsupervised discovery and localization of dominant objects from a noisy image collection with multiple object classes. The setting of this problem is fully unsupervised, without even image-level annotations or any assumption of a single dominant class. This is far more general than typical colocalization, cosegmentation, or weakly-supervised localization tasks. We tackle the discovery and localization problem using a part-based region matching approach: We use off-the-shelf region proposals to form a set of candidate bounding boxes for objects and object parts. These regions are efficiently matched across images using a probabilistic Hough transform that evaluates the confidence for each candidate correspondence considering both appearance and spatial consistency. Dominant objects are discovered and localized by comparing the scores of candidate regions and selecting those that stand out over other regions containing them. Extensive experimental evaluations on standard benchmarks demonstrate that the proposed approach significantly outperforms the current state of the art in colocalization, and achieves robust object discovery in challenging mixed-class datasets.

Subfields: Aerospace Engineering, 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 Aerospace Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

Grafit: Learning fine-grained image representations with coarse labels (2020, background): “Note that this work departs from the popular framework of object/category discovery [11, 21, 32, 57, 58], which is completely unsupervised.”
Learning Open-World Object Proposals without Learning to Classify (2021, background): “They have become the integral pre-processing steps for many computer vision systems, including object detection [33,41,42,45,59,74], segmentation [3,8,13], object discovery [12, 16, 47], weakly supervised object detection [5, 21, 53], visual tracking [35, 63], content-aware retargeting [51], etc.”
Object-Proposal Evaluation Protocol is ‘Gameable’ (2015, background): “Notice that the former definition has an emphasis on object discovery [27,28,30], while the latter definition emphasises on the ultimate performance of a detection pipeline.”
Unsupervised Object Discovery and Tracking in Video Collections (2015, methodology): “This agrees with the conclusions of [4] in the still image domain, and has also been conﬁrmed empirically by our experiments.”
Learning Word-Like Units from Joint Audio-Visual Analysis (2017, background): “While supervised object detection is a standard problem in the vision community, several recent works have tackled the problem of weakly-supervised or unsupervised object localization (Bergamo et al., 2014; Cho et al., 2015; Zhou et al., 2015; Cinbis et al., 2016).”
Unsupervised Visual Representation Learning by Graph-Based Consistent Constraints (2016, methodology): “Existing methods use various forms of clustering or matching algorithms for object discovery [23], ROI detection [24] and patch mining [25,26].”
Mining Object Parts from CNNs via Active Question-Answering (2017, background): “[11, 7] did not require any annotations during the learning process.”
Zero Shot Detection (2018, unknown): “There are also methods that aim to discover objects without supervision [36].”
BING: Binarized normed gradients for objectness estimation at 300fps (2014, methodology): “A generic objectness measure has great potential to be used as a pre-filter for many vision tasks, including object detection [3–5], visual tracking [6, 7], object discovery [8, 9], semantic segmentation [10, 11], content aware image retargeting [12], and action recognition [13].”
Deep Feature Factorization For Concept Discovery (2018, methodology): “As in previous work [21,5,19], we use the trainval set for evaluation and ﬁlter out images that only contain objects which are marked as diﬃcult or truncated .”
Unsupervised Image Matching and Object Discovery as Optimization (2019, methodology): “Intuitively, s ij scales the appearance-only score a ij by a geometric-consistency term akin to a generalized Hough transform [5], see [12] for details.”
Unsupervised Discovery of Object Landmarks as Structural Representations (2018, background): “5 [9] Minsu Cho, Suha Kwak, Cordelia Schmid, and Jean Ponce.”
Learning About Objects by Learning to Interact with Them (2020, methodology): “The supervised video object discovery approaches use different forms of supervision such as CNNs pre-trained for other tasks [35, 58, 57], supervised object proposal models [19, 11, 34], fixation data as annotation [61], or instance segmentation for single frames [46].”
Toward unsupervised, multi-object discovery in large-scale image collections (2020, methodology): “An important component of OSD is the similarity model used to compute score matrices Sij , which, in [34], is the Probabilistic Hough Matching (PHM) algorithm [6].”
Learning Dense Correspondence via 3D-Guided Cycle Consistency (2016, methodology): “[9] use correspondence consistency among selective search windows in a diverse image collection to perform unsupervised object discovery.”