The truth about cats and dogs

By Omkar M. Parkhi, Andrea Vedaldi, C. V. Jawahar, Andrew Zisserman. 2011

142 citations recorded by the source corpus.

Subfields: 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 Computer Vision and Pattern Recognition

Citations in the corpus

Hypercolumns for object segmentation and fine-grained localization (2014, methodology): “[33] use color models extracted from the detected cat and dog heads to segment them out.”
Simultaneous Detection and Segmentation (2014, methodology): “use color models from predefined rectangles on cat and dog faces to do GrabCut and improve the predicted bounding box [26].”
Part-Based R-CNNs for Fine-Grained Category Detection (2014, methodology): “The Poselet [8] and DPM [17] methods have previously been utilized to obtain part localizations with a modest degree of success; methods generally report adequate part localization only when given a known bounding box at test time [11,20,36,37,43].”
Detect What You Can: Detecting and Representing Objects Using Holistic Models and Body Parts (2014, methodology): “The reason is probably that head is a distinctive part for cat and dog as it is observed by [19], but for bird and sheep, it is often too small.”
Understanding Image Representations by Measuring Their Equivariance and Equivalence (2014, methodology): “To this end, an SVM classifier 〈w, φ(x)〉 is trained to discriminate between dog and cat faces using the data of [16] (using 15 × 15 HOG templates, 400 training and 1,000 testing images evenly split among cats and dogs).”
Iterative Instance Segmentation (2015, methodology): “More sophisticated approaches model the problem using CRFs with unary and pairwise potentials [27, 24, 19].”
Bird Species Categorization Using Pose Normalized Deep Convolutional Nets (2014, methodology): “Areas explored include feature representations that better preserve fine-grained information [35, 46, 47, 48], segmentation-based approaches [1, 13, 14, 15, 21, 37] that facilitate extraction of purer features, and part/pose normalized feature spaces [5, 6, 19, 33, 38, 39, 43, 50, 51].”
Attention for Fine-Grained Categorization (2014, methodology): “As a result, several hand-crafted vision pipelines use provided bounding boxes to isolate the object of interest or may perform segmentation of the object from the background, e.g. Parkhi et al. (2011); Chai et al. (2013); Angelova & Zhu (2013).”
Weakly Supervised Object Localization with Multi-Fold Multiple Instance Learning (2015, neutral): “[36] also observed this, and proposed to localize cats and dogs based on a head detector in a fully supervised detector setting.”
segDeepM: Exploiting segmentation and context in deep neural networks for object detection (2015, methodology): “In [20], segmentation within the detection boxes has been performed using a GrabCut method.”
Dog Breed Classification Using Part Localization (2012, background): “[19] has also recently addressed the problem of detection of cats and dogs.”
Amodal Instance Segmentation (2016, methodology): “Earlier approaches rely on DPM [11] detections and predict segmentation masks using a simple appearance model [36,30,8], combine DPM detections and semantic segmentation predictions [12,9] or adopt a transductive approach [34].”
Object Detection Using Strongly-Supervised Deformable Part Models (2012, unknown): “Region-level cues and image segmentation have also been explored to improve detection for textured objects such as cats and dogs in [21].”
Learning Rich Part Hierarchies With Progressive Attention Networks for Fine-Grained Image Recognition (2020, background): “Most part-based methods focus on learning explicit part localizations, which involves either supervised part detection technique [6], [12], [18], [24]–[26] or unsupervised/weakly supervised attention learning [13], [14], [20], [21], [27], [28].”
Multi-Attention Multi-Class Constraint for Fine-grained Image Recognition (2018, methodology): “A straightforward way is supervised learning with manual object part annotations, which has shown promising results in classifying birds [9,3,10,11], dogs [18,5,6,10], and cars [19,4,20].”
3D Object Representations for Fine-Grained Categorization (2013, background): “Driven by real-life applications, the focus has so far mostly been on distinguishing animate categories, such as flowers [22], leaves [16], dog breeds [19, 23], and birds [9, 29, 36].”
Semantic segmentation using regions and parts (2012, methodology): “[29] use appearance similarity to expand top-down detections of heads to detect cats and dogs.”
Deformable Part Descriptors for Fine-Grained Recognition and Attribute Prediction (2013, methodology): “[36, 37] provide an alternate way of detecting basic-level category objects such as dogs and cats by using a Deformable Part Model [24] trained specifically on the head.”
The Ignorant Led by the Blind: A Hybrid Human–Machine Vision System for Fine-Grained Categorization (2014, methodology): “FGVC methods that incorporate a super-category detection model (Farrell et al. 2011; Wah et al. 2011; Parkhi et al. 2011; Zhang et al. 2012; Liu et al. 2012; Parkhi et al. 2012) (i.”