Efficient Object Detection and Segmentation for Fine-Grained Recognition

By Anelia Angelova, Shenghuo Zhu. 2013

235 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Plant Science

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

In Plant Science

Citations in the corpus

CNN Features Off-the-Shelf: An Astounding Baseline for Recognition (2014, neutral): “4 Dense HOG+Coding+Pooling[2] w/o seg 76.”
Part-Based R-CNNs for Fine-Grained Category Detection (2014, background): “Recently, a large body of computer vision research has focused on the fine-grained classificationproblem in a number of domains, such as animal breeds or species [16, 25, 30, 32, 36, 45], plant species [1, 2, 5, 33, 34, 38], and man-made objects [31, 39].”
Deep Image: Scaling up Image Recognition (2015, methodology): “h as different types of birds and flowers, which is different from generic classification. Much work has been devoted on the learning of object parts that benefits from the alignment and segmentation [1, 8, 6, 18]. Current state-of-the-art results for bird species recognition have been achieved in [”
Neural Activation Constellations: Unsupervised Part Model Discovery with Convolutional Networks (2015, methodology): “Similar to the CUB200-2011 dataset, there is a clear advantage of using parts selected by our approach with an accuracy of 76.3%.”
Bird Species Categorization Using Pose Normalized Deep Convolutional Nets (2014, background): “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).”
Coarse-to-Fine Description for Fine-Grained Visual Categorization (2016, methodology): “Angelova and Zhu [29] propose to segment the foreground without the bounding box using a region-guided detection and segmentation algorithm.”
Weakly Supervised Learning of Part Selection Model with Spatial Constraints for Fine-Grained Image Classification (2017, background): “Fine-grained image classification is an extremely challenging task, which aims to distinguish the objects in subordinate classes, such as bird types (Wah et al. 2011), dog species (Khosla et al. 2011), plant breeds (Angelova and Zhu 2013) ∗Corresponding author.”
Multiple Granularity Descriptors for Fine-Grained Categorization (2015, background): “To tackle the issue of the insufficient discriminative power for fine-grained categorization, some of the existing works focused on feature encoding, such as partbased or pose normalized frameworks[5][36][38][37] and segmentation-based methods[1][7][14].”
Multi-scale pyramid pooling for deep convolutional representation (2015, unknown): “Angelova and Zhu [1] ’13 Seg+DenseHoG +LLC+MaxPooling Yes.”
Nonparametric Part Transfer for Fine-Grained Recognition (2014, methodology): “(DPD) [42], part-based one-vs-one features (POOF) [3], pooling-invariant image feature learning (PDL) [17], the template learning approach of [38], the segmentation technique of [1], and the Bubblebank method of [9].”
Birdsnap: Large-Scale Fine-Grained Visual Categorization of Birds (2014, background): “Methods have been demonstrated in many domains, from shoes [5] to motorcycles [13], but biological categories–species and breeds– have been especially well-studied, with work tackling subcategory recognition of flowers [25], trees [14], dogs [1], butterflies [8], birds [4], and insects [17].”
Which Looks Like Which: Exploring Inter-class Relationships in Fine-Grained Visual Categorization (2014, methodology): “However, the approaches of [1,14] include computationally expensive segmentation/detection, and [17] requires additional human inputs, which is therefore excluded from the table.”
Building a bird recognition app and large scale dataset with citizen scientists: The fine print in fine-grained dataset collection (2015, background): “Various domains have already had datasets introduced including Birds (the CUB-200 [35] and recently announced Birdsnap [2] datasets), Flowers [25, 1], Dogs and Cats [15, 27, 21], Stoneflies [24], Butterflies [19] and Fish [4] along with man-made domains such as Airplanes [23], Cars [16], and Shoes[3”