Combining randomization and discrimination for fine-grained image categorization

Yao, Bowen; Khosla, Aditya; Li, Feifei

doi:10.1109/cvpr.2011.5995368

Cited by 245 publications

(186 citation statements)

References 13 publications

Supporting

Mentioning

183

Contrasting

Unclassified

Order By: Relevance

“…The second way our work departs from previous work [20,32] is that we design a finegrained object class representation that captures variations in object shape and geometry rather than appearance, in order to match the object class of interest. To that end, we introduce two different variants of utilizing part detections as indicators of object geometry, of varying complexity.…”

Section: Introductionmentioning

confidence: 81%

“…The problem of fine-grained categorization is deemed challenging due to the need to capture subtle appearance differences between categories while at the same time maintaining robustness to intra-category variations induced by changes in pose and viewpoint. As a consequence, the focus of previous work has been mostly on object categories and methods that favor discrimination by strong local appearance cues (such as random color image patches for birds [32]) or global image statistics (such as color histograms for flowers [20]). In this setting, computer vision techniques could be shown to facilitate fine-grained categorization tasks that are difficult even for humans due to the sheer number and diversity of subordinate categories [3,20,28].…”

Section: Introductionmentioning

confidence: 99%

“…More recently, the recognition of finer-grained, subordinate categories is receiving increased attention [2,3,7,18,20,28,30,32,33]. The problem of fine-grained categorization is deemed challenging due to the need to capture subtle appearance differences between categories while at the same time maintaining robustness to intra-category variations induced by changes in pose and viewpoint.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Fine-Grained Categorization for 3D Scene Understanding

Stark¹,

Krause²,

Pepik³

et al. 2012

Procedings of the British Machine Vision Conference 2012

View full text Add to dashboard Cite

Fine-grained categorization of object classes is receiving increased attention, since it promises to automate classification tasks that are difficult even for humans, such as the distinction between different animal species. In this paper, we consider fine-grained categorization for a different reason: following the intuition that fine-grained categories encode metric information, we aim to generate metric constraints from fine-grained category predictions, for the benefit of 3D scene-understanding. To that end, we propose two novel methods for fine-grained classification, both based on part information, as well as a new fine-grained category data set of car types. We demonstrate superior performance of our methods to state-of-the-art classifiers, and show first promising results for estimating the depth of objects from fine-grained category predictions from a monocular camera.

show abstract

Section: Introductionmentioning

confidence: 81%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Fine-Grained Categorization for 3D Scene Understanding

Stark¹,

Krause²,

Pepik³

et al. 2012

Procedings of the British Machine Vision Conference 2012

View full text Add to dashboard Cite

show abstract

“…Even for a moderately sized image, the algorithm needs to sample and classify millions of rectangular boxes with arbitrary shapes, sizes or locations [11], which is computation intensive. In order to reduce computations, recent object detection approaches [12] use bottom-up saliency [13] to extract regions of probable objects in an image.…”

Section: Introductionmentioning

confidence: 99%

A classifier-guided approach for top-down salient object detection

Cholakkal

Johnson

Rajan

2016

Signal Processing: Image Communication

View full text Add to dashboard Cite

We propose a framework for top-down salient object detection that incorporates a tightly coupled image classification module. The classifier is trained on novel category-aware sparse codes computed on object dictionaries used for saliency modeling. A misclassification indicates that the corresponding saliency model is inaccurate. Hence, the classifier selects images for which the saliency models need to be updated. The category-aware sparse coding produces better image classification accuracy as compared to conventional sparse coding with a reduced computational complexity. A saliency-weighted max-pooling is proposed to improve image classification, which is further used to refine the saliency maps. Experimental results on Graz-02 and PASCAL VOC-07 datasets demonstrate the effectiveness of salient object detection. Although the role of the classifier is to support salient object detection, we evaluate its performance in image classification and also illustrate the utility of thresholded saliency maps for image segmentation.

show abstract

“…We model the spatio-temporal structure by exploiting the qualitative relationships between a pair of visual features. The proposed approach is inspired by [3,4]. The goal is to find a pair of visual features whose spatiotemporal relationships are discriminative enough, and temporally consistent for distinguishing various activities.…”

mentioning

confidence: 99%

Real-time Activity Recognition by Discerning Qualitative Relationships Between Randomly Chosen Visual Features

Behera¹,

Cohn²,

Hogg³

2014

Proceedings of the British Machine Vision Conference 2014

View full text Add to dashboard Cite

Motivation. Automatic recognition of human activities (or events) from video is important to many potential applications of computer vision. One of the most common approach is the bag-of-visual-features, which aggregate space-time features globally, from the entire video clip containing complete execution of a single activity. The bag-of-visual-features does not encode the spatio-temporal structure in the video. For this reason, there is a growing interest in modeling spatio-temporal structure between visual features in order to improve the results of activity recognition.The proposed framework. We model the spatio-temporal structure by exploiting the qualitative relationships between a pair of visual features. The proposed approach is inspired by [3,4]. The goal is to find a pair of visual features whose spatiotemporal relationships are discriminative enough, and temporally consistent for distinguishing various activities. The framework is applied to recognize activities from a continuous live video (egocentric view) of a person performing manipulative tasks in an industrial setup. In such environments, the purpose of activity recognition is to assist users by providing on-the-fly instructions from an automatic system that maintains an understanding of the on-going activities.In order to recognize activities in real-time, we propose a random forest with a discriminative Markov decision tree algorithm that considers a random subset of relational features at a time and Markov temporal structure that provides temporally smoothed output (Fig. 1). Our algorithm is different from conventional decision trees [2] and uses a linear SVM as a classifier at each nonterminal node and effectively explores temporal dependency at terminal nodes of the trees. We explicitly model the spatial relationships of left, right, top, bottom, very-near, near, far and very-far as well as temporal relationships of during, before and after between a pair of visual features (Fig. 2), which are selected randomly at the nonterminal nodes of a given Markov decision tree. Our hypothesis is that the proposed relationships are particularly suitable for detecting complex non-periodic manipulative tasks and can easily be applied to the existing visual descriptors such as SIFT, STIP, CUBOID and SURF.Growing discriminative Markov decision trees. Each tree is trained separately on a random subset of frames belonging to training videos. Learning proceeds recursively by splitting the training frames at internal nodes into the respective left and right subsets. This is done in the following four stages: randomly assign all frames from each activity class to a binary label; randomly sample a pair of visual words; compute the spatiotemporal relationships histogram h between them; and use a linear SVM to learn a binary split using the extracted h. The binary SVM at each internal node sends the frame to the left child if w T h ≤ 0 otherwise to the right child, where w is the set of weights learned through the linear SVM. Using an information gain criteria, ea...

show abstract

Combining randomization and discrimination for fine-grained image categorization

Cited by 245 publications

References 13 publications

Fine-Grained Categorization for 3D Scene Understanding

Fine-Grained Categorization for 3D Scene Understanding

A classifier-guided approach for top-down salient object detection

Real-time Activity Recognition by Discerning Qualitative Relationships Between Randomly Chosen Visual Features

Contact Info

Product

Resources

About