Max-Margin Boltzmann Machines for Object Segmentation

Yang, Jimei; Safar, Simon; Yang, Ming–Hsuan

doi:10.1109/cvpr.2014.48

Cited by 19 publications

(23 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Caltech-UCSD Birds 200 Caltech-UCSD Birds 200 (Welinder et al 2010) is a dataset with 6033 images of birds with 128 × 128 resolutions, split into 3000 train and 3033 test images. As a second source, we use segmentation masks provided by (Yang, Safar, and Yang 2014). On this dataset we assess whether learning with multiple modalities can be advantageous in scenarios where we are interested only in one particular modality.…”

Section: Learning and Inference Of Shared Representations For Structumentioning

confidence: 99%

Multi-Source Neural Variational Inference

Kurle

Günnemann

Smagt

2019

AAAI

View full text Add to dashboard Cite

Learning from multiple sources of information is an important problem in machine-learning research. The key challenges are learning representations and formulating inference methods that take into account the complementarity and redundancy of various information sources. In this paper we formulate a variational autoencoder based multi-source learning framework in which each encoder is conditioned on a different information source. This allows us to relate the sources via the shared latent variables by computing divergence measures between individual source’s posterior approximations. We explore a variety of options to learn these encoders and to integrate the beliefs they compute into a consistent posterior approximation. We visualise learned beliefs on a toy dataset and evaluate our methods for learning shared representations and structured output prediction, showing trade-offs of learning separate encoders for each information source. Furthermore, we demonstrate how conflict detection and redundancy can increase robustness of inference in a multi-source setting.

show abstract

Section: Learning and Inference Of Shared Representations For Structumentioning

confidence: 99%

Multi-Source Neural Variational Inference

Kurle

Günnemann

Smagt

2019

AAAI

View full text Add to dashboard Cite

show abstract

“…The object is treated as a cluster of pixels in the same category instead of a whole, which usually ignores the overall appearances and shapes of the objects. Some other models try to make structured label prediction by using RBM, like CHOPPS (Li, Tarlow, and Zemel 2013), GLOC (Kae et al 2013) and MMRBM (Yang, Safar, and Yang 2014). However, the object being recognizable is never under consideration in these models, nor are they capable of recognition.…”

Section: Simultaneous Segmentation and Classificationmentioning

confidence: 99%

“…For comparison, we evaluate the fore-and background segmentation performances by some existing models that employ RBM, such as GLOC (Kae et al 2013), CHOPPS (Li, Tarlow, and Zemel 2013) and MMBM (Yang, Safar, and Yang 2014), and DeepLab (Chen et al 2016). We also tested the framework Fig.3 implemented with a standard CNN encoder (and the classification layer), as the baseline model, following (Sabour, Frosst, and Hinton 2017).…”

Section: Experiments Signs and Logosmentioning

confidence: 99%

A Framework to Coordinate Segmentation and Recognition

Huang

Zheng

et al. 2019

AAAI

View full text Add to dashboard Cite

A novel coordination framework between the segmentation and the recognition is proposed, to conduct the two tasks collaboratively and iteratively. To accomplish the cooperation, objects are expressed in two aspects: shape and appearance, which are learned and leveraged as constraints to the segmentation so that the object segmentation mask will be consistent with the object regions in the image and the knowledge we have. For the shape, a bottom-top-bottom pathway is built using an encoder-decoder network with capsule neurons, where the encoder extracts the features of the shape that used for recognition and the decoder generates reference shapes according to these features and the recognition result. During this procedure, capsule neurons can parse the existence of the object and cope with the interference in the segmentation. The appearance knowledge is utilized in another pathway to assist the segmentation processing. Both the shape and appearance information are dependent on the recognition result, thus allowing the classifier to convey object information to the segmenter. Experiments demonstrate the effectiveness of our framework and model in collaboratively segmenting and recognizing objects that can be recognized using their shapes/shape-patterns.

show abstract

“…We extract color information from the foreground region based on the results using an max-margin segmentation method [30]. As large granular spatial decomposition is likely to cause misalignment due to pose changes, we follow recent schemes for re-identification [24,35] and partition an image into six horizontal stripes.…”

Section: Representationmentioning

confidence: 99%

An Ensemble Color Model for Human Re-identification

Liu

Yang

2015

2015 IEEE Winter Conference on Applications of Computer Vision

Self Cite

View full text Add to dashboard Cite

Appearance-based human re-identification is challenging due to different camera characteristics, varying lighting conditions, pose variations across camera views, etc. Recent studies have revealed that color information plays a critical role on performance. However, two problems remain unclear: (1) how do different color descriptors perform under the same scene in re-identification problem? and (2) how can we combine these descriptors without losing their invariance property and distinctiveness power? In this paper, we propose a novel ensemble model that combines different color descriptors in the decision level through metric learning. Experiments show that the proposed system significantly outperforms state-of-the-art algorithms on two challenging datasets (VIPeR and PRID 450S). We have improved the Rank 1 recognition rate on VIPeR dataset by 8.7%.

show abstract

Max-Margin Boltzmann Machines for Object Segmentation

Cited by 19 publications

References 23 publications

Multi-Source Neural Variational Inference

Multi-Source Neural Variational Inference

A Framework to Coordinate Segmentation and Recognition

An Ensemble Color Model for Human Re-identification

Contact Info

Product

Resources

About