• Corpus ID: 284030

PiCoDes: Learning a Compact Code for Novel-Category Recognition

@inproceedings{Bergamo2011PiCoDesLA,
  title={PiCoDes: Learning a Compact Code for Novel-Category Recognition},
  author={Alessandro Bergamo and Lorenzo Torresani and Andrew W. Fitzgibbon},
  booktitle={NIPS},
  year={2011}
}
We introduce PICODES: a very compact image descriptor which nevertheless allows high performance on object category recognition. In particular, we address novel-category recognition: the task of defining indexing structures and image representations which enable a large collection of images to be searched for an object category that was not known when the index was built. Instead, the training images defining the category are supplied at query time. We explicitly learn descriptors of a given… 

Figures from this paper

Classemes: A Compact Image Descriptor for Efficient Novel-Class Recognition and Search
TLDR
This chapter reviews a method that addresses the problem of object class recognition in large image collections by learning a compact image descriptor - classemes - yielding good categorization accuracy even with efficient linear classifiers.
Large-Margin Learning of Compact Binary Image Encodings
TLDR
A novel approach to learning a compact binary encoding, which exploits both pairwise proximity and class-label information on training data set, and achieves an accuracy comparable to, and in some cases better than, the visual descriptor in the original space despite being significantly more compact.
Classemes and Other Classifier-Based Features for Efficient Object Categorization
This paper describes compact image descriptors enabling accurate object categorization with linear classification models, which offer the advantage of being efficient to both train and test. The
Meta-class features for large-scale object categorization on a budget
TLDR
A novel image descriptor enabling accurate object categorization even with linear models and it is demonstrated that simple linear SVMs trained on the authors' meta-class descriptor significantly outperform the best known classifier on the Caltech256 benchmark.
VISOR: Towards On-the-Fly Large-Scale Object Category Retrieval
TLDR
This paper compares state of the art encoding methods and introduces a novel cascade retrieval architecture and shows that new visual concepts can be learnt on-the-fly, given a text description, and so images of that category can be retrieved from the dataset in realtime.
Attribute Discovery via Predictable Discriminative Binary Codes
TLDR
In this work, each image claims its own code in a way that maintains discrimination while being predictable from visual data, and this method outperforms state-of-the-art binary code methods on this large scale dataset.
Contributions to large-scale learning for image classification. (Contributions à l'apprentissage grande échelle pour la classification d'images)
TLDR
This thesis proposes a benchmark of learning algorithms for large scale image classification, and proposes a novel learning algorithm based on label embedding for learning with scarce training data that outperforms the state-of-the-art for zero-shot learning.
Few-Shot Hash Learning for Image Retrieval
TLDR
This paper addresses the problem of few-shot hash learning, in the spirit of one-shot learning in image recognition and classification and early work on locality sensitive hashing, based on the insight that universal hash functions can be learned off-line from unlabeled data because of the information implicit in the density structure of a discriminative feature space.
Learning Compact Visual Attributes for Large-Scale Image Classification
TLDR
A new compact way to represent images, based on attributes, which allows to obtain image signatures that are typically 103 times smaller than the FV+SPM combination without significant loss of performance is proposed.
Iterative Quantization: A Procrustean Approach to Learning Binary Codes for Large-Scale Image Retrieval
TLDR
This paper addresses the problem of learning similarity-preserving binary codes for efficient similarity search in large-scale image collections by proposing a simple and efficient alternating minimization algorithm, dubbed iterative quantization (ITQ), and demonstrating an application of ITQ to learning binary attributes or "classemes" on the ImageNet data set.
...
...

References

SHOWING 1-10 OF 32 REFERENCES
Efficient Object Category Recognition Using Classemes
TLDR
A new descriptor for images is introduced which allows the construction of efficient and compact classifiers with good accuracy on object category recognition, and allows object-category queries to be made against image databases using efficient classifiers such as linear support vector machines.
Small codes and large image databases for recognition
TLDR
The goal is to develop efficient image search and scene matching techniques that are not only fast, but also require very little memory, enabling their use on standard hardware or even on handheld devices.
Learning to detect unseen object classes by between-class attribute transfer
TLDR
The experiments show that by using an attribute layer it is indeed possible to build a learning object detection system that does not require any training images of the target classes, and assembled a new large-scale dataset, “Animals with Attributes”, of over 30,000 animal images that match the 50 classes in Osherson's classic table of how strongly humans associate 85 semantic attributes with animal classes.
Aggregating local descriptors into a compact image representation
TLDR
This work proposes a simple yet efficient way of aggregating local image descriptors into a vector of limited dimension, which can be viewed as a simplification of the Fisher kernel representation, and shows how to jointly optimize the dimension reduction and the indexing algorithm.
Kernelized locality-sensitive hashing for scalable image search
  • B. Kulis, K. Grauman
  • Computer Science
    2009 IEEE 12th International Conference on Computer Vision
  • 2009
TLDR
It is shown how to generalize locality-sensitive hashing to accommodate arbitrary kernel functions, making it possible to preserve the algorithm's sub-linear time similarity search guarantees for a wide class of useful similarity functions.
Combining attributes and Fisher vectors for efficient image retrieval
TLDR
It is demonstrated that retrieving images of particular objects based on attribute vectors gives results comparable to the state of the art, and that attribute features combined with Fisher vectors improve the performance and that combined image features can supplement text features.
On feature combination for multiclass object classification
  • P. Gehler, S. Nowozin
  • Computer Science
    2009 IEEE 12th International Conference on Computer Vision
  • 2009
TLDR
Several models that aim at learning the correct weighting of different features from training data are studied, including multiple kernel learning as well as simple baseline methods and ensemble methods inspired by Boosting are derived.
Describing objects by their attributes
TLDR
This paper proposes to shift the goal of recognition from naming to describing, and introduces a novel feature selection method for learning attributes that generalize well across categories.
Similarity metrics for categorization: From monolithic to category specific
TLDR
This paper presents an algorithm that learns a few similarity metrics, while simultaneously grouping categories together and assigning one of these metrics to each group and presents promising results and shows how the learned metrics generalize to novel categories.
Near Duplicate Image Detection: min-Hash and tf-idf Weighting
TLDR
This paper proposes two novel image similarity measures for fast indexing via locality sensitive hashing and an efficient way of exploiting more sophisticated similarity measures that have proven to be essential in image / particular object retrieval.
...
...