High-dimensional signature compression for large-scale image classification

By Jorge Sánchez, Florent Perronnin. 2011

362 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Efficiency & Compression

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Trevor Darrell
2. Luc Van Gool
3. Andrew Zisserman
4. Li Fei-Fei
5. Bernt Schiele
6. Cordelia Schmid
7. Yoshua Bengio
8. Mohit Bansal

In Computer Vision and Pattern Recognition

1. Luc Van Gool
2. Dacheng Tao
3. Xiaogang Wang
4. Andrew Zisserman
5. Andrea Vedaldi
6. Trevor Darrell
7. Yi Yang
8. Ming-Hsuan Yang

In Efficiency & Compression

1. Luc Van Gool
2. Andrea Vedaldi
3. Cordelia Schmid
4. Victor S. Lempitsky
5. Quoc V. Le
6. Kaiming He
7. Andrew Zisserman
8. Sanjiv Kumar

Citations in the corpus

• ImageNet Large Scale Visual Recognition Challenge (2014, methodology): “Im a g eN et L a rg e S ca le V isu a l R eco g n itio n C h a llen g e 1 7 ILSVRC 2010 Codename CLS LOC Insitutions Contributors and references Hminmax 54.4 Massachusetts Institute of Technology Jim Mutch, Sharat Chikkerur, Hristo Paskov, Ruslan Salakhutdinov, Stan Bileschi, Hueihan Jhuang IBM 70.1”
• Improving neural networks by preventing co-adaptation of feature detectors (2012, neutral): “7% [16].”
• Building high-level features using large scale unsupervised learning (2011, methodology): “We followed the experimental protocols specified by (Deng et al., 2010; Sanchez & Perronnin, 2011), in which, the datasets are randomly split into two halves for training and validation.”
• Scaling the Scattering Transform: Deep Hybrid Networks (2017, neutral): “On the other hand prior to 2012 local encoding meth-ods led to state of the art performance on large scale visual recognition tasks [30].”
• Label-Embedding for Image Classification (2015, methodology): “This includes work on patch encoding (see [40] for a recent comparison), on kernel-based methods [41] with a recent focus on explicit embeddings [42], [43], on dimensionality reduction [41] and on compression [44], [45], [46].”
• Blessing of Dimensionality: High-Dimensional Feature and Its Efficient Compression for Face Verification (2013, background): “[31] reported on the significance of high-dimensional features in large-scale image classification.”
• Circulant Binary Embedding (2014, methodology): “The advantage is to save on storage allowing even large scale datasets to fit in memory (Li et al., 2011; Sánchez & Perronnin, 2011).”
• Deep Convolutional Neural Networks for Image Classification: A Comprehensive Review (2017, background): “Downloaded from http://www.mitpressjournals.org/doi/pdf/10.1162/neco_a_00990 by guest on 04 June 2021 Lin et al., 2011; Sánchez & Perronnin, 2011), as well as an approximate correlation between classification performance and network depth (see section 5.5.4).”
• Hedging your bets: Optimizing accuracy-specificity trade-offs in large scale visual recognition (2012, background): “Our work is also inspired by an emerging trend in computer vision studying large scale visual recognition [19, 27, 13, 12, 31, 7, 26, 24].”
• Fisher vectors meet Neural Networks: A hybrid classification architecture (2015, methodology): “In 2010-2011, the leading approaches to ILSVRC [43, 31] were based on the Fisher Vector [38, 39] (FV) or the closely related Super Vector (SV) [57].”
• Transformation Pursuit for Image Classification (2014, methodology): “We then use PQ compression [13] which was shown to yield an almost-negligible loss of performance in large-scale classification [24].”
• Efficient feature extraction, encoding and classification for action recognition (positive): “We next investigate Fisher vector (FV) encoding [23] and show improved action recognition while using fast linear classifiers.”
• Efficient Feature Extraction, Encoding, and Classification for Action Recognition (2014, methodology): “We next investigate Fisher vector (FV) encoding [23] and show improved action recognition while using fast linear classifiers.”
• Vision-Language Models for Vision Tasks: A Survey (2023, background): “Before the deep learning era [7], visual recognition studies rely heavily on feature engineering with hand-crafted features [13], [45], [46], [47], [48], [49], [50], [51] and lightweight learning models [10], [11], [12] that classify the handcrafted features into pre-defined semantic categories.”
• Fisher Vector Faces in the Wild (2013, background): “Dense feature extraction is an essential component of many state-of-the-art image classification methods [18, 23, 27].”