Recent results indicate that the generic descriptors extracted from the convolutional neural networks are very powerful. This paper adds to the mounting evidence that this is indeed the case. We report on a series of experiments conducted for different recognition tasks using the publicly available code and model of the \overfeat network which was trained to perform object classification on ILSVRC13. We use features extracted from the \overfeat network as a generic image representation to tackle the diverse range of recognition tasks of object image classification, scene recognition, fine grained recognition, attribute detection and image retrieval applied to a diverse set of datasets. We selected these tasks and datasets as they gradually move further away from the original task and data the \overfeat network was trained to solve. Astonishingly, we report consistent superior results compared to the highly tuned state-of-the-art systems in all the visual classification tasks on various datasets. For instance retrieval it consistently outperforms low memory footprint methods except for sculptures dataset. The results are achieved using a linear SVM classifier (or $L2$ distance in case of retrieval) applied to a feature representation of size 4096 extracted from a layer in the net. The representations are further modified using simple augmentation techniques e.g. jittering. The results strongly suggest that features obtained from deep learning with convolutional nets should be the primary candidate in most visual recognition tasks.

CNN Features off-the-shelf: an Astounding Baseline for Recognition

Recent results indicate that the generic descriptors extracted from the convolutional neural networks are very powerful. This paper adds to the mounting evidence that this is indeed the case. We report on a series of experiments conducted for different recognition tasks using the publicly available code and model of the OverFeat network which was trained to perform object classification on ILSVRC13. We use features extracted from the OverFeat network as a generic image representation to tackle the diverse range of recognition tasks of object image classification, scene recognition, fine grained recognition, attribute detection and image retrieval applied to a diverse set of datasets. We selected these tasks and datasets as they gradually move further away from the original task and data the OverFeat network was trained to solve. Astonishingly, we report consistent superior results compared to the highly tuned state-of-the-art systems in all the visual classification tasks on various datasets. For instance retrieval it consistently outperforms low memory footprint methods except for sculptures dataset. The results are achieved using a linear SVM classifier (or L2 distance in case of retrieval) applied to a feature representation of size 4096 extracted from a layer in the net. The representations are further modified using simple augmentation techniques e.g. jittering. The results strongly suggest that features obtained from deep learning with convolutional nets should be the primary candidate in most visual recognition tasks.

/pdf/cnn-features-off-the-shelf-an-astounding-baseline-for-3bzk7sak39.pdf

CNN Features Off-the-Shelf: An Astounding Baseline for Recognition

We tackle the problem of large scale visual place recognition, where the task is to quickly and accurately recognize the location of a given query photograph. We present the following three principal contributions. First, we develop a convolutional neural network (CNN) architecture that is trainable in an end-to-end manner directly for the place recognition task. The main component of this architecture, NetVLAD, is a new generalized VLAD layer, inspired by the "Vector of Locally Aggregated Descriptors" image representation commonly used in image retrieval. The layer is readily pluggable into any CNN architecture and amenable to training via backpropagation. Second, we develop a training procedure, based on a new weakly supervised ranking loss, to learn parameters of the architecture in an end-to-end manner from images depicting the same places over time downloaded from Google Street View Time Machine. Finally, we show that the proposed architecture significantly outperforms non-learnt image representations and off-the-shelf CNN descriptors on two challenging place recognition benchmarks, and improves over current state of-the-art compact image representations on standard image retrieval benchmarks.

/pdf/netvlad-cnn-architecture-for-weakly-supervised-place-jj18zqn7c8.pdf

NetVLAD: CNN Architecture for Weakly Supervised Place Recognition

The objective of this work is object retrieval in large scale image datasets, where the object is specified by an image query and retrieval should be immediate at run time in the manner of Video Google [28]. We make the following three contributions: (i) a new method to compare SIFT descriptors (RootSIFT) which yields superior performance without increasing processing or storage requirements; (ii) a novel method for query expansion where a richer model for the query is learnt discriminatively in a form suited to immediate retrieval through efficient use of the inverted index; (iii) an improvement of the image augmentation method proposed by Turcot and Lowe [29], where only the augmenting features which are spatially consistent with the augmented image are kept. We evaluate these three methods over a number of standard benchmark datasets (Oxford Buildings 5k and 105k, and Paris 6k) and demonstrate substantial improvements in retrieval performance whilst maintaining immediate retrieval speeds. Combining these complementary methods achieves a new state-of-the-art performance on these datasets.

/pdf/three-things-everyone-should-know-to-improve-object-22pxpsf0yx.pdf

Three things everyone should know to improve object retrieval

Visual place recognition is a challenging problem due to the vast range of ways in which the appearance of real-world places can vary. In recent years, improvements in visual sensing capabilities, an ever-increasing focus on long-term mobile robot autonomy, and the ability to draw on state-of-the-art research in other disciplines—particularly recognition in computer vision and animal navigation in neuroscience—have all contributed to significant advances in visual place recognition systems. This paper presents a survey of the visual place recognition research landscape. We start by introducing the concepts behind place recognition—the role of place recognition in the animal kingdom, how a “place” is defined in a robotics context, and the major components of a place recognition system. Long-term robot operations have revealed that changing appearance can be a significant factor in visual place recognition failure; therefore, we discuss how place recognition solutions can implicitly or explicitly account for appearance change within the environment. Finally, we close with a discussion on the future of visual place recognition, in particular with respect to the rapid advances being made in the related fields of deep learning, semantic scene understanding, and video description.

/pdf/visual-place-recognition-a-survey-d2xtkdlp55.pdf

Visual Place Recognition: A Survey

Most effective particular object and image retrieval approaches are based on the bag-of-words (BoW) model. All state-of-the-art retrieval results have been achieved by methods that include a query expansion that brings a significant boost in performance. We introduce three extensions to automatic query expansion: (i) a method capable of preventing tf-idf failure caused by the presence of sets of correlated features (confusers), (ii) an improved spatial verification and re-ranking step that incrementally builds a statistical model of the query object and (iii) we learn relevant spatial context to boost retrieval performance. The three improvements of query expansion were evaluated on standard Paris and Oxford datasets according to a standard protocol, and state-of-the-art results were achieved.

Total recall II: Query expansion revisited

A novel similarity measure for bag-of-words type large scale image retrieval is presented. The similarity function is learned in an unsupervised manner, requires no extra space over the standard bag-of-words method and is more discriminative than both L2-based soft assignment and Hamming embedding.

We show experimentally that the novel similarity function achieves mean average precision that is superior to any result published in the literature on a number of standard datasets. At the same time, retrieval with the proposed similarity function is faster than the reference method.

/pdf/learning-a-fine-vocabulary-3otwpr8gcd.pdf

Learning a fine vocabulary

A novel similarity measure for bag-of-words type large scale image retrieval is presented. The similarity function is learned in an unsupervised manner, requires no extra space over the standard bag-of-words method and is more discriminative than both L2-based soft assignment and Hamming embedding. The novel similarity function achieves mean average precision that is superior to any result published in the literature on the standard Oxford 5k, Oxford 105k and Paris datasets/protocols. We study the effect of a fine quantization and very large vocabularies (up to 64 million words) and show that the performance of specific object retrieval increases with the size of the vocabulary. This observation is in contradiction with previously published results. We further demonstrate that the large vocabularies increase the speed of the tf-idf scoring step.

Learning Vocabularies over a Fine Quantization

Image processing for autonomous robots is nowadays very popular. In our paper, we show a method how to extract information from a camera attached on a robot to acquire locations of targets the robot is looking for. We apply maximally stable colour regions (a method originally used for image matching) to obtain an initial set of candidate regions. This set is then filtered using application specific filters to find only the regions that correspond to scene elements of interest. The presented method has been applied in practice and performs well even under varying illumination conditions since it does not rely heavily on manually specified colour thresholds. Furthermore, no colour calibration is needed.

/pdf/detecting-scene-elements-using-maximally-stable-colour-55ih78c0mj.pdf

Detecting Scene Elements Using Maximally Stable Colour Regions

Two new methods for large scale image retrieval are proposed, showing that the classical ranking of images based on similarity addresses only one of possible user requirements. The novel retrieval methods add zoom-in and zoom-out capabilities and answer the "What is this?" and "Where is this?" questions.

The functionality is obtained by modifying the scoring and ranking functions of a standard bag-of-words image retrieval pipeline. We show the importance of the DAAT scoring and query expansion for recall of zoomed images.

The proposed methods were tested on a standard large annotated image dataset together with images of Sagrada Familia and 100000 image confusers downloaded from Flickr. For completeness, we present in detail components of image retrieval pipelines in state-of-the-art systems. Finally, open problems related to zoom-in and zoom-out queries are discussed.

/pdf/image-retrieval-for-online-browsing-in-large-image-4ls7w334yf.pdf

Andrej Mikulík

Papers

Total recall II: Query expansion revisited

Learning a fine vocabulary

Learning Vocabularies over a Fine Quantization

Detecting Scene Elements Using Maximally Stable Colour Regions

Image Retrieval for Online Browsing in Large Image Collections