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

When considering person re-identification (re-ID) as a retrieval process, re-ranking is a critical step to improve its accuracy. Yet in the re-ID community, limited effort has been devoted to re-ranking, especially those fully automatic, unsupervised solutions. In this paper, we propose a k-reciprocal encoding method to re-rank the re-ID results. Our hypothesis is that if a gallery image is similar to the probe in the k-reciprocal nearest neighbors, it is more likely to be a true match. Specifically, given an image, a k-reciprocal feature is calculated by encoding its k-reciprocal nearest neighbors into a single vector, which is used for re-ranking under the Jaccard distance. The final distance is computed as the combination of the original distance and the Jaccard distance. Our re-ranking method does not require any human interaction or any labeled data, so it is applicable to large-scale datasets. Experiments on the large-scale Market-1501, CUHK03, MARS, and PRW datasets confirm the effectiveness of our method.

/pdf/re-ranking-person-re-identification-with-k-reciprocal-3erzmilgv1.pdf

Re-ranking Person Re-identification with k-Reciprocal Encoding

This paper develops a novel framework for semantic image retrieval based on the notion of a scene graph. Our scene graphs represent objects (“man”, “boat”), attributes of objects (“boat is white”) and relationships between objects (“man standing on boat”). We use these scene graphs as queries to retrieve semantically related images. To this end, we design a conditional random field model that reasons about possible groundings of scene graphs to test images. The likelihoods of these groundings are used as ranking scores for retrieval. We introduce a novel dataset of 5,000 human-generated scene graphs grounded to images and use this dataset to evaluate our method for image retrieval. In particular, we evaluate retrieval using full scene graphs and small scene subgraphs, and show that our method outperforms retrieval methods that use only objects or low-level image features. In addition, we show that our full model can be used to improve object localization compared to baseline methods.

/pdf/image-retrieval-using-scene-graphs-3qdk8c7ey7.pdf

Image retrieval using scene graphs

Person re-identification (re-ID) has become increasingly popular in the community due to its application and research significance. It aims at spotting a person of interest in other cameras. In the early days, hand-crafted algorithms and small-scale evaluation were predominantly reported. Recent years have witnessed the emergence of large-scale datasets and deep learning systems which make use of large data volumes. Considering different tasks, we classify most current re-ID methods into two classes, i.e., image-based and video-based; in both tasks, hand-crafted and deep learning systems will be reviewed. Moreover, two new re-ID tasks which are much closer to real-world applications are described and discussed, i.e., end-to-end re-ID and fast re-ID in very large galleries. This paper: 1) introduces the history of person re-ID and its relationship with image classification and instance retrieval; 2) surveys a broad selection of the hand-crafted systems and the large-scale methods in both image- and video-based re-ID; 3) describes critical future directions in end-to-end re-ID and fast retrieval in large galleries; and 4) finally briefs some important yet under-developed issues.

/pdf/person-re-identification-past-present-and-future-44l6xye7rx.pdf

Person Re-identification: Past, Present and Future

This paper introduces a simple yet effective method to improve visual word based image retrieval. Our method is based on an analysis of the k-reciprocal nearest neighbor structure in the image space. At query time the information obtained from this process is used to treat different parts of the ranked retrieval list with different distance measures. This leads effectively to a re-ranking of retrieved images. As we will show, this has two benefits: first, using different similarity measures for different parts of the ranked list allows for compensation of the “curse of dimensionality”. Second, it allows for dealing with the uneven distribution of images in the data space. Dealing with both challenges has very beneficial effect on retrieval accuracy. Furthermore, a major part of the process happens offline, so it does not affect speed at retrieval time. Finally, the method operates on the bag-of-words level only, thus it could be combined with any additional measures on e.g. either descriptor level or feature geometry making room for further improvement. We evaluate our approach on common object retrieval benchmarks and demonstrate a significant improvement over standard bag-of-words retrieval.

Hello neighbor: Accurate object retrieval with k-reciprocal nearest neighbors

Many recent object retrieval systems rely on local features for describing an image. The similarity between a pair of images is measured by aggregating the similarity between their corresponding local features. In this paper we present a probabilistic framework for modeling the feature to feature similarity measure. We then derive a query adaptive distance which is appropriate for global similarity evaluation. Furthermore, we propose a function to score the individual contributions into an image to image similarity within the probabilistic framework. Experimental results show that our method improves the retrieval accuracy significantly and consistently. Moreover, our result compares favorably to the state-of-the-art.

/pdf/query-adaptive-similarity-for-large-scale-object-retrieval-hmv420psc5.pdf

Query Adaptive Similarity for Large Scale Object Retrieval

We study how to leverage Web images to augment human-curated object detection datasets. Our approach is two-pronged. On the one hand, we retrieve Web images by image-to-image search, which incurs less domain shift from the curated data than other search methods. The Web images are diverse, supplying a wide variety of object poses, appearances, their interactions with the context, etc. On the other hand, we propose a novel learning method motivated by two parallel lines of work that explore unlabeled data for image classification: self-training and self-supervised learning. They fail to improve object detectors in their vanilla forms due to the domain gap between the Web images and curated datasets. To tackle this challenge, we propose a selective net to rectify the supervision signals in Web images. It not only identifies positive bounding boxes but also creates a safe zone for mining hard negative boxes. We report state-of-the-art results on detecting backpacks and chairs from everyday scenes, along with other challenging object classes.

Improving Object Detection with Selective Self-supervised Self-training

Learning to localize and name object instances is a fundamental problem in vision, but state-of-the-art approaches rely on expensive bounding box supervision. While weakly supervised detection (WSOD) methods relax the need for boxes to that of image-level annotations, even cheaper supervision is naturally available in the form of unstructured textual descriptions that users may freely provide when uploading image content. However, straightforward approaches to using such data for WSOD wastefully discard captions that do not exactly match object names. Instead, we show how to squeeze the most information out of these captions by training a text-only classifier that generalizes beyond dataset boundaries. Our discovery provides an opportunity for learning detection models from noisy but more abundant and freely-available caption data. We also validate our model on three classic object detection benchmarks and achieve state-of-the-art WSOD performance. Our code is available at https://github.com/yekeren/Cap2Det.

/pdf/cap2det-learning-to-amplify-weak-caption-supervision-for-1cqvlyk567.pdf

Cap2Det: Learning to Amplify Weak Caption Supervision for Object Detection

Learning to localize and name object instances is a fundamental problem in vision, but state-of-the-art approaches rely on expensive bounding box supervision. While weakly supervised detection (WSOD) methods relax the need for boxes to that of image-level annotations, even cheaper supervision is naturally available in the form of unstructured textual descriptions that users may freely provide when uploading image content. However, straightforward approaches to using such data for WSOD wastefully discard captions that do not exactly match object names. Instead, we show how to squeeze the most information out of these captions by training a text-only classifier that generalizes beyond dataset boundaries. Our discovery provides an opportunity for learning detection models from noisy but more abundant and freely-available caption data. We also validate our model on three classic object detection benchmarks and achieve state-of-the-art WSOD performance. Our code is available at this https URL.

Danfeng Qin

Papers

Hello neighbor: Accurate object retrieval with k-reciprocal nearest neighbors

Query Adaptive Similarity for Large Scale Object Retrieval

Improving Object Detection with Selective Self-supervised Self-training

Cap2Det: Learning to Amplify Weak Caption Supervision for Object Detection

Cap2Det: Learning to Amplify Weak Caption Supervision for Object Detection