We present a new dataset with the goal of advancing the state-of-the-art in object recognition by placing the question of object recognition in the context of the broader question of scene understanding. This is achieved by gathering images of complex everyday scenes containing common objects in their natural context. Objects are labeled using per-instance segmentations to aid in precise object localization. Our dataset contains photos of 91 objects types that would be easily recognizable by a 4 year old. With a total of 2.5 million labeled instances in 328k images, the creation of our dataset drew upon extensive crowd worker involvement via novel user interfaces for category detection, instance spotting and instance segmentation. We present a detailed statistical analysis of the dataset in comparison to PASCAL, ImageNet, and SUN. Finally, we provide baseline performance analysis for bounding box and segmentation detection results using a Deformable Parts Model.

/pdf/microsoft-coco-common-objects-in-context-55ihxq1zt5.pdf

Microsoft COCO: Common Objects in Context

Convolutional Neural Networks define an exceptionally powerful class of models, but are still limited by the lack of ability to be spatially invariant to the input data in a computationally and parameter efficient manner. In this work we introduce a new learnable module, the Spatial Transformer, which explicitly allows the spatial manipulation of data within the network. This differentiable module can be inserted into existing convolutional architectures, giving neural networks the ability to actively spatially transform feature maps, conditional on the feature map itself, without any extra training supervision or modification to the optimisation process. We show that the use of spatial transformers results in models which learn invariance to translation, scale, rotation and more generic warping, resulting in state-of-the-art performance on several benchmarks, and for a number of classes of transformations.

/pdf/spatial-transformer-networks-459aor1dlh.pdf

Spatial transformer networks

In this work, we revisit the global average pooling layer proposed in [13], and shed light on how it explicitly enables the convolutional neural network (CNN) to have remarkable localization ability despite being trained on imagelevel labels. While this technique was previously proposed as a means for regularizing training, we find that it actually builds a generic localizable deep representation that exposes the implicit attention of CNNs on an image. Despite the apparent simplicity of global average pooling, we are able to achieve 37.1% top-5 error for object localization on ILSVRC 2014 without training on any bounding box annotation. We demonstrate in a variety of experiments that our network is able to localize the discriminative image regions despite just being trained for solving classification task1.

/pdf/learning-deep-features-for-discriminative-localization-2t8moexmea.pdf

Learning Deep Features for Discriminative Localization

We propose Prototypical Networks for the problem of few-shot classification, where a classifier must generalize to new classes not seen in the training set, given only a small number of examples of each new class. Prototypical Networks learn a metric space in which classification can be performed by computing distances to prototype representations of each class. Compared to recent approaches for few-shot learning, they reflect a simpler inductive bias that is beneficial in this limited-data regime, and achieve excellent results. We provide an analysis showing that some simple design decisions can yield substantial improvements over recent approaches involving complicated architectural choices and meta-learning. We further extend Prototypical Networks to zero-shot learning and achieve state-of-the-art results on the CU-Birds dataset.

/pdf/prototypical-networks-for-few-shot-learning-2l18ppn4sw.pdf

Prototypical Networks for Few-shot Learning

In this work, we revisit the global average pooling layer proposed in [13], and shed light on how it explicitly enables the convolutional neural network to have remarkable localization ability despite being trained on image-level labels. While this technique was previously proposed as a means for regularizing training, we find that it actually builds a generic localizable deep representation that can be applied to a variety of tasks. Despite the apparent simplicity of global average pooling, we are able to achieve 37.1% top-5 error for object localization on ILSVRC 2014, which is remarkably close to the 34.2% top-5 error achieved by a fully supervised CNN approach. We demonstrate that our network is able to localize the discriminative image regions on a variety of tasks despite not being trained for them

CUB-200-2011 is an extended version of CUB-200 [7], a challenging dataset of 200 bird species. The extended version roughly doubles the number of images per category and adds new part localization annotations. All images are annotated with bounding boxes, part locations, and at- tribute labels. Images and annotations were filtered by mul- tiple users of Mechanical Turk. We introduce benchmarks and baseline experiments for multi-class categorization and part localization.

/pdf/the-caltech-ucsd-birds-200-2011-dataset-430natao92.pdf

The Caltech-UCSD Birds-200-2011 Dataset

Caltech-UCSD Birds 200 (CUB-200) is a challenging image dataset annotated with 200 bird species. It was created to enable the study of subordinate categorization, which is not possible with other popular datasets that focus on basic level categories (such as PASCAL VOC, Caltech-101, etc). The images were downloaded from the website Flickr and filtered by workers on Amazon Mechanical Turk. Each image is annotated with a bounding box, a rough bird segmentation, and a set of attribute labels.

Caltech-UCSD Birds 200

We present an interactive, hybrid human-computer method for object classification. The method applies to classes of objects that are recognizable by people with appropriate expertise (e.g., animal species or airplane model), but not (in general) by people without such expertise. It can be seen as a visual version of the 20 questions game, where questions based on simple visual attributes are posed interactively. The goal is to identify the true class while minimizing the number of questions asked, using the visual content of the image. We introduce a general framework for incorporating almost any off-the-shelf multi-class object recognition algorithm into the visual 20 questions game, and provide methodologies to account for imperfect user responses and unreliable computer vision algorithms. We evaluate our methods on Birds-200, a difficult dataset of 200 tightly-related bird species, and on the Animals With Attributes dataset. Our results demonstrate that incorporating user input drives up recognition accuracy to levels that are good enough for practical applications, while at the same time, computer vision reduces the amount of human interaction required.

/pdf/visual-recognition-with-humans-in-the-loop-2myqc00150.pdf

Visual recognition with humans in the loop

We propose a visual recognition system that is designed for fine-grained visual categorization. The system is composed of a machine and a human user. The user, who is unable to carry out the recognition task by himself, is interactively asked to provide two heterogeneous forms of information: clicking on object parts and answering binary questions. The machine intelligently selects the most informative question to pose to the user in order to identify the object's class as quickly as possible. By leveraging computer vision and analyzing the user responses, the overall amount of human effort required, measured in seconds, is minimized. We demonstrate promising results on a challenging dataset of uncropped images, achieving a significant average reduction in human effort over previous methods.

/pdf/multiclass-recognition-and-part-localization-with-humans-in-35xbnzhey8.pdf

Multiclass recognition and part localization with humans in the loop

With the rapid proliferation of smartphones and tablet computers, search has moved beyond text to other modalities like images and voice. For many applications like Fashion, visual search offers a compelling interface that can capture stylistic visual elements beyond color and pattern that cannot be as easily described using text. However, extracting and matching such attributes remains an extremely challenging task due to high variability and deformability of clothing items. In this paper, we propose a fine-grained learning model and multimedia retrieval framework to address this problem. First, an attribute vocabulary is constructed using human annotations obtained on a novel fine-grained clothing dataset. This vocabulary is then used to train a fine-grained visual recognition system for clothing styles. We report benchmark recognition and retrieval results on Women's Fashion Coat Dataset and illustrate potential mobile applications for attribute-based multimedia retrieval of clothing items and image annotation.

/pdf/style-finder-fine-grained-clothing-style-detection-and-1sjagvydsh.pdf

Catherine Wah

Papers

The Caltech-UCSD Birds-200-2011 Dataset

Caltech-UCSD Birds 200

Visual recognition with humans in the loop

Multiclass recognition and part localization with humans in the loop

Style Finder: Fine-Grained Clothing Style Detection and Retrieval