In this paper we present the first large-scale scene attribute database. First, we perform crowd-sourced human studies to find a taxonomy of 102 discriminative attributes. Next, we build the “SUN attribute database ” on top of the diverse SUN categorical database. Our attribute database spans more than 700 categories and 14,000 images and has potential for use in high-level scene understanding and fine-grained scene recognition. We use our dataset to train attribute classifiers and evaluate how well these relatively simple classifiers can recognize a variety of attributes related to materials, surface properties, lighting, functions and affordances, and spatial envelope properties. 1.

We propose a method for recognizing attributes, such as the gender, hair style and types of clothes of people under large variation in viewpoint, pose, articulation and occlusion typical of personal photo album images. Robust attribute classifiers under such conditions must be invariant to pose, but inferring the pose in itself is a challenging problem. We use a part-based approach based on poselets. Our parts implicitly decompose the aspect (the pose and viewpoint). We train attribute classifiers for each such aspect and we combine them together in a discriminative model. We propose a new dataset of 8000 people with annotated attributes. Our method performs very well on this dataset, significantly outperforming a baseline built on the spatial pyramid match kernel method. On gender recognition we outperform a commercial face recognition system. Figure 1. People can easily infer the gender based on the face, the hair style, the body proportions and the types of clothes. A robust gender classifier should take into account all such available cues. 1.

the degree of Doctor of Philosophy. Human computation is the study of systems where humans perform a major part of the computation or are an integral part of the overall computational process. The ESP Game, for example, is a human computation system that maps images to tags, by engaging humans to play a game in which they are rewarded each time they agree on a description for an image. It was shown that these so-called Games with a Purpose are a reliable way to quickly collect millions of accurate image descriptors, which can then used to index images and facilitate search. However, most existing human computation systems operate without any machine intervention. Likewise, very few supervised learning systems are taking advantage of these powerful new platforms to elicit help from human teachers. It is therefore largely unknown what more a human computation system can achieve with machines in the loop. This thesis is centered around the problem of attribute learning – using the joint effort of human game players and machine learning algorithms to determine that a piece of music is “soothing”, that the bird in an image “has a red beak”, or that Ernest Hemingway is an “Nobel Prize winning author”. In particular, our work focuses on two aspects of the problem – how to acquire attributes and attribute values from human computers using incentive-compatible game mechanisms, and what active learning strategies to employ for attribute and attribute value acquisition.

Human-nameable visual attributes offer many advantages when used as mid-level features for object recognition, but existing techniques to gather relevant attributes can be inefficient (costing substantial effort or expertise) and/or insufficient (descriptive properties need not be discriminative). We introduce an approach to define a vocabulary of attributes that is both human understandable and discriminative. The system takes object/scene-labeled images as input, and returns as output a set of attributes elicited from human annotators that distinguish the categories of interest. To ensure a compact vocabulary and efficient use of annotators ’ effort, we 1) show how to actively augment the vocabulary such that new attributes resolve inter-class confusions, and 2) propose a novel “nameability” manifold that prioritizes candidate attributes by their likelihood of being associated with a nameable property. We demonstrate the approach with multiple datasets, and show its clear advantages over baselines that lack a nameability model or rely on a list of expert-provided attributes. 1.

We present a new approach to learning attribute-based descriptions of objects. Unlike earlier works, we do not assume that the descriptions are hand-labeled. Instead, our approach jointly learns both the attribute classifiers and the descriptions from data. By incorporating class information into the attribute classifier learning, we get an attributelevel representation that generalizes well to both unseen examples of known classes and unseen classes. We consider two different settings, one with unlabeled images available for learning, and another without. The former corresponds to a novel transductive setting where the unlabeled images can come from new classes. Results from Animals with Attributes and a-Yahoo, a-Pascal benchmark datasets show that the learned representations give similar or even better accuracy than the hand-labeled descriptions. 1.

This paper presents the first effort to discover and exploit a diverse taxonomy of scene attributes. Starting with the fine-grained SUN database, we perform crowd-sourced human studies to find over 100 attributes that discriminate between scene categories. We construct an attributelabeled dataset on top of the SUN database [7]. This “SUN Attribute database ” spans more than 700 categories and 14,000 images and has potential for use in high-level scene understanding, attribute-based hierarchy construction, and fine-grained scene recognition.

We present an active learning approach to choose image annotation requests among both object category labels and the objects ’ attribute labels. The goal is to solicit those labels that will best use human effort when training a multiclass object recognition model. In contrast to previous work in active visual category learning, our approach directly exploits the dependencies between human-nameable visual attributes and the objects they describe, shifting its requests in either label space accordingly. We adopt a discriminative latent model that captures object-attribute and attribute-attribute relationships, and then define a suitable entropy reduction selection criterion to predict the influence a new label might have throughout those connections. On three challenging datasets, we demonstrate that the method can more successfully accelerate object learning relative to both passive learning and traditional active learning approaches. 1.

We introduce the use of describable visual attributes for face images. Describable visual attributes are labels that can be given to an image to describe its appearance. This thesis focuses mostly on images of faces and the attributes used to describe them, although the concepts also apply to other domains. Examples of face attributes include gender, age, jaw shape, nose size, etc. The advantages of an attribute-based representation for vision tasks are manifold: they can be composed to create descriptions at various levels of specificity; they are generalizable, as they can be learned once and then applied to recognize new objects or categories without any further training; and they are efficient, possibly requiring exponentially fewer attributes (and training data) than explicitly naming each category. We show how one can create and label large datasets of real-world images to train classifiers which measure the presence, absence, or degree to which an attribute is expressed in images. These classifiers can then automatically label new images. We demonstrate the current effectiveness and explore the future potential of using attributes for image search, automatic face replacement in images, and face verification, via both human and computational experiments. To aid other researchers in studying these

Recent work has shown that visual attributes are a powerful approach for applications such as recognition, image description and retrieval. However, fusing multiple attribute scores – as required during multi-attribute queries or similarity searches – presents a significant challenge. Scores from different attribute classifiers cannot be combined in a simple way; the same score for different attributes can mean different things. In this work, we show how to construct normalized “multi-attribute spaces ” from raw classifier outputs, using techniques based on the statistical Extreme Value Theory. Our method calibrates each raw score to a probability that the given attribute is present in the image. We describe how these probabilities can be fused in a simple way to perform more accurate multiattribute searches, as well as enable attribute-based similarity searches. A significant advantage of our approach is that the normalization is done after-the-fact, requiring neither modification to the attribute classification system nor ground truth attribute annotations. We demonstrate results on a large data set of nearly 2 million face images and show significant improvements over prior work. We also show that perceptual similarity of search results increases by using contextual attributes. 1

We propose a novel mode of feedback for image search, where a user describes which properties of exemplar images should be adjusted in order to more closely match his/her mental model of the image(s) sought. For example, perusing image results for a query “black shoes”, the user might state, “Show me shoe images like these, but sportier. ” Offline, our approach first learns a set of ranking functions, each of which predicts the relative strength of a nameable attribute in an image (‘sportiness’, ‘furriness’, etc.). At query time, the system presents an initial set of reference images, and the user selects among them to provide relative attribute feedback. Using the resulting constraints in the multi-dimensional attribute space, our method updates its relevance function and re-ranks the pool of images. This procedure iterates using the accumulated constraints until the top ranked images are acceptably close to the user’s envisioned target. In this way, our approach allows a user to efficiently “whittle away ” irrelevant portions of the visual feature space, using semantic language to precisely communicate her preferences to the system. We demonstrate the technique for refining image search for people, products, and scenes, and show it outperforms traditional binary relevance feedback in terms of search speed and accuracy. 1.