Understanding Objects in Detail with Fine-Grained Attributes

Abstract

We study the problem of understanding objects in detail, intended as recognizing a wide array of fine-grained object attributes. To this end, we introduce a dataset of 7,413 airplanes annotated in detail with parts and their attributes, leveraging images donated by airplane spotters and crowdsourcing both the design and collection of the detailed annotations. We provide a number of insights that should help researchers interested in designing fine-grained datasets for other basic level categories. We show that the collected data can be used to study the relation between part detection and attribute prediction by diagnosing the performance of classifiers that pool information from different parts of an object. We note that the prediction of certain attributes can benefit substantially from accurate part detection. We also show that, differently from previous results in object detection, employing a large number of part templates can improve detection accuracy at the expenses of detection speed. We finally propose a coarse-to-fine approach to speed up detection through a hierarchical cascade algorithm. 1 We already introduced a superset of these aircraft images for FGcomp 2013 [28], but without detailed annotations.

Generic and attribute-specific deep representations for maritime vessels

“…We should also note that no images of the same vessels appear in both training and test sets. The classification performance is quantified by the help of a normalized confusion matrix [7]. The practical + …”

“…Thus, fine-grained datasets were collected for specific object categories. Some examples are aircraft datasets [6,7]; Caltech-UCSD bird species dataset [8] consisting of 12 K images, car make, and model datasets; Standford cars dataset [9] containing 16 K car images; and CompCars dataset [10] of 130 K images. One work related to marine vessel recognition is [11], where 130,000 random example images from the Shipspotting website [12] is utilized and a convolutional neural network [2] is trained for classifying vessel types.…”

Learning Localized Perceptual Similarity Metrics for Interactive Categorization

“…Fine-grained visual categorization (FGVC) is an area of computer vision that has experienced an increased amount of attention in recent years across various visual domains [39,9,27,52]. The goal is to distinguish between fine-grained categories or subcategories (e.g., a Cardinal vs. a Lazuli Bunting) that belong to the same basic-level category (e.g., Bird).…”

Gamifying Video Object Segmentation

“…Another option to support low-level computer vision tasks is to understand how human perform them and to seek how human inference/reasoning can be integrated into computer programs. Examples are the ones that ask people to provide explicitly annotation rationales [42] or to elicit the visual features employed to discriminate between image/object classes [25], [43]. Nevertheless, unlike computers, humans need incentives, either monetary or for entertainment, to carry out specific tasks.…”