Showing papers by "Ali Farhadi published in 2013"

Object-Centric Anomaly Detection by Attribute-Based Reasoning

Abstract: When describing images, humans tend not to talk about the obvious, but rather mention what they find interesting. We argue that abnormalities and deviations from typicalities are among the most important components that form what is worth mentioning. In this paper we introduce the abnormality detection as a recognition problem and show how to model typicalities and, consequently, meaningful deviations from prototypical properties of categories. Our model can recognize abnormalities and report the main reasons of any recognized abnormality. We also show that abnormality predictions can help image categorization. We introduce the abnormality detection dataset and show interesting results on how to reason about abnormalities.

Multi-attribute Queries: To Merge or Not to Merge?

Abstract: Users often have very specific visual content in mind that they are searching for. The most natural way to communicate this content to an image search engine is to use key-words that specify various properties or attributes of the content. A naive way of dealing with such multi-attribute queries is the following: train a classifier for each attribute independently, and then combine their scores on images to judge their fit to the query. We argue that this may not be the most effective or efficient approach. Conjunctions of attribute often correspond to very characteristic appearances. It would thus be beneficial to train classifiers that detect these conjunctions as a whole. But not all conjunctions result in such tight appearance clusters. So given a multi-attribute query, which conjunctions should we model? An exhaustive evaluation of all possible conjunctions would be time consuming. Hence we propose an optimization approach that identifies beneficial conjunctions without explicitly training the corresponding classifier. It reasons about geometric quantities that capture notions similar to intra- and inter-class variances. We exploit a discriminative binary space to compute these geometric quantities efficiently. Experimental results on two challenging datasets of objects and birds show that our proposed approach can improve performance significantly over several strong base-lines, while being an order of magnitude faster than exhaustively searching through all possible conjunctions.

Adding Unlabeled Samples to Categories by Learned Attributes

Abstract: We propose a method to expand the visual coverage of training sets that consist of a small number of labeled examples using learned attributes. Our optimization formulation discovers category specific attributes as well as the images that have high confidence in terms of the attributes. In addition, we propose a method to stably capture example-specific attributes for a small sized training set. Our method adds images to a category from a large unlabeled image pool, and leads to significant improvement in category recognition accuracy evaluated on a large-scale dataset, Image Net.

Phrasal Recognition

Abstract: In this paper, we introduce visual phrases, complex visual composites like "a person riding a horse." Visual phrases often display significantly reduced visual complexity compared to their component objects because the appearance of those objects can change profoundly when they participate in relations. We introduce a dataset suitable for phrasal recognition that uses familiar PASCAL object categories, and demonstrate significant experimental gains resulting from exploiting visual phrases. We show that a visual phrase detector significantly outperforms a baseline which detects component objects and reasons about relations, even though visual phrase training sets tend to be smaller than those for objects. We argue that any multiclass detection system must decode detector outputs to produce final results; this is usually done with nonmaximum suppression. We describe a novel decoding procedure that can account accurately for local context without solving difficult inference problems. We show this decoding procedure outperforms the state of the art. Finally, we show that decoding a combination of phrasal and object detectors produces real improvements in detector results.

The evaluation of poisoning mortality in the admitted patients in Shohada Ashayer hospital of Khorramabad from 2006 to 2010

Abstract:  همدقم : تـساه تیمومسم زا یشان ایند مامت رد ریم و گرم للع نیرتعیاش زا یکی . زا یـشان رـیمو گرـم لـلع یـسررب و قـیقحت درادناتسا دوبهب و تامیمصت ذاختا رد اه تیمومسم يارب مزلا ياه ،راوگان ثداوح زا يریگشیپ دنک یم افیا ار یمهم شقن . يارـب اذل خانـش ت تیمومسم زا یشان ریمو گرم یسررب هب میمصت ،مومسم نارامیب توف هب جتنم ضراوع و للع رتهب ياهلاـس یط اه 1386 تـیاغل 1390 رد میتفرگ دابآ مرخ ناتسرهش ریاشع يادهش ناتسرامیب رد يرتسب نارامیب .  شور و داوم اه : یفیصوت ي هعلاطم نیا اراـمیب يور یـعطقم تروص هب یلیلحت ن رد تیمومسـم زا یـشان هدـش يرتسـب یتوـف ياهلاس یط ریاشع يادهش ناتسرامیب 1386 تیاغل 1390 ياهـشور اـب و يروآ درـگ همانشسرپ بلاق رد رظن دروم تاعلاطا و هتفرگ تروص ارق لیلحت و هیزجت دروم تبسن و رایعم فارحنا ،نیگنایم ،یقفاوت لوادج ،یناوارف عیزوت لوادج ریظن یفیصوت رامآ تفرگ ر .  هتفای اه : نایم زا 13090 ،زکرم نیا هب هدننک هعجارم تیمومسم راچد رامیب 124 هـک دـندوب هدرـک توف هلصاح ضراوع تدش رثا رب رفن 9 / 58 % دندوب درم نانآ زا . درجم نارامیب تیرثکا ) 6 / 51 (% ملپید ياراد ، ) 5 / 43 (% رهش نکاس و ) 4 / 77 (% دندوب . 4 / 73 % هدـش توف نارامیب ب ه ط دندوب هدرک یشکدوخ هب مادقا هنارازآدوخ و يدمع رو . تاـفآ عـفد مومـس بـیترت هـب یفرصـم مومس نیرتشیب ) 2 / 53 (% پا ، یوی اهدـی ) 8 / 21 (% نکسم ياهوراد و کیتونپیاه ) 5 / 10 (% دندوب .  هجیتن و ثحب يریگ : رد ناتسرل ناتسا تیمومسم اب مومس تافآ عفد ًاصوصخم جنرب صرق ) موینیمولآدیفسف ( و و اه مویپا گرـم و ریم یشان زا زا رتشیب اهنآ ریاس اهوراد و مومس دشاب یم .