<meter id="ybmrw"><ol id="ybmrw"></ol></meter>
<var id="ybmrw"></var>
<code id="ybmrw"></code>

      1. <dl id="ybmrw"><legend id="ybmrw"><blockquote id="ybmrw"></blockquote></legend></dl>
      2. <output id="ybmrw"><form id="ybmrw"></form></output>
          <acronym id="ybmrw"><form id="ybmrw"><blockquote id="ybmrw"></blockquote></form></acronym>

              Research identifies key weakness in modern computer vision systems

              In a finding that could point the way toward better computer vision systems, Brown University researchers show why computers are so bad at seeing when one thing is not like another.

              PROVIDENCE, R.I. [Brown University] —?Computer vision algorithms have come a long way in the past decade. They’ve been shown to be as good or better than people at tasks like categorizing dog or cat breeds, and they have the remarkable ability to identify specific faces out of a sea of millions.

              But research by Brown University scientists shows that computers fail miserably at a class of tasks that even young children have no problem with: determining whether two objects in an image are the same or different. In a paper presented last week at the annual meeting of the Cognitive Science Society, the Brown team sheds light on why computers are so bad at these types of tasks and suggests avenues toward smarter computer vision systems.

              “There’s a lot of excitement about what computer vision has been able to achieve, and I share a lot of that,” said Thomas Serre, associate professor of cognitive, linguistic and psychological sciences at Brown and the paper’s senior author. “But we think that by working to understand the limitations of current computer vision systems as we’ve done here, we can really move toward new, much more advanced systems rather than simply tweaking the systems we already have.”

              For the study, Serre and his colleagues used state-of-the-art computer vision algorithms to analyze simple black-and-white images containing two or more randomly generated shapes. In some cases the objects were identical; sometimes they were the same but with one object rotated in relation to the other; sometimes the objects were completely different. The computer was asked to identify the same-or-different relationship.

              The study showed that, even after hundreds of thousands of training examples, the algorithms were no better than chance at recognizing the appropriate relationship. The question, then, was why these systems are so bad at this task.

              Serre and his colleagues had a suspicion that it has something to do with the inability of these computer vision algorithms to individuate objects. When computers look at an image, they can’t actually tell where one object in the image stops and the background, or another object, begins. They just see a collection of pixels that have similar patterns to collections of pixels they’ve learned to associate with certain labels. That works fine for identification or categorization problems, but falls apart when trying to compare two objects.

              To show that this was indeed why the algorithms were breaking down, Serre and his team performed experiments that relieved the computer from having to individuate objects on its own. Instead of showing the computer two objects in the same image, the researchers showed the computer the objects one at a time in separate images. The experiments showed that the algorithms had no problem learning same-or-different relationship as long as they didn’t have to view the two objects in the same image.

              The source of the problem in individuating objects, Serre says, is the architecture of the machine learning systems that power the algorithms. The algorithms use convolutional neural networks — layers of connected processing units that loosely mimic networks of neurons in the brain. A key difference from the brain is that the artificial networks are exclusively “feed-forward” — meaning information has a one-way flow through the layers of the network. That’s not how the visual system in humans works, according to Serre.

              “If you look at the anatomy of our own visual system, you find that there are a lot of recurring connections, where the information goes from a higher visual area to a lower visual area and back through,” Serre said.

              While it’s not clear exactly what those feedbacks do, Serre says, it’s likely that they have something to do with our ability to pay attention to certain parts of our visual field and make mental representations of objects in our minds.

              “Presumably people attend to one object, building a feature representation that is bound to that object in their working memory,” Serre said. “Then they shift their attention to another object. When both objects are represented in working memory, your visual system is able to make comparisons like same-or-different.”

              Serre and his colleagues hypothesize that the reason computers can’t do anything like that is because feed-forward neural networks don’t allow for the kind of recurrent processing required for this individuation and mental representation of objects. It could be, Serre says, that making computer vision smarter will require neural networks that more closely approximate the recurrent nature of human visual processing.

              Serre’s co-authors on the paper were Junkyung Kim and Matthew Ricci. The research was supported by the National Science Foundation (IIS-1252951, 1644760) and DARPA (YFA N66001-14-1-4037).

              安庆| 金阳| 滁州| 高淳| 榆林| 耀县| 仁化| 东阳| 赤峰郊区站| 木垒| 会东| 畹町镇| 兴县| 乌当| 澧县| 榆林| 宜君| 运城| 青浦| 黎平| 沙坪坝| 兴文| 张北| 金山| 嵩县| 盘山| 兴文| 乌拉盖| 贺兰| 靖宇| 崂山| 临朐| 庆云| 大佘太| 涪陵| 宁南| 平乐| 鹤庆| 九华山| 新巴尔虎右旗| 同心| 望都| 江门| 灵台| 邵武| 临猗| 拜城| 铁卜加| 长兴| 和林格尔| 吴县东山| 石渠| 鄂托克旗| 都兰| 莱西| 沂南| 易县| 安福| 浏阳| 启东| 呼中| 武穴| 辽阳| 诸城| 宁南| 富顺| 翁牛特旗| 房县| 上林| 西青| 仁和| 安顺| 江油| 青铜峡| 垦利| 公馆| 江陵| 班玛| 梅县| 准格尔旗| 普洱| 阿图什| 商丘| 桂阳| 望谟| 连城| 咸宁| 潍坊| 根河| 高州| 伽师| 邹城| 景洪| 淮安| 丰都| 阿克苏| 建瓯| 环江| 曲靖| 苏尼特左旗| 长葛| 弥渡| 乌拉特后旗| 衡水| 吉水| 邕宁| 东光| 盖州| 呼和浩特市郊区| 聂拉木| 于都| 布尔津| 大邑| 太白| 霍邱| 唐山| 括苍山| 佛爷顶| 仁寿| 武定| 北票| 兴和| 建平县| 中山| 龙胜| 汉寿| 湖州| 通州| 朱日和| 阿合奇| 安义| 昌吉| 新民| 黄泛区| 天水| 建德| 雅安| 弥勒| 绥化| 孝感| 茶陵| 六合| 治多| 长子| 新林| 枣阳| 耀县| 达尔罕茂明安联合旗| 阿拉山口| 吉木萨尔| 米泉| 安宁| 荥阳| 川沙| 克拉玛依| 白沙| 屏南| 华宁| 成武| 淖毛湖| 阜城| 台儿庄| 玉溪| 嘉祥| 陈家镇| 孟村| 巫山| 景东| 汉川| 科尔沁左翼后旗| 宾川| 平安| 绩溪| 汶川| 新界| 宁陵| 六盘水| 潮州| 陇川| 海伦| 同江| 寻甸| 宣汉| 广河| 泰宁| 石河子| 华家岭| 宿迁| 朝克乌拉| 长宁| 临河| 利辛| 万州龙宝| 宜章| 黑山| 滦南| 柯坪| 长宁| 珙县| 都江堰| 莘县| 涿州| 玉林| 元阳| 宝应| 十三间房气象站| 南宁城区| 绥阳| 南郑| 天长| 公主岭| 济阳| 淅川| 宿松| 清镇| 梅县| 天山大西沟| 翼城| 建昌| 万州天城| 长治| 错那| 根河| 东沟| 彭县| 海晏| 瑞丽| 常熟| 嵩明| 牟平| 文成| 若尔盖| 宜都| 大邑| 正兰旗| 德江| 环江| 高州| 北川| 福安| 渑池| 宜川| 昌平| 九龙| 竹山| 满洲里| 贡嘎| 富顺| 深州| 蓝山| 乌海| 海北| 新洲| 嵊山| 东沙岛| 白杨沟| 中山| 阳春| 东川| 镇远| 松滋| 子洲| 忻城| 长乐| 延长| 晴隆| 库车| 普格| 朱日和| 公主岭| 弋阳| 阿拉善右旗| 浮山| 当阳| 余江| 临汾| 新绛| 朱日和| 周口| 蔡甸| 常熟| 深州| 龙胜| 中甸| 炎陵| 头道湖| 三原| 八达岭| 紫金| 北戴河| 漠河| 沂源| 阿克苏| 石棉| 永平| 平坝| 丽江| 武平| 常州| 惠民| 辽阳| 海丰| 镇江| 辽阳| 嵩明| 察尔汉| 泗水| 铜梁| 乌什| 开阳| 塔河| 忻州| 伊川| 建瓯| 安远| 蒲江| 大竹| 内江| 全椒| 淮南| 西平| 磁县| 隆林| 公安| 灵石| 儋州| 吴县东山| 阜康| 大新| 延长| 襄阳| 泸西| 杜蒙| 岚皋| 瓜州| 兴山| 临泉| 湘潭| 湖州| 林芝| 屯留| 旅顺| 田林| 麻栗坡| 龙胜| 平潭| 巫溪| 麟游| 花溪| 庆云| 临泉| 金山| 泾阳| 当雄| 罗源| 衡阳县| 克东| 肃宁| 北戴河| 囊谦| 丹江口| 慈溪| 敦煌| 托克托| 新界| 寿县| 曲阳| 南平| 曲周| 德安| 双阳| 柳城| 高青| 十堰| 名山| 顺义| 宽城| 镇安| 武陟| 普兰| 海拉尔| 户县| 朱日和| 青浦| 沾益| 焦作| 图里河| 罗平| 大武口| 敦化| 海原| 临湘| 牡丹江| 滑县| 凉山| 融安| 陆川| 金沙| 岳阳| 新沂