Semi-supervised instance object detection method based on SVD co-training

نویسندگان

چکیده

åœ¨å®¤å† å®žä¾‹ç‰©ä½“ç›®æ ‡æ£€æµ‹ä¸­ï¼Œä¼ ç»Ÿæ·±åº¦å­¦ä¹ éœ€è¦å¤§é‡äººå·¥æ ‡æ³¨çš„è®­ç»ƒæ ·æœ¬è¿›è¡Œç½‘ç»œè®­ç»ƒï¼Œè´¹æ—¶è´¹åŠ›ï¼Œä¸ºæ­¤æå‡ºå¹¶å®žçŽ°äº†ä¸€ç§é‡‡ç”¨å¥‡å¼‚å€¼åˆ†è§£ï¼ˆSingular Value Decomposition,SVDï¼‰å’ŒååŒè®­ç»ƒçš„åŠç›‘ç£å®žä¾‹çº§ç›®æ ‡æ£€æµ‹ç½‘ç»œSVD-RCNNã€‚æŒ‘é€‰å ³é”®æ ·æœ¬è¿›è¡Œäººå·¥æ ‡æ³¨å¹¶é¢„è®­ç»ƒSVD-RCNNï¼Œä»¥ç¡®ä¿å ¶èŽ·å–æ›´å¤šå ˆéªŒçŸ¥è¯†ï¼Œé‡‡ç”¨åŸºäºŽSVD的收敛-分解-微调策略,在SVD-RCNNä¸­å¾—åˆ°ä¸¤ä¸ªè¾ƒå¼ºç‹¬ç«‹æ€§çš„æ£€æµ‹å™¨ä»¥æ»¡è¶³ååŒè®­ç»ƒçš„è¦æ±‚ï¼Œæœ€åŽæå‡ºä¸€ç§è‡ªé€‚åº”çš„è‡ªæ ‡æ³¨ç­–ç•¥ï¼ŒèŽ·å¾—é«˜è´¨é‡çš„è‡ªæ ‡æ³¨åŠæ£€æµ‹ç»“æžœã€‚åœ¨å¤šä¸ªå®¤å† å®žä¾‹æ•°æ®é›†ä¸Šå¯¹è¯¥æ–¹æ³•è¿›è¡Œæµ‹è¯•ï¼Œåœ¨GMUæ•°æ®é›†ä¸Šåªéœ€äººå·¥æ ‡æ³¨199ä¸ªæ ·æœ¬ï¼Œå‡å€¼å¹³å‡ç²¾åº¦ï¼ˆmean Average Precision,mAP)达到了79.3%ï¼Œç›¸è¾ƒäºŽéœ€æ ‡æ³¨3 851ä¸ªæ ·æœ¬çš„å ¨ç›‘ç£Faster RCNN的81.3% mAPä» ä¸‹é™äº†2%ã€‚æ¶ˆèžå®žéªŒåŠç³»åˆ—å®žéªŒè¯æ˜Žäº†æœ¬æ–‡æ–¹æ³•çš„æœ‰æ•ˆæ€§å’Œæ™®é€‚æ€§ï¼Œæœ¬æ–‡æå‡ºçš„æ–¹æ³•ä» éœ€äººå·¥æ ‡æ³¨5%çš„è®­ç»ƒæ•°æ®ï¼Œå³å¯è¾¾åˆ°ä¸Žå ¨ç›‘ç£å­¦ä¹ ç›¸å½“çš„å®žä¾‹çº§ç›®æ ‡æ£€æµ‹ç²¾åº¦ï¼Œæœ‰åˆ©äºŽæ™ºèƒ½æœºå™¨äººé«˜æ•ˆè¯†åˆ«ä¸åŒå®žä¾‹ç‰©ä½“çš„å®žé™ åº”ç”¨ã€‚

برای دانلود باید عضویت طلایی داشته باشید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Co-occurrence matrix analysis-based semi-supervised training for object detection

One of the most important factors in training object recognition networks using convolutional neural networks (CNNs) is the provision of annotated data accompanying human judgment. Particularly, in object detection or semantic segmentation, the annotation process requires considerable human effort. In this paper, we propose a semi-supervised learning (SSL)-based training methodology for object ...

متن کامل

Semi-supervised Co-training Algorithm Based on Assisted Learning

The classification performance of the learner is weakened when unlabeled examples are mislabeled during co-training process. A semisupervised co-training algorithm based on assisted learning (AR-Tri-training) was proposed. Firstly, the assisted learning strategy was presented, which is combined with rich information strategy for designing the assisted learner. Secondly, the evaluation factor wa...

متن کامل

Instance Selection Method for Improving Graph-Based Semi-supervised Learning

Graph-based semi-supervised learning (GSSL) is one of the most important semi-supervised learning (SSL) paradigms. Though GSSL methods are helpful in many situations, they may hurt performance when using unlabeled data. In this paper, we propose a new GSSL method GsslIs based on instance selection in order to reduce the chances of performance degeneration. Our basic idea is that given a set of ...

متن کامل

Semi-Supervised Self-Training of Object Detection Models

The construction of appearance-based object detection systems is time-consuming and difficult because a large number of training examples must be collected and manually labeled in order to capture variations in object appearance. Semi-supervised training is a means for reducing the effort needed to prepare the training set by training the model with a small number of fully labeled examples and ...

متن کامل

Semi-Supervised Regression with Co-Training

In many practical machine learning and data mining applications, unlabeled training examples are readily available but labeled ones are fairly expensive to obtain. Therefore, semi-supervised learning algorithms such as co-training have attracted much attention. Previous research mainly focuses on semi-supervised classification. In this paper, a co-training style semi-supervised regression algor...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

ژورنال

عنوان ژورنال: Guangxue jingmi gongcheng

سال: 2023

ISSN: ['1004-924X']

DOI: https://doi.org/10.37188/ope.20233113.2000