{"title":"对象识别中的上下文反馈:生物学启发的计算模型和人类行为研究","authors":"Elahe Soltandoost , Karim Rajaei , Reza Ebrahimpour","doi":"10.1016/j.visres.2025.108679","DOIUrl":null,"url":null,"abstract":"<div><div>Scene context is known to significantly influence visual perception, enhancing object recognition particularly under challenging viewing conditions. Behavioral and neuroimaging studies suggest that high-level scene information modulates activity in object-selective brain areas through top-down mechanisms, yet the underlying mechanism of this process remains unclear. Here, we introduce a biologically inspired context-based computational model (CBM) that integrates scene context into object recognition via an explicit feedback mechanism. CBM consists of two distinct pathways: Object_CNN, which processes localized object features, and Place_CNN, which extracts global scene information to modulate object processing. We compare CBM to a standard feedforward model, AlexNet, in a multiclass object recognition task under varying levels of visual degradation and occlusion. CBM significantly outperformed a standard feedforward model (AlexNet), demonstrating the effectiveness of structured contextual feedback in resolving ambiguous or degraded visual input. However, behavioral experiments revealed that while humans also benefited from congruent context — particularly at high occlusion levels — the effect was modest. Human recognition remained relatively robust even without contextual support, suggesting that mechanisms such as global shape processing and pattern completion, likely mediated by local recurrent processes, play a dominant role in resolving occluded input. These findings highlight the potential of contextual feedback for enhancing model performance, while also underscoring key differences between human and models. Our results point toward the need for models that combine context-sensitive feedback with object-intrinsic local recurrent processes to more closely approximate the flexible and resilient strategies of human perception.</div></div>","PeriodicalId":23670,"journal":{"name":"Vision Research","volume":"237 ","pages":"Article 108679"},"PeriodicalIF":1.4000,"publicationDate":"2025-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Contextual feedback in object recognition: A biologically inspired computational model and human behavioral study\",\"authors\":\"Elahe Soltandoost , Karim Rajaei , Reza Ebrahimpour\",\"doi\":\"10.1016/j.visres.2025.108679\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><div>Scene context is known to significantly influence visual perception, enhancing object recognition particularly under challenging viewing conditions. Behavioral and neuroimaging studies suggest that high-level scene information modulates activity in object-selective brain areas through top-down mechanisms, yet the underlying mechanism of this process remains unclear. Here, we introduce a biologically inspired context-based computational model (CBM) that integrates scene context into object recognition via an explicit feedback mechanism. CBM consists of two distinct pathways: Object_CNN, which processes localized object features, and Place_CNN, which extracts global scene information to modulate object processing. We compare CBM to a standard feedforward model, AlexNet, in a multiclass object recognition task under varying levels of visual degradation and occlusion. CBM significantly outperformed a standard feedforward model (AlexNet), demonstrating the effectiveness of structured contextual feedback in resolving ambiguous or degraded visual input. However, behavioral experiments revealed that while humans also benefited from congruent context — particularly at high occlusion levels — the effect was modest. Human recognition remained relatively robust even without contextual support, suggesting that mechanisms such as global shape processing and pattern completion, likely mediated by local recurrent processes, play a dominant role in resolving occluded input. These findings highlight the potential of contextual feedback for enhancing model performance, while also underscoring key differences between human and models. Our results point toward the need for models that combine context-sensitive feedback with object-intrinsic local recurrent processes to more closely approximate the flexible and resilient strategies of human perception.</div></div>\",\"PeriodicalId\":23670,\"journal\":{\"name\":\"Vision Research\",\"volume\":\"237 \",\"pages\":\"Article 108679\"},\"PeriodicalIF\":1.4000,\"publicationDate\":\"2025-08-30\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Vision Research\",\"FirstCategoryId\":\"102\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S0042698925001403\",\"RegionNum\":4,\"RegionCategory\":\"心理学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q4\",\"JCRName\":\"NEUROSCIENCES\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Vision Research","FirstCategoryId":"102","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0042698925001403","RegionNum":4,"RegionCategory":"心理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"NEUROSCIENCES","Score":null,"Total":0}
Contextual feedback in object recognition: A biologically inspired computational model and human behavioral study
Scene context is known to significantly influence visual perception, enhancing object recognition particularly under challenging viewing conditions. Behavioral and neuroimaging studies suggest that high-level scene information modulates activity in object-selective brain areas through top-down mechanisms, yet the underlying mechanism of this process remains unclear. Here, we introduce a biologically inspired context-based computational model (CBM) that integrates scene context into object recognition via an explicit feedback mechanism. CBM consists of two distinct pathways: Object_CNN, which processes localized object features, and Place_CNN, which extracts global scene information to modulate object processing. We compare CBM to a standard feedforward model, AlexNet, in a multiclass object recognition task under varying levels of visual degradation and occlusion. CBM significantly outperformed a standard feedforward model (AlexNet), demonstrating the effectiveness of structured contextual feedback in resolving ambiguous or degraded visual input. However, behavioral experiments revealed that while humans also benefited from congruent context — particularly at high occlusion levels — the effect was modest. Human recognition remained relatively robust even without contextual support, suggesting that mechanisms such as global shape processing and pattern completion, likely mediated by local recurrent processes, play a dominant role in resolving occluded input. These findings highlight the potential of contextual feedback for enhancing model performance, while also underscoring key differences between human and models. Our results point toward the need for models that combine context-sensitive feedback with object-intrinsic local recurrent processes to more closely approximate the flexible and resilient strategies of human perception.
期刊介绍:
Vision Research is a journal devoted to the functional aspects of human, vertebrate and invertebrate vision and publishes experimental and observational studies, reviews, and theoretical and computational analyses. Vision Research also publishes clinical studies relevant to normal visual function and basic research relevant to visual dysfunction or its clinical investigation. Functional aspects of vision is interpreted broadly, ranging from molecular and cellular function to perception and behavior. Detailed descriptions are encouraged but enough introductory background should be included for non-specialists. Theoretical and computational papers should give a sense of order to the facts or point to new verifiable observations. Papers dealing with questions in the history of vision science should stress the development of ideas in the field.