Why is real-world visual object recognition hard?
Ontology highlight
ABSTRACT:
SUBMITTER: Pinto N
PROVIDER: S-EPMC2211529 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Background: The environments that we live in impact on our ability to recognise objects, with recognition being facilitated when objects appear in expected locations (congruent) compared to unexpected locations (incongruent). However, these findings are based on experiments where the object is isolated from its environment. Moreover, it is not clear which components of the recognition process are impacted by the environment. In this experiment, we seek to examine the impact real world environments have on object recognition. Specifically, we will use mobile electroencephalography (mEEG) and augmented reality (AR) to investigate how the visual and semantic processing aspects of object recognition are changed by the environment. Methods: We will use AR to place congruent and incongruent virtual objects around indoor and outdoor environments. During the experiment a total of 34 participants will walk around the environments and find these objects while we record their eye movements and neural signals. We will perform two primary analyses. First, we will analyse the event-related potential (ERP) data using paired samples t-tests in the N300/400 time windows in an attempt to replicate congruency effects on the N300/400. Second, we will use representational similarity analysis (RSA) and computational models of vision and semantics to determine how visual and semantic processes are changed by congruency. Conclusions: Based on previous literature, we hypothesise that scene-object congruence would facilitate object recognition. For ERPs, we predict a congruency effect in the N300/N400, and for RSA we predict that higher level visual and semantic information will be represented earlier for congruent scenes than incongruent scenes. By collecting mEEG data while participants are exploring a real-world environment, we will be able to determine the impact of a natural context on object recognition, and the different processing stages of object recognition.
| S-EPMC10238820 | biostudies-literature
Project description:Context plays an important role in visual recognition. Recent studies have shown that visual recognition networks can be fooled by placing objects in inconsistent contexts (e.g. a cow in the ocean). To understand and model the role of contextual information in visual recognition, we systematically and quantitatively investigated ten critical properties of where, when, and how context modulates recognition including amount of context, context and object resolution, geometrical structure of context, context congruence, time required to incorporate contextual information, and temporal dynamics of contextual modulation. The tasks involve recognizing a target object surrounded with context in a natural image. As an essential benchmark, we first describe a series of psychophysics experiments, where we alter one aspect of context at a time, and quantify human recognition accuracy. To computationally assess performance on the same tasks, we propose a biologically inspired context aware object recognition model consisting of a two-stream architecture. The model processes visual information at the fovea and periphery in parallel, dynamically incorporates both object and contextual information, and sequentially reasons about the class label for the target object. Across a wide range of behavioral tasks, the model approximates human level performance without retraining for each task, captures the dependence of context enhancement on image properties, and provides initial steps towards integrating scene and object information for visual recognition.
| S-EPMC8459751 | biostudies-literature
Project description:Key properties of inferior temporal cortex neurons are described, and then, the biological plausibility of two leading approaches to invariant visual object recognition in the ventral visual system is assessed to investigate whether they account for these properties. Experiment 1 shows that VisNet performs object classification with random exemplars comparably to HMAX, except that the final layer C neurons of HMAX have a very non-sparse representation (unlike that in the brain) that provides little information in the single-neuron responses about the object class. Experiment 2 shows that VisNet forms invariant representations when trained with different views of each object, whereas HMAX performs poorly when assessed with a biologically plausible pattern association network, as HMAX has no mechanism to learn view invariance. Experiment 3 shows that VisNet neurons do not respond to scrambled images of faces, and thus encode shape information. HMAX neurons responded with similarly high rates to the unscrambled and scrambled faces, indicating that low-level features including texture may be relevant to HMAX performance. Experiment 4 shows that VisNet can learn to recognize objects even when the view provided by the object changes catastrophically as it transforms, whereas HMAX has no learning mechanism in its S-C hierarchy that provides for view-invariant learning. This highlights some requirements for the neurobiological mechanisms of high-level vision, and how some different approaches perform, in order to help understand the fundamental underlying principles of invariant visual object recognition in the ventral visual stream.
| S-EPMC4572081 | biostudies-literature
Project description:In virtually every real-life situation humans are confronted with complex and cluttered visual environments that contain a multitude of objects. Because of the limited capacity of the visual system, objects compete for neural representation and cognitive processing resources. Previous work has shown that such attentional competition is partly object based, such that competition among elements is reduced when these elements perceptually group into an object based on low-level cues. Here, using functional MRI (fMRI) and behavioral measures, we show that the attentional benefit of grouping extends to higher-level grouping based on the relative position of objects as experienced in the real world. An fMRI study designed to measure competitive interactions among objects in human visual cortex revealed reduced neural competition between objects when these were presented in commonly experienced configurations, such as a lamp above a table, relative to the same objects presented in other configurations. In behavioral visual search studies, we then related this reduced neural competition to improved target detection when distracter objects were shown in regular configurations. Control studies showed that low-level grouping could not account for these results. We interpret these findings as reflecting the grouping of objects based on higher-level spatial-relational knowledge acquired through a lifetime of seeing objects in specific configurations. This interobject grouping effectively reduces the number of objects that compete for representation and thereby contributes to the efficiency of real-world perception.
| S-EPMC4121846 | biostudies-literature
Project description:Although there is mounting evidence that input from the dorsal visual pathway is crucial for object processes in the ventral pathway, the specific functional contributions of dorsal cortex to these processes remain poorly understood. Here, we hypothesized that dorsal cortex computes the spatial relations among an object's parts, a process crucial for forming global shape percepts, and transmits this information to the ventral pathway to support object categorization. Using fMRI with human participants (females and males), we discovered regions in the intraparietal sulcus (IPS) that were selectively involved in computing object-centered part relations. These regions exhibited task-dependent functional and effective connectivity with ventral cortex, and were distinct from other dorsal regions, such as those representing allocentric relations, 3D shape, and tools. In a subsequent experiment, we found that the multivariate response of posterior (p)IPS, defined on the basis of part-relations, could be used to decode object category at levels comparable to ventral object regions. Moreover, mediation and multivariate effective connectivity analyses further suggested that IPS may account for representations of part relations in the ventral pathway. Together, our results highlight specific contributions of the dorsal visual pathway to object recognition. We suggest that dorsal cortex is a crucial source of input to the ventral pathway and may support the ability to categorize objects on the basis of global shape.SIGNIFICANCE STATEMENT Humans categorize novel objects rapidly and effortlessly. Such categorization is achieved by representing an object's global shape structure, that is, the relations among object parts. Yet, despite their importance, it is unclear how part relations are represented neurally. Here, we hypothesized that object-centered part relations may be computed by the dorsal visual pathway, which is typically implicated in visuospatial processing. Using fMRI, we identified regions selective for the part relations in dorsal cortex. We found that these regions can support object categorization, and even mediate representations of part relations in the ventral pathway, the region typically thought to support object categorization. Together, these findings shed light on the broader network of brain regions that support object categorization.
| S-EPMC9186804 | biostudies-literature
Project description:Visual processing refers to the process of perceiving, analyzing, synthesizing, manipulating, transforming, and thinking of visual objects. It is modulated by both stimulus-driven and goal-directed factors and manifested in neural activities that extend from visual cortex to high-level cognitive areas. Extensive body of studies have investigated the neural mechanisms of visual object processing using synthetic or curated visual stimuli. However, synthetic or curated images generally do not accurately reflect the semantic links between objects and their backgrounds, and previous studies have not provided answers to the question of how the native background affects visual target detection. The current study bridged this gap by constructing a stimulus set of natural scenes with two levels of complexity and modulating participants' attention to actively or passively attend to the background contents. Behaviorally, the decision time was elongated when the background was complex or when the participants' attention was distracted from the detection task, and the object detection accuracy was decreased when the background was complex. The results of event-related potentials (ERP) analysis explicated the effects of scene complexity and attentional state on the brain responses in occipital and centro-parietal areas, which were suggested to be associated with varied attentional cueing and sensory evidence accumulation effects in different experimental conditions. Our results implied that efficient visual processing of real-world objects may involve a competition process between context and distractors that co-exist in the native background, and extensive attentional cues and fine-grained but semantically irrelevant scene information were perhaps detrimental to real-world object detection.
| S-EPMC8119748 | biostudies-literature
Project description:Objects contain rich visual and conceptual information, but do these two types of information interact? Here, we examine whether visual and conceptual information interact when observers see novel objects for the first time. We then address how this interaction influences the acquisition of perceptual expertise. We used two types of novel objects (Greebles), designed to resemble either animals or tools, and two lists of words, which described non-visual attributes of people or man-made objects. Participants first judged if a word was more suitable for describing people or objects while ignoring a task-irrelevant image, and showed faster responses if the words and the unfamiliar objects were congruent in terms of animacy (e.g., animal-like objects with words that described human). Participants then learned to associate objects and words that were either congruent or not in animacy, before receiving expertise training to rapidly individuate the objects. Congruent pairing of visual and conceptual information facilitated observers' ability to become a perceptual expert, as revealed in a matching task that required visual identification at the basic or subordinate levels. Taken together, these findings show that visual and conceptual information interact at multiple levels in object recognition.
| S-EPMC4114261 | biostudies-literature
Project description:Recognizing hand-object interactions presents a significant challenge in computer vision. It arises due to the varying nature of hand-object interactions. Moreover, estimating the 3D position of a hand from a single frame can be problematic, especially when the hand obstructs the view of the object from the observer's perspective. In this article, we present a novel approach to recognizing objects and facilitating virtual interactions, using a steering wheel as an illustrative example. We propose a real-time solution for identifying hand-object interactions in eXtended reality (XR) environments. Our approach relies on data captured by a single RGB camera during a manipulation scenario involving a steering wheel. Our model pipeline consists of three key components: (a) a hand landmark detector based on the MediaPipe cross-platform hand tracking solution; (b) a three-spoke steering wheel model tracker implemented using the faster region-based convolutional neural network (Faster R-CNN) architecture; and (c) a gesture recognition module designed to analyze interactions between the hand and the steering wheel. This approach not only offers a realistic experience of interacting with steering-based mechanisms but also contributes to reducing emissions in the real-world environment. Our experimental results demonstrate the natural interaction between physical objects in virtual environments, showcasing precision and stability in our system.
| S-EPMC11232578 | biostudies-literature
Project description:The human visual system is able to recognize objects despite tremendous variation in their appearance on the retina resulting from variation in view, size, lighting, etc. This ability--known as "invariant" object recognition--is central to visual perception, yet its computational underpinnings are poorly understood. Traditionally, nonhuman primates have been the animal model-of-choice for investigating the neuronal substrates of invariant recognition, because their visual systems closely mirror our own. Meanwhile, simpler and more accessible animal models such as rodents have been largely overlooked as possible models of higher-level visual functions, because their brains are often assumed to lack advanced visual processing machinery. As a result, little is known about rodents' ability to process complex visual stimuli in the face of real-world image variation. In the present work, we show that rats possess more advanced visual abilities than previously appreciated. Specifically, we trained pigmented rats to perform a visual task that required them to recognize objects despite substantial variation in their appearance, due to changes in size, view, and lighting. Critically, rats were able to spontaneously generalize to previously unseen transformations of learned objects. These results provide the first systematic evidence for invariant object recognition in rats and argue for an increased focus on rodents as models for studying high-level visual processing.
| S-EPMC2679579 | biostudies-literature
Project description:Humans rely heavily on the shape of objects to recognise them. Recently, it has been argued that Convolutional Neural Networks (CNNs) can also show a shape-bias, provided their learning environment contains this bias. This has led to the proposal that CNNs provide good mechanistic models of shape-bias and, more generally, human visual processing. However, it is also possible that humans and CNNs show a shape-bias for very different reasons, namely, shape-bias in humans may be a consequence of architectural and cognitive constraints whereas CNNs show a shape-bias as a consequence of learning the statistics of the environment. We investigated this question by exploring shape-bias in humans and CNNs when they learn in a novel environment. We observed that, in this new environment, humans (i) focused on shape and overlooked many non-shape features, even when non-shape features were more diagnostic, (ii) learned based on only one out of multiple predictive features, and (iii) failed to learn when global features, such as shape, were absent. This behaviour contrasted with the predictions of a statistical inference model with no priors, showing the strong role that shape-bias plays in human feature selection. It also contrasted with CNNs that (i) preferred to categorise objects based on non-shape features, and (ii) increased reliance on these non-shape features as they became more predictive. This was the case even when the CNN was pre-trained to have a shape-bias and the convolutional backbone was frozen. These results suggest that shape-bias has a different source in humans and CNNs: while learning in CNNs is driven by the statistical properties of the environment, humans are highly constrained by their previous biases, which suggests that cognitive constraints play a key role in how humans learn to recognise novel objects.
| S-EPMC9132323 | biostudies-literature