Object Category Learning Research Articles

Memory Reactivation during Sleep Does Not Act Holistically on Object Memory.

Memory reactivation during sleep is thought to facilitate memory consolidation. Most sleep reactivation research has examined how reactivation of specific facts, objects, and associations benefits their overall retention. However, our memories are not unitary, and not all features of a memory persist in tandem over time. Instead, our memories are transformed, with some features strengthened and others weakened. Does sleep reactivation drive memory transformation? We leveraged the Targeted Memory Reactivation technique in an object category learning paradigm to examine this question. Participants (20 female, 14 male) learned three categories of novel objects, where each object had unique, distinguishing features as well as features shared with other members of its category. We used a real-time EEG protocol to cue the reactivation of these objects during sleep at moments optimized to generate reactivation events. We found that reactivation improved memory for distinguishing features while worsening memory for shared features, suggesting a differentiation process. The results indicate that sleep reactivation does not act holistically on object memories, instead supporting a transformation where some features are enhanced over others.

MFNet: Multiclass Few-Shot Segmentation Network With Pixel-Wise Metric Learning

In visual recognition tasks, few-shot learning requires the ability to learn object categories with few support examples. Its re-popularity in light of the deep learning development is mainly in image classification. This work focuses on few-shot semantic segmentation, which is still a largely unexplored field. A few recent advances are often restricted to single-class few-shot segmentation. In this paper, we first present a novel multi-way (class) encoding and decoding architecture which effectively fuses multi-scale query information and multi-class support information into one query-support embedding. Multi-class segmentation is directly decoded upon this embedding. For better feature fusion, a multi-level attention mechanism is proposed within the architecture, which includes the attention for support feature modulation and attention for multi-scale combination. Last, to enhance the embedding space learning, an additional pixel-wise metric learning module is introduced with triplet loss formulated on the pixel-level of the query-support embedding. Extensive experiments on standard benchmarks PASCAL- <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$5^{i}$ </tex-math></inline-formula> and COCO- <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$20^{i}$ </tex-math></inline-formula> show clear benefits of our method over the state of the art in multi-class few-shot segmentation.

OrthographicNet: A Deep Transfer Learning Approach for 3-D Object Recognition in Open-Ended Domains

Nowadays, service robots are appearing more and more in our daily life. For this type of robot, open-ended object category learning and recognition is necessary since no matter how extensive the training data used for batch learning, the robot might be faced with a <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">new object</i> when operating in a real-world environment. In this article, we present <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">OrthographicNet</i> , a convolutional neural network based model, for 3-D object recognition in open-ended domains. In particular, <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">OrthographicNet</i> generates a global rotation- and scale-invariant representation for a given 3-D object, enabling robots to recognize the same or similar objects seen from different perspectives. Experimental results show that our approach yields significant improvements over the previous state-of-the-art approaches concerning object recognition performance and scalability in open-ended scenarios. Moreover, <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">OrthographicNet</i> demonstrates the capability of learning new categories from very few examples on-site. Regarding real-time performance, three real-world demonstrations validate the promising performance of the proposed architecture.

Proposed fMRI Study: The Role of Self-Generated Object Formation in Novel Object Category Learning

Recent research indicates that the self-produced visual-motor nature of handwriting provides variable visual output that better facilitates symbol understanding (Li &amp; James 2016). In addition, viewing novel objects/hearing novel verbs that were learned through active manipulation resulted in greater motor activation in the brain than learning through passive viewing (James &amp; Swain 2011). The proposed study attempts to investigate the understanding and neural underpinnings of novel objects when learned in a self-production condition similar to handwriting: forming objects with clay. 7-8 year-old participants will learn novel object categories through three conditions: a high active condition in which participants form objects with clay, a low active condition in which participants actively hold/explore pre-made objects, and a passive condition in which participants watch the experimenter hold pre-made objects. Following this training session, an object-sorting task will be used to assess the participants’ knowledge of the object categories. Finally, a fMRI session will attempt to investigate motor and whole-brain activation differences between the two active conditions.

The resonant brain: How attentive conscious seeing regulates action sequences that interact with attentive cognitive learning, recognition, and prediction

This article describes mechanistic links that exist in advanced brains between processes that regulate conscious attention, seeing, and knowing, and those that regulate looking and reaching. These mechanistic links arise from basic properties of brain design principles such as complementary computing, hierarchical resolution of uncertainty, and adaptive resonance. These principles require conscious states to mark perceptual and cognitive representations that are complete, context sensitive, and stable enough to control effective actions. Surface–shroud resonances support conscious seeing and action, whereas feature–category resonances support learning, recognition, and prediction of invariant object categories. Feedback interactions between cortical areas such as peristriate visual cortical areas V2, V3A, and V4, and the lateral intraparietal area (LIP) and inferior parietal sulcus (IPS) of the posterior parietal cortex (PPC) control sequences of saccadic eye movements that foveate salient features of attended objects and thereby drive invariant object category learning. Learned categories can, in turn, prime the objects and features that are attended and searched. These interactions coordinate processes of spatial and object attention, figure–ground separation, predictive remapping, invariant object category learning, and visual search. They create a foundation for learning to control motor-equivalent arm movement sequences, and for storing these sequences in cognitive working memories that can trigger the learning of cognitive plans with which to read out skilled movement sequences. Cognitive–emotional interactions that are regulated by reinforcement learning can then help to select the plans that control actions most likely to acquire valued goal objects in different situations. Many interdisciplinary psychological and neurobiological data about conscious and unconscious behaviors in normal individuals and clinical patients have been explained in terms of these concepts and mechanisms.

Defining the Role Of Language in Infants' Object Categorization with Eye-tracking Paradigms.

Assessing infant category learning is a challenging but vital aspect of studying infant cognition. By employing a familiarization-test paradigm, we straightforwardly measure infants' success in learning a novel category while relying only on their looking behavior. Moreover, the paradigm can directly measure the impact of different auditory signals on the infant categorization across a range of ages. For instance, we assessed how 2-year-olds learn categories in a variety of labeling environments: in our task, 2-year-olds successfully learned categories when all exemplars were labeledor the first two exemplars were labeled, but they failed to categorize when no exemplars were labeled or only the final two exemplars were labeled. To determine infants' success in such tasks, researchers can examine both the overall preference displayed by infants in each condition and infants' pattern of looking over the course of the test phase, using an eye-tracker to provide fine-grained time-course data. Thus, we present a powerful paradigm for identifying the role of language, or any auditory signal, in infants' object category learning.

Lifelong Learning of Spatiotemporal Representations With Dual-Memory Recurrent Self-Organization.

Artificial autonomous agents and robots interacting in complex environments are required to continually acquire and fine-tune knowledge over sustained periods of time. The ability to learn from continuous streams of information is referred to as lifelong learning and represents a long-standing challenge for neural network models due to catastrophic forgetting in which novel sensory experience interferes with existing representations and leads to abrupt decreases in the performance on previously acquired knowledge. Computational models of lifelong learning typically alleviate catastrophic forgetting in experimental scenarios with given datasets of static images and limited complexity, thereby differing significantly from the conditions artificial agents are exposed to. In more natural settings, sequential information may become progressively available over time and access to previous experience may be restricted. Therefore, specialized neural network mechanisms are required that adapt to novel sequential experience while preventing disruptive interference with existing representations. In this paper, we propose a dual-memory self-organizing architecture for lifelong learning scenarios. The architecture comprises two growing recurrent networks with the complementary tasks of learning object instances (episodic memory) and categories (semantic memory). Both growing networks can expand in response to novel sensory experience: the episodic memory learns fine-grained spatiotemporal representations of object instances in an unsupervised fashion while the semantic memory uses task-relevant signals to regulate structural plasticity levels and develop more compact representations from episodic experience. For the consolidation of knowledge in the absence of external sensory input, the episodic memory periodically replays trajectories of neural reactivations. We evaluate the proposed model on the CORe50 benchmark dataset for continuous object recognition, showing that we significantly outperform current methods of lifelong learning in three different incremental learning scenarios.

Perceiving, Learning, and Recognizing 3D Objects: An Approach to Cognitive Service Robots

There is growing need for robots that can interact with people in everyday situations. For service robots, it is not reasonable to assume that one can pre-program all object categories. Instead, apart from learning from a batch of labelled training data, robots should continuously update and learn new object categories while working in the environment. This paper proposes a cognitive architecture designed to create a concurrent 3D object category learning and recognition in an interactive and open-ended manner. In particular, this cognitive architecture provides automatic perception capabilities that will allow robots to detect objects in highly crowded scenes and learn new object categories from the set of accumulated experiences in an incremental and open-ended way. Moreover, it supports constructing the full model of an unknown object in an on-line manner and predicting next best view for improving object detection and manipulation performance. We provide extensive experimental results demonstrating system performance in terms of recognition, scalability, next-best-view prediction and real-world robotic applications.

Towards lifelong assistive robotics: A tight coupling between object perception and manipulation

Abstract This paper presents an artificial cognitive system tightly integrating object perception and manipulation for assistive robotics. This is necessary for assistive robots, not only to perform manipulation tasks in a reasonable amount of time and in an appropriate manner, but also to robustly adapt to new environments by handling new objects. In particular, this system includes perception capabilities that allow robots to incrementally learn object categories from the set of accumulated experiences and reason about how to perform complex tasks. To achieve these goals, it is critical to detect, track and recognize objects in the environment as well as to conceptualize experiences and learn novel object categories in an open-ended manner, based on human–robot interaction. Interaction capabilities were developed to enable human users to teach new object categories and instruct the robot to perform complex tasks. A naive Bayes learning approach with a Bag-of-Words object representation are used to acquire and refine object category models. Perceptual memory is used to store object experiences, feature dictionary and object category models. Working memory is employed to support communication purposes between the different modules of the architecture. A reactive planning approach is used to carry out complex tasks. To examine the performance of the proposed architecture, a quantitative evaluation and a qualitative analysis are carried out. Experimental results show that the proposed system is able to interact with human users, learn new object categories over time, as well as perform complex tasks.

Desirability, availability, credit assignment, category learning, and attention: Cognitive-emotional and working memory dynamics of orbitofrontal, ventrolateral, and dorsolateral prefrontal cortices.

Background:The prefrontal cortices play an essential role in cognitive-emotional and working memory processes through interactions with multiple brain regions.Methods:This article further develops a unified neural architecture that explains many recent and classical data about prefrontal function and makes testable predictions.Results:Prefrontal properties of desirability, availability, credit assignment, category learning, and feature-based attention are explained. These properties arise through interactions of orbitofrontal, ventrolateral prefrontal, and dorsolateral prefrontal cortices with the inferotemporal cortex, perirhinal cortex, parahippocampal cortices; ventral bank of the principal sulcus, ventral prearcuate gyrus, frontal eye fields, hippocampus, amygdala, basal ganglia, hypothalamus, and visual cortical areas V1, V2, V3A, V4, middle temporal cortex, medial superior temporal area, lateral intraparietal cortex, and posterior parietal cortex. Model explanations also include how the value of visual objects and events is computed, which objects and events cause desired consequences and which may be ignored as predictively irrelevant, and how to plan and act to realise these consequences, including how to selectively filter expected versus unexpected events, leading to movements towards, and conscious perception of, expected events. Modelled processes include reinforcement learning and incentive motivational learning; object and spatial working memory dynamics; and category learning, including the learning of object categories, value categories, object-value categories, and sequence categories, or list chunks.Conclusion:This article hereby proposes a unified neural theory of prefrontal cortex and its functions.

Tracking Multiple Statistics: Simultaneous Learning of Object Names and Categories in English and Mandarin Speakers.

Two experiments were conducted to examine adult learners' ability to extract multiple statistics in simultaneously presented visual and auditory input. Experiment 1 used a cross-situational learning paradigm to test whether English speakers were able to use co-occurrences to learn word-to-object mappings and concurrently form object categories based on the commonalities across training stimuli. Experiment 2 replicated the first experiment and further examined whether speakers of Mandarin, a language in which final syllables of object names are more predictive of category membership than English, were able to learn words and form object categories when trained with the same type of structures. The results indicate that both groups of learners successfully extracted multiple levels of co-occurrence and used them to learn words and object categories simultaneously. However, marked individual differences in performance were also found, suggesting possible interference and competition in processing the two concurrent streams of regularities.

Grandmother cohorts: multiple-scale brain compression dynamics during learning of object and sequence categories

ABSTRACTThis article summarises neural models of how invariant object categories are learned under conditions where eye movements freely scan a scene, and of how list categories, or chunks, are learned in response to sequences, or lists, of events that are temporarily stored in working memory. During both kinds of category learning, distributed information is compressed by a category learning process into compact groups of cells that can selectively respond to this information. Adaptive Resonance Theory models describe these learning processes and enable, in a limiting case, winner-take-all grandmother cells to be learned, even in a single trial, and rapidly activated during recall trials by bottom-up direct access. The degree of compression can vary with the amount of contextual evidence, and a distributed network of multiple categories may be needed to represent an object or event, all computed using localist mechanisms. Such a network is called a grandmother cohort in the current article.

Binocular fusion and invariant category learning due to predictive remapping during scanning of a depthful scene with eye movements.

How does the brain maintain stable fusion of 3D scenes when the eyes move? Every eye movement causes each retinal position to process a different set of scenic features, and thus the brain needs to binocularly fuse new combinations of features at each position after an eye movement. Despite these breaks in retinotopic fusion due to each movement, previously fused representations of a scene in depth often appear stable. The 3D ARTSCAN neural model proposes how the brain does this by unifying concepts about how multiple cortical areas in the What and Where cortical streams interact to coordinate processes of 3D boundary and surface perception, spatial attention, invariant object category learning, predictive remapping, eye movement control, and learned coordinate transformations. The model explains data from single neuron and psychophysical studies of covert visual attention shifts prior to eye movements. The model further clarifies how perceptual, attentional, and cognitive interactions among multiple brain regions (LGN, V1, V2, V3A, V4, MT, MST, PPC, LIP, ITp, ITa, SC) may accomplish predictive remapping as part of the process whereby view-invariant object categories are learned. These results build upon earlier neural models of 3D vision and figure-ground separation and the learning of invariant object categories as the eyes freely scan a scene. A key process concerns how an object's surface representation generates a form-fitting distribution of spatial attention, or attentional shroud, in parietal cortex that helps maintain the stability of multiple perceptual and cognitive processes. Predictive eye movement signals maintain the stability of the shroud, as well as of binocularly fused perceptual boundaries and surface representations.

From brain synapses to systems for learning and memory: Object recognition, spatial navigation, timed conditioning, and movement control

This article provides an overview of neural models of synaptic learning and memory whose expression in adaptive behavior depends critically on the circuits and systems in which the synapses are embedded. It reviews Adaptive Resonance Theory, or ART, models that use excitatory matching and match-based learning to achieve fast category learning and whose learned memories are dynamically stabilized by top-down expectations, attentional focusing, and memory search. ART clarifies mechanistic relationships between consciousness, learning, expectation, attention, resonance, and synchrony. ART models are embedded in ARTSCAN architectures that unify processes of invariant object category learning, recognition, spatial and object attention, predictive remapping, and eye movement search, and that clarify how conscious object vision and recognition may fail during perceptual crowding and parietal neglect. The generality of learned categories depends upon a vigilance process that is regulated by acetylcholine via the nucleus basalis. Vigilance can get stuck at too high or too low values, thereby causing learning problems in autism and medial temporal amnesia. Similar synaptic learning laws support qualitatively different behaviors: Invariant object category learning in the inferotemporal cortex; learning of grid cells and place cells in the entorhinal and hippocampal cortices during spatial navigation; and learning of time cells in the entorhinal–hippocampal system during adaptively timed conditioning, including trace conditioning. Spatial and temporal processes through the medial and lateral entorhinal–hippocampal system seem to be carried out with homologous circuit designs. Variations of a shared laminar neocortical circuit design have modeled 3D vision, speech perception, and cognitive working memory and learning. A complementary kind of inhibitory matching and mismatch learning controls movement.This article is part of a Special Issue entitled SI: Brain and Memory.

Mechanisms of object recognition: what we have learned from pigeons.

Behavioral studies of object recognition in pigeons have been conducted for 50 years, yielding a large body of data. Recent work has been directed toward synthesizing this evidence and understanding the visual, associative, and cognitive mechanisms that are involved. The outcome is that pigeons are likely to be the non-primate species for which the computational mechanisms of object recognition are best understood. Here, we review this research and suggest that a core set of mechanisms for object recognition might be present in all vertebrates, including pigeons and people, making pigeons an excellent candidate model to study the neural mechanisms of object recognition. Behavioral and computational evidence suggests that error-driven learning participates in object category learning by pigeons and people, and recent neuroscientific research suggests that the basal ganglia, which are homologous in these species, may implement error-driven learning of stimulus-response associations. Furthermore, learning of abstract category representations can be observed in pigeons and other vertebrates. Finally, there is evidence that feedforward visual processing, a central mechanism in models of object recognition in the primate ventral stream, plays a role in object recognition by pigeons. We also highlight differences between pigeons and people in object recognition abilities, and propose candidate adaptive specializations which may explain them, such as holistic face processing and rule-based category learning in primates. From a modern comparative perspective, such specializations are to be expected regardless of the model species under study. The fact that we have a good idea of which aspects of object recognition differ in people and pigeons should be seen as an advantage over other animal models. From this perspective, we suggest that there is much to learn about human object recognition from studying the “simple” brains of pigeons.

Supplemental Material for The Perceptual Effects of Learning Object Categories That Predict Perceptual Goals

Supplemental Material for The Perceptual Effects of Learning Object Categories That Predict Perceptual Goals

The perceptual effects of learning object categories that predict perceptual goals.

In classic category learning studies, subjects typically learn to assign items to 1 of 2 categories, with no further distinction between how items on each side of the category boundary should be treated. In real life, however, we often learn categories that dictate further processing goals, for instance, with objects in only 1 category requiring further individuation. Using methods from category learning and perceptual expertise, we studied the perceptual consequences of experience with objects in tasks that rely on attention to different dimensions in different parts of the space. In 2 experiments, subjects first learned to categorize complex objects from a single morphspace into 2 categories based on 1 morph dimension, and then learned to perform a different task, either naming or a local feature judgment, for each of the 2 categories. A same-different discrimination test before and after each training measured sensitivity to feature dimensions of the space. After initial categorization, sensitivity increased along the category-diagnostic dimension. After task association, sensitivity increased more for the category that was named, especially along the nondiagnostic dimension. The results demonstrate that local attentional weights, associated with individual exemplars as a function of task requirements, can have lasting effects on perceptual representations.

A co-boost framework for learning object categories from Google Images with 1st and 2nd order features

Conventional object recognition techniques rely heavily on manually annotated image datasets to achieve good performances. However, collecting high quality datasets is really laborious. The image search engines such as Google Images seem to provide quantities of object images. Unfortunately, a large portion of the search images are irrelevant. In this paper, we propose a semi-supervised framework for learning visual categories from Google Images. We exploit a co-training algorithm, the CoBoost algorithm, and integrate it with two kinds of features, the 1st and 2nd order features, which define bag of words representation and spatial relationship between local features, respectively. We create two boosting classifiers based on the 1st and 2nd order features in the training, during which one classifier provides labels for the other. The 2nd order features are generated dynamically rather than extracted exhaustively to avoid high computation. An active learning technique is also introduced to further improve the performance. Experimental results show that the object models learned from Google Images by our method are competitive with the state-of-the-art unsupervised approaches and some supervised techniques on the standard benchmark datasets.

Attention-Guided Organized Perception and Learning of Object Categories Based on Probabilistic Latent Variable Models

This paper proposes a probabilistic model of object category learning in conjunction with attention-guided organized perception. This model consists of a model of attention-guided organized perception of object segments on Markov random fields and a model of learning object categories based on a probabilistic latent component analysis. In attention guided organized perception, concurrent figure-ground segmentation is performed on dynamically-formed Markov random fields around salient preattentive points and co-occurring segments are grouped in the neighborhood of selective attended segments. In object category learning, a set of classes of each object category is obtained based on the probabilistic latent component analysis with the variable number of classes from bags of features of segments extracted from images which contain the categorical objects in context and an object category is represented by a composite of object classes. Through experiments using two image data sets, it is shown that the model learns a probabilistic structure of intra-categorical composition and inter-categorical difference of object categories and achieves high performance in object category recognition.

Web-enhanced object category learning for domestic robots

We present a system architecture for domestic robots that allows them to learn object categories after one sample object was initially learned. We explore the situation in which a human teaches a r...