Active Object Recognition with a Space-Variant Retina

Kanan, Christopher

doi:10.1155/2013/138057

Cited by 7 publications

(4 citation statements)

References 35 publications

(57 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Log-polar transformation has been applied in computational models, such as modeling the retina (Bolduc & Levine, 1998), performing active object recognition (Kanan, 2013), and modeling the determination of the focus of expansion in optical flow at different retinal eccentricities (Chessa, Maiello, Bex, & Solari, 2016). We use the well-established OpenCV method to generate log-polar transformed images, where the scale 3 parameters are , and .…”

Section: Image Preprocessingmentioning

confidence: 99%

Central and peripheral vision for scene recognition: A neurocomputational modeling exploration

Wang

Cottrell

2017

Journal of Vision

View full text Add to dashboard Cite

What are the roles of central and peripheral vision in human scene recognition? Larson and Loschky (2009) showed that peripheral vision contributes more than central vision in obtaining maximum scene recognition accuracy. However, central vision is more efficient for scene recognition than peripheral, based on the amount of visual area needed for accurate recognition. In this study, we model and explain the results of Larson and Loschky (2009) using a neurocomputational modeling approach. We show that the advantage of peripheral vision in scene recognition, as well as the efficiency advantage for central vision, can be replicated using state-of-the-art deep neural network models. In addition, we propose and provide support for the hypothesis that the peripheral advantage comes from the inherent usefulness of peripheral features. This result is consistent with data presented by Thibaut, Tran, Szaffarczyk, and Boucart (2014), who showed that patients with central vision loss can still categorize natural scenes efficiently. Furthermore, by using a deep mixture-of-experts model ("The Deep Model," or TDM) that receives central and peripheral visual information on separate channels simultaneously, we show that the peripheral advantage emerges naturally in the learning process: When trained to categorize scenes, the model weights the peripheral pathway more than the central pathway. As we have seen in our previous modeling work, learning creates a transform that spreads different scene categories into different regions in representational space. Finally, we visualize the features for the two pathways, and find that different preferences for scene categories emerge for the two pathways during the training process.

show abstract

Section: Image Preprocessingmentioning

confidence: 99%

Central and peripheral vision for scene recognition: A neurocomputational modeling exploration

Wang

Cottrell

2017

Journal of Vision

View full text Add to dashboard Cite

show abstract

“…However, we do emphasize that our aim in the present research is to investigate how the cerebral cortex operates in vision, not how computer vision attempts to solve similar problems. Within computer vision, we note that many approaches start with using independent component analysis (ICA) (Kanan, 2013 ), sparse coding (Kanan and Cottrell, 2010 ), and other mathematical approaches (Larochelle and Hinton, 2010 ) to derive what may be suitable “feature analyzers,” which are frequently compared to the responses of V1 neurons. Computer vision approaches to object identification then may take combinations of these feature analyzers, and perform statistical analyses using computer-based algorithms that are not biologically plausible such as Restricted Boltzmann Machines (RBMs) on these primitives to statistically discriminate different objects (Larochelle and Hinton, 2010 ).…”

Section: Discussionmentioning

confidence: 99%

Finding and recognizing objects in natural scenes: complementary computations in the dorsal and ventral visual systems

Rolls

Webb

2014

Front. Comput. Neurosci.

View full text Add to dashboard Cite

Searching for and recognizing objects in complex natural scenes is implemented by multiple saccades until the eyes reach within the reduced receptive field sizes of inferior temporal cortex (IT) neurons. We analyze and model how the dorsal and ventral visual streams both contribute to this. Saliency detection in the dorsal visual system including area LIP is modeled by graph-based visual saliency, and allows the eyes to fixate potential objects within several degrees. Visual information at the fixated location subtending approximately 9° corresponding to the receptive fields of IT neurons is then passed through a four layer hierarchical model of the ventral cortical visual system, VisNet. We show that VisNet can be trained using a synaptic modification rule with a short-term memory trace of recent neuronal activity to capture both the required view and translation invariances to allow in the model approximately 90% correct object recognition for 4 objects shown in any view across a range of 135° anywhere in a scene. The model was able to generalize correctly within the four trained views and the 25 trained translations. This approach analyses the principles by which complementary computations in the dorsal and ventral visual cortical streams enable objects to be located and recognized in complex natural scenes.

show abstract

“…The resulting rectangular shape is also suitable for use with ANNs and because of the nature of the transformation, under certain conditions, is invariant to scale and rotation (Schwartz, 1984 ). For these reasons, the log-polar transform is a very popular foveation technique in many vision models (Wallace et al, 1994 ; Colombo et al, 1996 ; Kanan, 2013 ; Aboudib et al, 2016 ; Akbas and Eckstein, 2017 ; Ozimek et al, 2019 ; Daucé et al, 2020 ), as well as for specific tasks such as image registration (Wolberg and Zokai, 2000 ; Sarvaiya et al, 2009 ) and object detection and tracking (Jurie, 1999 ; Metta et al, 2004 ). Due to its biological plausibility and well-established place in similar vision models, we use this method as a baseline for performance of our model.…”

Section: Related Workmentioning

confidence: 99%

Biologically Inspired Deep Learning Model for Efficient Foveal-Peripheral Vision

Lukanov

König

Pipa

2021

Front. Comput. Neurosci.

View full text Add to dashboard Cite

While abundant in biology, foveated vision is nearly absent from computational models and especially deep learning architectures. Despite considerable hardware improvements, training deep neural networks still presents a challenge and constraints complexity of models. Here we propose an end-to-end neural model for foveal-peripheral vision, inspired by retino-cortical mapping in primates and humans. Our model has an efficient sampling technique for compressing the visual signal such that a small portion of the scene is perceived in high resolution while a large field of view is maintained in low resolution. An attention mechanism for performing “eye-movements” assists the agent in collecting detailed information incrementally from the observed scene. Our model achieves comparable results to a similar neural architecture trained on full-resolution data for image classification and outperforms it at video classification tasks. At the same time, because of the smaller size of its input, it can reduce computational effort tenfold and uses several times less memory. Moreover, we present an easy to implement bottom-up and top-down attention mechanism which relies on task-relevant features and is therefore a convenient byproduct of the main architecture. Apart from its computational efficiency, the presented work provides means for exploring active vision for agent training in simulated environments and anthropomorphic robotics.

show abstract

Active Object Recognition with a Space-Variant Retina

Cited by 7 publications

References 35 publications

Central and peripheral vision for scene recognition: A neurocomputational modeling exploration

Central and peripheral vision for scene recognition: A neurocomputational modeling exploration

Finding and recognizing objects in natural scenes: complementary computations in the dorsal and ventral visual systems

Biologically Inspired Deep Learning Model for Efficient Foveal-Peripheral Vision

Contact Info

Product

Resources

About