Fine-grained object recognition with Gnostic Fields

Kanan, Christopher

doi:10.1109/wacv.2014.6836122

Cited by 14 publications

(4 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [13], a new vessel recognition dataset, MARVEL, is introduced, which is used to perform three tasks: vessel identity verification through CNNs (derived from [29]), vessel retrieval through multi-class SVMs [30] and vessel recognition by employing VGG-F (a VGG-variant) and Alexnet networks [31]. The VAIS dataset is presented in [14], encompassing maritime images in the visible and infrared spectrums, and three classification methods are employed: CNNs [32], gnostic fields [33] and a combination of both. In [15], Zwemer et al provide a dataset for maritime vessel detection and tracking and perform cross-validation on viewpoints to assess the influence of scene context on the detection performance of various implementations of the SSD detector [28].…”

Section: Maritime Object Detectionmentioning

confidence: 99%

A Benchmark for Maritime Object Detection with Centernet on an Improved Dataset, ABOships-PLUS

Iancu,

Winsten,

Soloviev

et al. 2023

JMSE

View full text Add to dashboard Cite

Object detection from waterborne imagery is an essential aspect in maritime traffic management, navigation safety and coastal security. Building efficient autonomous systems, which can take decisions in critical situations, requires an integration of complex object detectors in real time. Object detectors trained on generic datasets often give unsatisfactory results in complex scenarios like the maritime environment, since only a fraction of their images contain maritime vessels. Publicly available domain-specific datasets are scarce, and they are limited in the number of images and annotations. Compared to object detection in applications such as autonomous vehicles, maritime vessel detection is considerably reduced in computer vision research. This creates a deficit in exhaustive benchmarking studies for maritime detection datasets. To bridge this gap, we relabel the ABOships dataset and benchmark a state-of-the-art center-based detector, Centernet, on the newly relabeled dataset, ABOships-PLUS. We explore its performance under different feature extractors, and investigate the effect of object size and inter-class variation on detection accuracy. The reported benchmarking illustrates that the ABOships-PLUS dataset is adequate to use in supervised domain adaptation. The experimental results show that Centernet with DLA (Deep Layer Aggregation) as a feature extractor achieved the highest accuracy in detecting maritime objects overall (with mean average precision 74.4%).

show abstract

Section: Maritime Object Detectionmentioning

confidence: 99%

A Benchmark for Maritime Object Detection with Centernet on an Improved Dataset, ABOships-PLUS

Iancu,

Winsten,

Soloviev

et al. 2023

JMSE

View full text Add to dashboard Cite

show abstract

“…Wang et al (2015) use recursive ICA to automatically learn visual features that accord with those found in the early visual cortex. The authors subsequently model the object recognition pathway using gnostic fields (Kanan, 2013(Kanan, , 2014, a brain-inspired model of object categorization. Wang et al (2015) demonstrate that the features in the first ICA layer, trained on natural images, are oriented-edges with the color opponent characteristics typical of V1 neurons (dark-light, yellowblue, red-green).…”

Section: Opponency In Artificial Visionmentioning

confidence: 99%

How Convolutional Neural Network Architecture Biases Learned Opponency and Color Tuning

2021

View full text Add to dashboard Cite

Recent work suggests that changing convolutional neural network (CNN) architecture by introducing a bottleneck in the second layer can yield changes in learned function. To understand this relationship fully requires a way of quantitatively comparing trained networks. The fields of electrophysiology and psychophysics have developed a wealth of methods for characterizing visual systems that permit such comparisons. Inspired by these methods, we propose an approach to obtaining spatial and color tuning curves for convolutional neurons that can be used to classify cells in terms of their spatial and color opponency. We perform these classifications for a range of CNNs with different depths and bottleneck widths. Our key finding is that networks with a bottleneck show a strong functional organization: almost all cells in the bottleneck layer become both spatially and color opponent, and cells in the layer following the bottleneck become nonopponent. The color tuning data can further be used to form a rich understanding of how color a network encodes color. As a concrete demonstration, we show that shallower networks without a bottleneck learn a complex nonlinear color system, whereas deeper networks with tight bottlenecks learn a simple channel opponent code in the bottleneck layer. We develop a method of obtaining a hue sensitivity curve for a trained CNN that enables high-level insights that complement the low-level findings from the color tuning data. We go on to train a series of networks under different conditions to ascertain the robustness of the discussed results. Ultimately our methods and findings coalesce with prior art, strengthening our ability to interpret trained CNNs and furthering our understanding of the connection between architecture and learned representation. Trained models and code for all experiments are available at https://github.com/ecs-vlc/opponency .

show abstract

“…A gnostic field consists of competing gnostic sets, with each set containing a population of gnostic neurons that act as template matchers for a particular class. More recently, gnostic fields were turned into an algorithm and achieved good results on various object recognition benchmarks [19,20]. Gnostic fields generally operate on dense topologically organized image descriptors, and each gnostic set compares each descriptor to the learned templates for the class.…”

Section: Appearance Saliencymentioning

confidence: 99%

Online tracking using saliency

Yousefhussien

Browning

Kanan

2016

2016 IEEE Winter Conference on Applications of Computer Vision (WACV)

Self Cite

View full text Add to dashboard Cite

When tracking small moving objects, primates use smooth pursuit eye movements to keep a target in the center of the field of view. In this paper, we propose the Smooth Pursuit tracking algorithm, which uses three kinds of saliency maps to perform online target tracking: appearance, location, and motion. In addition to tracking single targets, our method can track multiple targets with little additional overhead. The appearance saliency map uses deep convolutional neural network features along with gnostic fields, a brain-inspired model for object recognition. The location saliency map predicts where the object will move next. Finally, the motion saliency map indicates which objects are moving in the scene. We combine all three saliency maps into a smooth pursuit map, which is used to generate bounding boxes for tracked objects. We evaluate our algorithm and others from the literature on a vehicle tracking task. Our approach achieves the best overall performance, including being the only method we tested capable of handling long-term occlusions.

show abstract

Fine-grained object recognition with Gnostic Fields

Cited by 14 publications

References 30 publications

A Benchmark for Maritime Object Detection with Centernet on an Improved Dataset, ABOships-PLUS

A Benchmark for Maritime Object Detection with Centernet on an Improved Dataset, ABOships-PLUS

How Convolutional Neural Network Architecture Biases Learned Opponency and Color Tuning

Online tracking using saliency

Contact Info

Product

Resources

About