Deep Networks Can Resemble Human Feed-forward Vision in Invariant Object Recognition
نویسندگان
چکیده
Deep convolutional neural networks (DCNNs) have attracted much attention recently, and have shown to be able to recognize thousands of object categories in natural image databases. Their architecture is somewhat similar to that of the human visual system: both use restricted receptive fields, and a hierarchy of layers which progressively extract more and more abstracted features. Yet it is unknown whether DCNNs match human performance at the task of view-invariant object recognition, whether they make similar errors and use similar representations for this task, and whether the answers depend on the magnitude of the viewpoint variations. To investigate these issues, we benchmarked eight state-of-the-art DCNNs, the HMAX model, and a baseline shallow model and compared their results to those of humans with backward masking. Unlike in all previous DCNN studies, we carefully controlled the magnitude of the viewpoint variations to demonstrate that shallow nets can outperform deep nets and humans when variations are weak. When facing larger variations, however, more layers were needed to match human performance and error distributions, and to have representations that are consistent with human behavior. A very deep net with 18 layers even outperformed humans at the highest variation level, using the most human-like representations.
منابع مشابه
Humans and Deep Networks Largely Agree on Which Kinds of Variation Make Object Recognition Harder
View-invariant object recognition is a challenging problem that has attracted much attention among the psychology, neuroscience, and computer vision communities. Humans are notoriously good at it, even if some variations are presumably more difficult to handle than others (e.g., 3D rotations). Humans are thought to solve the problem through hierarchical processing along the ventral stream, whic...
متن کاملBrain-inspired Recurrent Neural Algorithms for Advanced Object Recognition
Deep learning has enabled breakthroughs in machine learning, resulting in performance levels seeming on par with humans. This is particularly the case in computer vision where models can learn to classify objects in the images of a dataset. These datasets however often feature perfect information, whereas objects in the real world are frequently cluttered with other objects and thereby occluded...
متن کاملEffect of sound classification by neural networks in the recognition of human hearing
In this paper, we focus on two basic issues: (a) the classification of sound by neural networks based on frequency and sound intensity parameters (b) evaluating the health of different human ears as compared to of those a healthy person. Sound classification by a specific feed forward neural network with two inputs as frequency and sound intensity and two hidden layers is proposed. This process...
متن کاملDeep Sparse Coding for Invariant Multimodal Halle Berry Neurons
Deep feed-forward convolutional neural networks (CNNs) have become ubiquitous in virtually all machine learning and computer vision challenges; however, advancements in CNNs have arguably reached an engineering saturation point where incremental novelty results in minor performance gains. Although there is evidence that object classification has reached human levels on narrowly defined tasks, f...
متن کاملBasic Level Categorization Facilitates Visual Object Recognition
Recent advances in deep learning have led to significant progress in the computer vision field, especially for visual object recognition tasks. The features useful for object classification are learned by feed-forward deep convolutional neural networks (CNNs) automatically, and they are shown to be able to predict and decode neural representations in the ventral visual pathway of humans and mon...
متن کامل