Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userInterpretable Graph Capsule Networks for Object Recognition
71
0
0.0
(
0
)
Added by
Jindong Gu
Publication date
2020
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
Capsule Networks, as alternatives to Convolutional Neural Networks, have been proposed to recognize objects from images. The current literature demonstrates many advantages of CapsNets over CNNs. However, how to create explanations for individual classifications of CapsNets has not been well explored. The widely used saliency methods are mainly proposed for explaining CNN-based classifications; they create saliency map explanations by combining activation values and the corresponding gradients, e.g., Grad-CAM. These saliency methods require a specific architecture of the underlying classifiers and cannot be trivially applied to CapsNets due to the iterative routing mechanism therein. To overcome the lack of interpretability, we can either propose new post-hoc interpretation methods for CapsNets or modifying the model to have build-in explanations. In this work, we explore the latter. Specifically, we propose interpretable Graph Capsule Networks (GraCapsNets), where we replace the routing part with a multi-head attention-based Graph Pooling approach. In the proposed model, individual classification explanations can be created effectively and efficiently. Our model also demonstrates some unexpected benefits, even though it replaces the fundamental part of CapsNets. Our GraCapsNets achieve better classification performance with fewer parameters and better adversarial robustness, when compared to CapsNets. Besides, GraCapsNets also keep other advantages of CapsNets, namely, disentangled representations and affine transformation robustness.
rate research
Read More
We propose an interpretable Capsule Network, iCaps, for image classification. A capsule is a group of neurons nested inside each layer, and the one in the last layer is called a class capsule, which is a vector whose norm indicates a predicted probability for the class. Using the class capsule, existing Capsule Networks already provide some level of interpretability. However, there are two limitations which degrade its interpretability: 1) the class capsule also includes classification-irrelevant information, and 2) entities represented by the class capsule overlap. In this work, we address these two limitations using a novel class-supervised disentanglement algorithm and an additional regularizer, respectively. Through quantitative and qualitative evaluations on three datasets, we demonstrate that the resulting classifier, iCaps, provides a prediction along with clear rationales behind it with no performance degradation.
For a given video-based Human-Object Interaction scene, modeling the spatio-temporal relationship between humans and objects are the important cue to understand the contextual information presented in the video. With the effective spatio-temporal relationship modeling, it is possible not only to uncover contextual information in each frame but also to directly capture inter-time dependencies. It is more critical to capture the position changes of human and objects over the spatio-temporal dimension when their appearance features may not show up significant changes over time. The full use of appearance features, the spatial location and the semantic information are also the key to improve the video-based Human-Object Interaction recognition performance. In this paper, Spatio-Temporal Interaction Graph Parsing Networks (STIGPN) are constructed, which encode the videos with a graph composed of human and object nodes. These nodes are connected by two types of relations: (i) spatial relations modeling the interactions between human and the interacted objects within each frame. (ii) inter-time relations capturing the long range dependencies between human and the interacted objects across frame. With the graph, STIGPN learn spatio-temporal features directly from the whole video-based Human-Object Interaction scenes. Multi-modal features and a multi-stream fusion strategy are used to enhance the reasoning capability of STIGPN. Two Human-Object Interaction video datasets, including CAD-120 and Something-Else, are used to evaluate the proposed architectures, and the state-of-the-art performance demonstrates the superiority of STIGPN.
Convolutional Neural Networks (CNN) have demon- strated its successful applications in computer vision, speech recognition, and natural language processing. For object recog- nition, CNNs might be limited by its strict label requirement and an implicit assumption that images are supposed to be target- object-dominated for optimal solutions. However, the labeling procedure, necessitating laying out the locations of target ob- jects, is very tedious, making high-quality large-scale dataset prohibitively expensive. Data augmentation schemes are widely used when deep networks suffer the insufficient training data problem. All the images produced through data augmentation share the same label, which may be problematic since not all data augmentation methods are label-preserving. In this paper, we propose a weakly supervised CNN framework named Multiple Instance Learning Convolutional Neural Networks (MILCNN) to solve this problem. We apply MILCNN framework to object recognition and report state-of-the-art performance on three benchmark datasets: CIFAR10, CIFAR100 and ILSVRC2015 classification dataset.
We address the problem of recognizing situations in images. Given an image, the task is to predict the most salient verb (action), and fill its semantic roles such as who is performing the action, what is the source and target of the action, etc. Different verbs have different roles (e.g. attacking has weapon), and each role can take on many possible values (nouns). We propose a model based on Graph Neural Networks that allows us to efficiently capture joint dependencies between roles using neural networks defined on a graph. Experiments with different graph connectivities show that our approach that propagates information between roles significantly outperforms existing work, as well as multiple baselines. We obtain roughly 3-5% improvement over previous work in predicting the full situation. We also provide a thorough qualitative analysis of our model and influence of different roles in the verbs.
Inspired by the conclusion that humans choose the visual cortex regions corresponding to the real size of an object to analyze its features when identifying objects in the real world, this paper presents a framework, SizeNet, which is based on both the real sizes and features of objects to solve object recognition problems. SizeNet was used for object recognition experiments on the homemade Rsize dataset, and was compared with the state-of-the-art methods AlexNet, VGG-16, Inception V3, Resnet-18, and DenseNet-121. The results showed that SizeNet provides much higher accuracy rates for object recognition than the other algorithms. SizeNet can solve the two problems of correctly recognizing objects with highly similar features but real sizes that are obviously different from each other, and correctly distinguishing a target object from interference objects whose real sizes are obviously different from the target object. This is because SizeNet recognizes objects based not only on their features, but also on their real size. The real size of an object can help exclude the interference objects categories whose real size ranges do not match the real size of the object, which greatly reduces the objects categories number in the label set used for the downstream object recognition based on object features. SizeNet is of great significance for studying the interpretable computer vision. Our code and dataset will thus be made public.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
