Conceptor Learning for Class Activation Mapping

by   Guangwu Qian, et al.

Class Activation Mapping (CAM) has been widely adopted to generate saliency maps which provides visual explanations for deep neural networks (DNNs). The saliency maps are conventionally generated by fusing the channels of the target feature map using a weighted average scheme. It is a weak model for the inter-channel relation, in the sense that it only models the relation among channels in a contrastive way (i.e., channels that play key roles in the prediction are given higher weights for them to stand out in the fusion). The collaborative relation, which makes the channels work together to provide cross reference, has been ignored. Furthermore, the model has neglected the intra-channel relation thoroughly.In this paper, we address this problem by introducing Conceptor learning into CAM generation. Conceptor leaning has been originally proposed to model the patterns of state changes in recurrent neural networks (RNNs). By relaxing the dependency of Conceptor learning to RNNs, we make Conceptor-CAM not only generalizable to more DNN architectures but also able to learn both the inter- and intra-channel relations for better saliency map generation. Moreover, we have enabled the use of Boolean operations to combine the positive and pseudo-negative evidences, which has made the CAM inference more robust and comprehensive. The effectiveness of Conceptor-CAM has been validated with both formal verifications and experiments on the dataset of the largest scale in literature. The experimental results show that Conceptor-CAM is compatible with and can bring significant improvement to all well recognized CAM-based methods, and has outperformed the state-of-the-art methods by 43.14 (Drop), 15.42 (47.54


page 1

page 3

page 4

page 5

page 6

page 8

page 10

page 11


Deriving Explanation of Deep Visual Saliency Models

Deep neural networks have shown their profound impact on achieving human...

SESS: Saliency Enhancing with Scaling and Sliding

High-quality saliency maps are essential in several machine learning app...

FD-CAM: Improving Faithfulness and Discriminability of Visual Explanation for CNNs

Class activation map (CAM) has been widely studied for visual explanatio...

Rethinking gradient weights' influence over saliency map estimation

Class activation map (CAM) helps to formulate saliency maps that aid in ...

Verifying Attention Robustness of Deep Neural Networks against Semantic Perturbations

It is known that deep neural networks (DNNs) classify an input image by ...

Understanding CNNs from excitations

For instance-level explanation, in order to reveal the relations between...

Towards Stable Co-saliency Detection and Object Co-segmentation

In this paper, we present a novel model for simultaneous stable co-salie...

Please sign up or login with your details

Forgot password? Click here to reset