Distinct Class-Specific Saliency Maps for Weakly Supervised Semantic Segmentation
نویسندگان
چکیده
Improved points (each point contributes 1~3pt improvement) Fully Convolutional Net Guided back propagation [2] Use the derivatives of multiple intermediate layers Aggregate multi-scale class saliency maps (3 scales) Assumption Raw saliency maps are affected by both class-specific saliency and generic object-ness The degree of class saliency factors should be larger than the generic object-ness factor. Background regions do not respond.
منابع مشابه
Discovering Class-Specific Pixels for Weakly-Supervised Semantic Segmentation
We propose an approach to discover class-specific pixels for the weakly-supervised semantic segmentation task. We show that properly combining saliency and attention maps allows us to obtain reliable cues capable of significantly boosting the performance. First, we propose a simple yet powerful hierarchical approach to discover the classagnostic salient regions, obtained using a salient object ...
متن کاملDeep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps
This paper addresses the visualisation of image classification models, learnt using deep Convolutional Networks (ConvNets). We consider two visualisation techniques, based on computing the gradient of the class score with respect to the input image. The first one generates an image, which maximises the class score [5], thus visualising the notion of the class, captured by a ConvNet. The second ...
متن کاملCo-salient Object Detection Based on Deep Saliency Networks and Seed Propagation over an Integrated Graph
This paper presents a co-salient object detection method to find common salient regions in a set of images. We utilize deep saliency networks to transfer co-saliency prior knowledge and better capture high-level semantic information, and the resulting initial co-saliency maps are enhanced by seed propagation steps over an integrated graph. The deep saliency networks are trained in a supervised ...
متن کاملAmortized Inference and Learning in Latent Conditional Random Fields for Weakly-Supervised Semantic Image Segmentation
Conditional random fields (CRFs) are commonly employed as a post-processing tool for image segmentation tasks. The unary potentials of the CRF are often learnt independently by a classifier, thereby decoupling the inference in CRF from the training of classifier. Such a scheme works effectively, when pixel-level labelling is available for all the images. However, in absence of pixel-level label...
متن کاملSaliency Guided End-to-End Learning for Weakly Supervised Object Detection
Weakly supervised object detection (WSOD), which is the problem of learning detectors using only image-level labels, has been attracting more and more interest. However, this problem is quite challenging due to the lack of location supervision. To address this issue, this paper integrates saliency into a deep architecture, in which the location information is explored both explicitly and implic...
متن کامل