paper-with-me

홈 › Papers

Semantics Meet Saliency: Exploring Domain Affinity and Models for Dual-Task Prediction

2018-07-25 · Md Amirul Islam, Mahmoud Kalash, Neil D. B. Bruce

Much research has examined models for prediction of semantic labels or instances including dense pixel-wise prediction. The problem of predicting salient objects or regions of an image has also been examined in a similar light. With that said, there is an apparent relationship between these two problem domains in that the composition of a scene and associated semantic categories is certain to play into what is deemed salient. In this paper, we explore the relationship between these two problem domains. This is carried out in constructing deep neural networks that perform both predictions together albeit with different configurations for flow of conceptual information related to each distinct problem. This is accompanied by a detailed analysis of object co-occurrences that shed light on dataset bias and semantic precedence specific to individual categories.

📄 PDF Abstract BibTeX arXiv:1807.09430

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Leveraging Auxiliary Tasks with Affinity Learning for Weakly Supervised Semantic Segmentation

2021-07-25 · ICCV 2021 10 · Lian Xu, Wanli Ouyang, Mohammed Bennamoun, Farid Boussaid 외

Semantic segmentation is a challenging task in the absence of densely labelled data. Only relying on class activation maps (CAM) with image-level labels provides deficient segmentation supervision. Prior works thus consi…

Auxiliary Learningimage-classificationImage ClassificationMulti-Label Image Classification+7

Auxiliary Tasks Enhanced Dual-affinity Learning for Weakly Supervised Semantic Segmentation

2024-03-02 · Lian Xu, Mohammed Bennamoun, Farid Boussaid, Wanli Ouyang 외

Most existing weakly supervised semantic segmentation (WSSS) methods rely on Class Activation Mapping (CAM) to extract coarse class-specific localization maps using image-level labels. Prior works have commonly used an o…

Auxiliary Learningimage-classificationImage ClassificationMulti-Label Image Classification+6

Exploring Opinion-unaware Video Quality Assessment with Semantic Affinity Criterion

2023-02-26 · HaoNing Wu, Liang Liao, Jingwen Hou, Chaofeng Chen 외

Recent learning-based video quality assessment (VQA) algorithms are expensive to implement due to the cost of data collection of human quality opinions, and are less robust across various scenarios due to the biases of t…

Video Quality AssessmentVisual Question Answering (VQA)

Exploring Saliency Bias in Manipulation Detection

2024-02-12 · Joshua Krinsky, Alan Bettis, Qiuyu Tang, Daniel Moreira 외

The social media-fuelled explosion of fake news and misinformation supported by tampered images has led to growth in the development of models and datasets for image manipulation detection. However, existing detection me…

Image ManipulationImage Manipulation DetectionMisinformation

What Do Deep Saliency Models Learn about Visual Attention?

2023-10-14 · NeurIPS 2023 11 · Shi Chen, Ming Jiang, Qi Zhao

In recent years, deep saliency models have made significant progress in predicting human visual attention. However, the mechanisms behind their success remain largely unexplained due to the opaque nature of deep neural n…

Saliency Prediction