Apples and Oranges? Assessing Image Quality over Content Recognition

2023-01-22 · Junyong You, Zheng Zhang

Image recognition and quality assessment are two important viewing tasks, while potentially following different visual mechanisms. This paper investigates if the two tasks can be performed in a multitask learning manner. A sequential spatial-channel attention module is proposed to simulate the visual attention and contrast sensitivity mechanisms that are crucial for content recognition and quality assessment. Spatial attention is shared between content recognition and quality assessment, while channel attention is solely for quality assessment. Such attention module is integrated into Transformer to build a uniform model for the two viewing tasks. The experimental results have demonstrated that the proposed uniform model can achieve promising performance for both quality assessment and content recognition tasks.

📄 PDF Abstract BibTeX arXiv:2301.09190

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음

Attention 설명 없음

Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…

Adam 설명 없음

Position-Wise Feed-Forward Layer 설명 없음

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…

Apples to Oranges: Evaluating Image Annotations from Natural Language Processing Systems

2012-06-01 · NAACL 2012 6 · Rebecca Mason, Eugene Charniak

Image Retrieval Information Retrieval Named Entity Recognition (NER)Topic Models

What Can We Do to Improve Peer Review in NLP?

2020-10-08 · Findings of the Association for Computational Linguistics 2020 · Anna Rogers, Isabelle Augenstein

Peer review is our best tool for judging the quality of conference submissions, but it is becoming increasingly spurious. We argue that a part of the problem is that the reviewers and area chairs face a poorly defined ta…

Comparing Apples and Oranges: Two Examples of the Limits of Statistical Inference, With an Application to Google Advertising Markets

2016-11-30 · John Mount, Nina Zumel

We show how the classic Cramer-Rao bound limits how accurately one can simultaneously estimate values of a large number of Google Ad campaigns (or similarly limit the measurement rate of many confounding A/B tests).

Comparison requires valid measurement: Rethinking attack success rate comparisons in AI red teaming

2026-01-26 · Alexandra Chouldechova, A. Feder Cooper, Solon Barocas, Abhinav Palia 외 arxiv

We argue that conclusions drawn about relative system safety or attack method efficacy via AI red teaming are often not supported by evidence provided by attack success rate (ASR) comparisons. We show, through conceptual…

Red Teaming

Sciama's argument on life in a random universe: Distinguishing apples from oranges

2023-06-26 · Zhi-Wei Wang, Samuel L. Braunstein

Dennis Sciama argued that the existence of life depended on many quantities, the fundamental constants, so in a random universe life should be highly unlikely. However, without full knowledge of these constants, his argu…