paper-with-me

Papers

Underwater Ranker: Learn Which Is Better and How to Be Better

2022-08-14 · Chunle Guo, Ruiqi Wu, Xin Jin, Linghao Han, Zhi Chai, Weidong Zhang, Chongyi Li

In this paper, we present a ranking-based underwater image quality assessment (UIQA) method, abbreviated as URanker. The URanker is built on the efficient conv-attentional image Transformer. In terms of underwater images, we specially devise (1) the histogram prior that embeds the color distribution of an underwater image as histogram token to attend global degradation and (2) the dynamic cross-scale correspondence to model local degradation. The final prediction depends on the class tokens from different scales, which comprehensively considers multi-scale dependencies. With the margin ranking loss, our URanker can accurately rank the order of underwater images of the same scene enhanced by different underwater image enhancement (UIE) algorithms according to their visual quality. To achieve that, we also contribute a dataset, URankerSet, containing sufficient results enhanced by different UIE algorithms and the corresponding perceptual rankings, to train our URanker. Apart from the good performance of URanker, we found that a simple U-shape UIE network can obtain promising performance when it is coupled with our pre-trained URanker as additional supervision. In addition, we also propose a normalization tail that can significantly improve the performance of UIE networks. Extensive experiments demonstrate the state-of-the-art performance of our method. The key designs of our method are discussed. We will release our dataset and code.

📄 PDF Abstract BibTeX arXiv:2208.06857

Code (1)

RQ-Wu/UnderwaterRanker 공식 구현 pytorch

Tasks

Image EnhancementImage Quality AssessmentUIE

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
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…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Position-Wise Feed-Forward Layer 설명 없음
Adam 설명 없음

Similar Papers 제목 키워드 기반

Underwater Acoustic Communication Channel Modeling using Deep Learning

2022-01-25 · Oluwaseyi Onasami, Damilola Adesina, Lijun Qian

With the recent increase in the number of underwater activities, having effective underwater communication systems has become increasingly important. Underwater acoustic communication has been widely used but greatly imp…

Deep Learning

Underwater Color Restoration Using U-Net Denoising Autoencoder

2019-05-22 · Yousif Hashisho, Mohamad Albadawi, Tom Krause, Uwe Freiherr von Lukas

Visual inspection of underwater structures by vehicles, e.g. remotely operated vehicles (ROVs), plays an important role in scientific, military, and commercial sectors. However, the automatic extraction of information us…

Denoising

Underwater Image Super-Resolution using Generative Adversarial Network-based Model

2022-11-07 · Alireza Aghelan, Modjtaba Rouhani

Single image super-resolution (SISR) models are able to enhance the resolution and visual quality of underwater images and contribute to a better understanding of underwater environments. The integration of these models …

Generative Adversarial NetworkImage Super-ResolutionSuper-Resolution

Language Model Re-rankers are Steered by Lexical Similarities

2025-02-24 · Lovisa Hagström, Ercong Nie, Ruben Halifa, Helmut Schmid 외

Language model (LM) re-rankers are used to refine retrieval results for retrieval-augmented generation (RAG). They are more expensive than lexical matching methods like BM25 but assumed to better process semantic informa…

Language ModelingLanguage ModellingRAGRetrieval+1

BERT meets Cranfield: Uncovering the Properties of Full Ranking on Fully Labeled Data

2021-04-01 · EACL 2021 2 · Negin Ghasemi, Djoerd Hiemstra

Recently, various information retrieval models have been proposed based on pre-trained BERT models, achieving outstanding performance. The majority of such models have been tested on data collections with partial relevan…

Information RetrievalRetrieval