paper-with-me

Papers

Trash or Treasure? An Interactive Dual-Stream Strategy for Single Image Reflection Separation

2021-10-20 · NeurIPS 2021 12 · Qiming Hu, Xiaojie Guo

Single image reflection separation (SIRS), as a representative blind source separation task, aims to recover two layers, $\textit{i.e.}$, transmission and reflection, from one mixed observation, which is challenging due to the highly ill-posed nature. Existing deep learning based solutions typically restore the target layers individually, or with some concerns at the end of the output, barely taking into account the interaction across the two streams/branches. In order to utilize information more efficiently, this work presents a general yet simple interactive strategy, namely $\textit{your trash is my treasure}$ (YTMT), for constructing dual-stream decomposition networks. To be specific, we explicitly enforce the two streams to communicate with each other block-wisely. Inspired by the additive property between the two components, the interactive path can be easily built via transferring, instead of discarding, deactivated information by the ReLU rectifier from one stream to the other. Both ablation studies and experimental results on widely-used SIRS datasets are conducted to demonstrate the efficacy of YTMT, and reveal its superiority over other state-of-the-art alternatives. The implementation is quite simple and our code is publicly available at $\href{https://github.com/mingcv/YTMT-Strategy}{\textit{https://github.com/mingcv/YTMT-Strategy}}$.

📄 PDF Abstract BibTeX arXiv:2110.10546

Code (1)

mingcv/ytmt-strategy 공식 구현 pytorch

Tasks

blind source separationReflection Removal

Similar Papers 제목 키워드 기반

Trash to Treasure: Low-Light Object Detection via Decomposition-and-Aggregation

2023-09-07 · Xiaohan Cui, Long Ma, Tengyu Ma, JinYuan Liu 외

Object detection in low-light scenarios has attracted much attention in the past few years. A mainstream and representative scheme introduces enhancers as the pre-processing for regular detectors. However, because of the…

object-detectionObject Detection

Trash to Treasure: Using text-to-image models to inform the design of physical artefacts

2023-02-01 · Amy Smith, Hope Schroeder, Ziv Epstein, Michael Cook 외

Text-to-image generative models have recently exploded in popularity and accessibility. Yet so far, use of these models in creative tasks that bridge the 2D digital world and the creation of physical artefacts has been u…

Prompt Engineering

Trash to Treasure: Harvesting OOD Data with Cross-Modal Matching for Open-Set Semi-Supervised Learning

2021-08-12 · ICCV 2021 10 · Junkai Huang, Chaowei Fang, Weikai Chen, Zhenhua Chai 외

Open-set semi-supervised learning (open-set SSL) investigates a challenging but practical scenario where out-of-distribution (OOD) samples are contained in the unlabeled data. While the mainstream technique seeks to comp…

Binary Classification

One Man's Trash is Another Man's Treasure: Resisting Adversarial Examples by Adversarial Examples

2019-11-25 · CVPR 2020 6 · Chang Xiao, Changxi Zheng

Modern image classification systems are often built on deep neural networks, which suffer from adversarial examples--images with deliberately crafted, imperceptible noise to mislead the network's classification. To defen…

ClassificationGeneral Classificationimage-classificationImage Classification

Turning Trash into Treasure: Accelerating Inference of Large Language Models with Token Recycling

2024-08-16 · Xianzhen Luo, YiXuan Wang, Qingfu Zhu, Zhiming Zhang 외

Massive parameters of LLMs have made inference latency a fundamental bottleneck. Speculative decoding represents a lossless approach to accelerate inference through a guess-and-verify paradigm. Some methods rely on addit…

Retrieval