SLLEN: Semantic-aware Low-light Image Enhancement Network
- URL: http://arxiv.org/abs/2211.11571v2
- Date: Mon, 15 May 2023 09:28:33 GMT
- Title: SLLEN: Semantic-aware Low-light Image Enhancement Network
- Authors: Mingye Ju, Chuheng Chen, Charles A. Guo, Jinshan Pan, Jinhui Tang, and
Dacheng Tao
- Abstract summary: We develop a semantic-aware LLE network (SSLEN) composed of a LLE main-network (LLEmN) and a SS auxiliary-network (SSaN)
Unlike currently available approaches, the proposed SLLEN is able to fully lever the semantic information, e.g., IEF, HSF, and SS dataset, to assist LLE.
Comparisons between the proposed SLLEN and other state-of-the-art techniques demonstrate the superiority of SLLEN with respect to LLE quality.
- Score: 123.44639609889802
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: How to effectively explore semantic feature is vital for low-light image
enhancement (LLE). Existing methods usually utilize the semantic feature that
is only drawn from the output produced by high-level semantic segmentation (SS)
network. However, if the output is not accurately estimated, it would affect
the high-level semantic feature (HSF) extraction, which accordingly interferes
with LLE. To this end, we develop a simple and effective semantic-aware LLE
network (SSLEN) composed of a LLE main-network (LLEmN) and a SS
auxiliary-network (SSaN). In SLLEN, LLEmN integrates the random intermediate
embedding feature (IEF), i.e., the information extracted from the intermediate
layer of SSaN, together with the HSF into a unified framework for better LLE.
SSaN is designed to act as a SS role to provide HSF and IEF. Moreover, thanks
to a shared encoder between LLEmN and SSaN, we further propose an alternating
training mechanism to facilitate the collaboration between them. Unlike
currently available approaches, the proposed SLLEN is able to fully lever the
semantic information, e.g., IEF, HSF, and SS dataset, to assist LLE, thereby
leading to a more promising enhancement performance. Comparisons between the
proposed SLLEN and other state-of-the-art techniques demonstrate the
superiority of SLLEN with respect to LLE quality over all the comparable
alternatives.
Related papers
- FANet: Feature Amplification Network for Semantic Segmentation in Cluttered Background [9.970265640589966]
Existing deep learning approaches leave out the semantic cues that are crucial in semantic segmentation present in complex scenarios.
We propose a feature amplification network (FANet) as a backbone network that incorporates semantic information using a novel feature enhancement module at multi-stages.
Our experimental results demonstrate the state-of-the-art performance compared to existing methods.
arXiv Detail & Related papers (2024-07-12T15:57:52Z) - Non-Federated Multi-Task Split Learning for Heterogeneous Sources [17.47679789733922]
We introduce a new architecture and methodology to perform multi-task learning for heterogeneous data sources efficiently.
We show through theoretical analysis that MTSL can achieve fast convergence by tuning the learning rate of the server and clients.
arXiv Detail & Related papers (2024-05-31T19:27:03Z) - Continual Learning: Forget-free Winning Subnetworks for Video Representations [75.40220771931132]
Winning Subnetwork (WSN) in terms of task performance is considered for various continual learning tasks.
It leverages pre-existing weights from dense networks to achieve efficient learning in Task Incremental Learning (TIL) and Task-agnostic Incremental Learning (TaIL) scenarios.
The use of Fourier Subneural Operator (FSO) within WSN is considered for Video Incremental Learning (VIL)
arXiv Detail & Related papers (2023-12-19T09:11:49Z) - AAFACE: Attribute-aware Attentional Network for Face Recognition [9.766991422985598]
We present a new multi-branch neural network that simultaneously performs soft biometric (SB) prediction as an auxiliary modality and face recognition (FR) as the main task.
Our proposed network named AAFace utilizes SB attributes to enhance the discriminative ability of FR representation.
Our proposed AAI module is not only fully context-aware but also capable of learning complex relationships between input features.
arXiv Detail & Related papers (2023-08-14T16:24:35Z) - High-Similarity-Pass Attention for Single Image Super-Resolution [81.56822938033118]
Recent developments in the field of non-local attention (NLA) have led to a renewed interest in self-similarity-based single image super-resolution (SISR)
We introduce a concise yet effective soft thresholding operation to obtain high-similarity-pass attention (HSPA)
To demonstrate the effectiveness of the HSPA, we constructed a deep high-similarity-pass attention network (HSPAN)
arXiv Detail & Related papers (2023-05-25T06:24:14Z) - Self-Ensembling GAN for Cross-Domain Semantic Segmentation [107.27377745720243]
This paper proposes a self-ensembling generative adversarial network (SE-GAN) exploiting cross-domain data for semantic segmentation.
In SE-GAN, a teacher network and a student network constitute a self-ensembling model for generating semantic segmentation maps, which together with a discriminator, forms a GAN.
Despite its simplicity, we find SE-GAN can significantly boost the performance of adversarial training and enhance the stability of the model.
arXiv Detail & Related papers (2021-12-15T09:50:25Z) - Inter-class Discrepancy Alignment for Face Recognition [55.578063356210144]
We propose a unified framework calledInter-class DiscrepancyAlignment(IDA)
IDA-DAO is used to align the similarity scores considering the discrepancy between the images and its neighbors.
IDA-SSE can provide convincing inter-class neighbors by introducing virtual candidate images generated with GAN.
arXiv Detail & Related papers (2021-03-02T08:20:08Z) - Multi-Knowledge Fusion for New Feature Generation in Generalized
Zero-Shot Learning [4.241513887019675]
We propose a novel generative ZSL method to learn more generalized features from multi-knowledge with continuously generated new semantics in semantic-to-visual embedding.
We show that our approach can achieve significantly better performance compared to existing state-of-the-art methods on a large number of benchmarks for several ZSL tasks.
arXiv Detail & Related papers (2021-02-23T09:11:05Z) - PIN: A Novel Parallel Interactive Network for Spoken Language
Understanding [68.53121591998483]
In the existing RNN-based approaches, ID and SF tasks are often jointly modeled to utilize the correlation information between them.
The experiments on two benchmark datasets, i.e., SNIPS and ATIS, demonstrate the effectiveness of our approach.
More encouragingly, by using the feature embedding of the utterance generated by the pre-trained language model BERT, our method achieves the state-of-the-art among all comparison approaches.
arXiv Detail & Related papers (2020-09-28T15:59:31Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.