A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf
.
Filters
Generative Semantic Manipulation with Contrasting GAN
[article]
2017
arXiv
pre-print
Generative Adversarial Networks (GANs) have recently achieved significant improvement on paired/unpaired image-to-image translation, such as photo→ sketch and artist painting style transfer. However, existing models can only be capable of transferring the low-level information (e.g. color or texture changes), but fail to edit high-level semantic meanings (e.g., geometric structure or content) of objects. On the other hand, while some researches can synthesize compelling real-world images given
arXiv:1708.00315v1
fatcat:2ih6k4dukra4xkgflrvvhthc4a
more »
... class label or caption, they cannot condition on arbitrary shapes or structures, which largely limits their application scenarios and interpretive capability of model results. In this work, we focus on a more challenging semantic manipulation task, which aims to modify the semantic meaning of an object while preserving its own characteristics (e.g. viewpoints and shapes), such as cow→sheep, motor→ bicycle, cat→dog. To tackle such large semantic changes, we introduce a contrasting GAN (contrast-GAN) with a novel adversarial contrasting objective. Instead of directly making the synthesized samples close to target data as previous GANs did, our adversarial contrasting objective optimizes over the distance comparisons between samples, that is, enforcing the manipulated data be semantically closer to the real data with target category than the input data. Equipped with the new contrasting objective, a novel mask-conditional contrast-GAN architecture is proposed to enable disentangle image background with object semantic changes. Experiments on several semantic manipulation tasks on ImageNet and MSCOCO dataset show considerable performance gain by our contrast-GAN over other conditional GANs. Quantitative results further demonstrate the superiority of our model on generating manipulated results with high visual fidelity and reasonable object semantics.
MetaLogic: Logical Reasoning Explanations with Fine-Grained Structure
[article]
2022
arXiv
pre-print
In this paper, we propose a comprehensive benchmark to investigate models' logical reasoning capabilities in complex real-life scenarios. Current explanation datasets often employ synthetic data with simple reasoning structures. Therefore, it cannot express more complex reasoning processes, such as the rebuttal to a reasoning step and the degree of certainty of the evidence. To this end, we propose a comprehensive logical reasoning explanation form. Based on the multi-hop chain of reasoning,
arXiv:2210.12487v1
fatcat:rnv2anleqjg3ha4nvk3kfpepmq
more »
... explanation form includes three main components: (1) The condition of rebuttal that the reasoning node can be challenged; (2) Logical formulae that uncover the internal texture of reasoning nodes; (3) Reasoning strength indicated by degrees of certainty. The fine-grained structure conforms to the real logical reasoning scenario, better fitting the human cognitive process but, simultaneously, is more challenging for the current models. We evaluate the current best models' performance on this new explanation form. The experimental results show that generating reasoning graphs remains a challenging task for current models, even with the help of giant pre-trained language models.
ERCP during the COVID-19 epidemic
2020
Endoscopy
Ada-Segment: Automated Multi-loss Adaptation for Panoptic Segmentation
[article]
2020
arXiv
pre-print
Panoptic segmentation that unifies instance segmentation and semantic segmentation has recently attracted increasing attention. While most existing methods focus on designing novel architectures, we steer toward a different perspective: performing automated multi-loss adaptation (named Ada-Segment) on the fly to flexibly adjust multiple training losses over the course of training using a controller trained to capture the learning dynamics. This offers a few advantages: it bypasses manual tuning
arXiv:2012.03603v1
fatcat:6unlyvl76bdhjag2ccpfmfcfge
more »
... of the sensitive loss combination, a decisive factor for panoptic segmentation; it allows to explicitly model the learning dynamics, and reconcile the learning of multiple objectives (up to ten in our experiments); with an end-to-end architecture, it generalizes to different datasets without the need of re-tuning hyperparameters or re-adjusting the training process laboriously. Our Ada-Segment brings 2.7% panoptic quality (PQ) improvement on COCO val split from the vanilla baseline, achieving the state-of-the-art 48.5% PQ on COCO test-dev split and 32.9% PQ on ADE20K dataset. The extensive ablation studies reveal the ever-changing dynamics throughout the training process, necessitating the incorporation of an automated and adaptive learning strategy as presented in this paper.
Theme-Aware Semi-Supervised Image Aesthetic Quality Assessment
2022
Mathematics
For example, Zhang et al. [17] proposed a simple learning principle, MixUp, to reduce memory and sensitivity to antagonistic examples of large deep neural networks. Berthelot et al. ...
doi:10.3390/math10152609
fatcat:f2dy4xxaovgdrhouad2zxfmznq
Behavioral oscillations in attentional processing
2021
Advances in Psychological Science
Intraocular Pressure Changes during Accommodation in Progressing Myopes, Stable Myopes and Emmetropes
2015
PLoS ONE
Purpose To investigate the changes of intraocular pressure (IOP) induced by 3-diopter (3 D) accommodation in progressing myopes, stable myopes and emmetropes. Design Cross-sectional study. Participants 318 subjects including 270 myopes and 48 emmetropes. Methods 195 progressing myopes, 75 stable myopes and 48 emmetropes participated in this study. All subjects had their IOP measured using iCare rebound tonometer while accommodative stimuli of 0 D and 3 D were presented. Main Outcome Measures
doi:10.1371/journal.pone.0141839
pmid:26517725
pmcid:PMC4627769
fatcat:fro4wtjuuzgtleuai5qovvljfu
more »
... values without accommodation and with 3 D accommodation were measured in all subjects. Baseline IOPs and IOP changes were compared within and between groups. Results There was no significant difference in IOPs between progressing myopes, stable myopes and emmetropes when no accommodation was induced (17.47±3.46, 16.62±2.98 and 16.80±3.62 respectively, p>0.05). IOP experienced an insignificantly slight decrease after 3 D accommodation in three groups (mean change -0.19±2.16, -0.03±1.68 and -0.39±2.65 respectively, p>0.05). Subgroup analysis showed in progressing myopic group, IOP of children (<18 years old) declined with accommodation while IOP of adults (18 years) increased, and the difference was statistically significant (p = 0.008). However, after PLOS ONE |
Target-Mounted Intelligent Reflecting Surface for Secure Wireless Sensing
[article]
2023
arXiv
pre-print
In this paper, we consider a challenging secure wireless sensing scenario where a legitimate radar station (LRS) intends to detect a target at unknown location in the presence of an unauthorized radar station (URS). We aim to enhance the sensing performance of the LRS and in the meanwhile prevent the detection of the same target by the URS. Under this setup, conventional stealth-based approaches such as wrapping the target with electromagnetic wave absorbing materials are not applicable, since
arXiv:2308.02676v1
fatcat:oyemkxr3yvgnjhedkvhz3v6fae
more »
... hey will disable the target detection by not only the URS, but the LRS as well. To tackle this challenge, we propose in this paper a new target-mounted IRS approach, where intelligent reflecting surface (IRS) is mounted on the outer/echo surface of the target and by tuning the IRS reflection, the strength of its reflected radar signal in any angle of departure (AoD) can be adjusted based on the signal's angle of arrival (AoA), thereby enhancing/suppressing the signal power towards the LRS/URS, respectively. To this end, we propose a practical protocol for the target-mounted IRS to estimate the LRS/URS channel and waveform parameters based on its sensed signals and control the IRS reflection for/against the LRS/URS accordingly. Specifically, we formulate new optimization problems to design the reflecting phase shifts at IRS for maximizing the received signal power at the LRS while keeping that at the URS below a certain level, for both the cases of short-term and long-term IRS operations with different dynamic reflection capabilities. To solve these non-convex problems, we apply the penalty dual decomposition method to obtain high-quality suboptimal solutions for them efficiently. Finally, simulation results are presented that verify the effectiveness of the proposed protocol and algorithms for the target-mounted IRS to achieve secure wireless sensing, as compared with various benchmark schemes.
Fashion Editing with Adversarial Parsing Learning
[article]
2019
arXiv
pre-print
Interactive fashion image manipulation, which enables users to edit images with sketches and color strokes, is an interesting research problem with great application value. Existing works often treat it as a general inpainting task and do not fully leverage the semantic structural information in fashion images. Moreover, they directly utilize conventional convolution and normalization layers to restore the incomplete image, which tends to wash away the sketch and color information. In this
arXiv:1906.00884v2
fatcat:3i2kxaal7rh65dh7kw6absgila
more »
... , we propose a novel Fashion Editing Generative Adversarial Network (FE-GAN), which is capable of manipulating fashion images by free-form sketches and sparse color strokes. FE-GAN consists of two modules: 1) a free-form parsing network that learns to control the human parsing generation by manipulating sketch and color; 2) a parsing-aware inpainting network that renders detailed textures with semantic guidance from the human parsing map. A new attention normalization layer is further applied at multiple scales in the decoder of the inpainting network to enhance the quality of the synthesized image. Extensive experiments on high-resolution fashion image datasets demonstrate that the proposed method significantly outperforms the state-of-the-art methods on image manipulation.
Structured Generative Adversarial Networks
[article]
2017
arXiv
pre-print
Hao Zhang is supported by the AFRL/DARPA project FA872105C0003. Xiaodan Liang is supported by award FA870215D0002. ...
arXiv:1711.00889v1
fatcat:tspqsn3zfjfwnacjgg5bru2bp4
Correlation Analysis of Ocular Symptoms and Signs in Patients with Dry Eye
2017
Journal of Ophthalmology
Authors' Contributions Hang Song and Mingzhou Zhang contributed equally to this work. ...
doi:10.1155/2017/1247138
pmid:28321333
pmcid:PMC5339423
fatcat:juod4wfe6ve7rnd3pva57y7e3e
Language-Driven Visual Consensus for Zero-Shot Semantic Segmentation
[article]
2024
arXiv
pre-print
The pre-trained vision-language model, exemplified by CLIP, advances zero-shot semantic segmentation by aligning visual features with class embeddings through a transformer decoder to generate semantic masks. Despite its effectiveness, prevailing methods within this paradigm encounter challenges, including overfitting on seen classes and small fragmentation in masks. To mitigate these issues, we propose a Language-Driven Visual Consensus (LDVC) approach, fostering improved alignment of semantic
arXiv:2403.08426v1
fatcat:ueqdlcjg45a3bcpggq4c7tdl3i
more »
... and visual information.Specifically, we leverage class embeddings as anchors due to their discrete and abstract nature, steering vision features toward class embeddings. Moreover, to circumvent noisy alignments from the vision part due to its redundant nature, we introduce route attention into self-attention for finding visual consensus, thereby enhancing semantic consistency within the same object. Equipped with a vision-language prompting strategy, our approach significantly boosts the generalization capacity of segmentation models for unseen classes. Experimental results underscore the effectiveness of our approach, showcasing mIoU gains of 4.5 on the PASCAL VOC 2012 and 3.6 on the COCO-Stuff 164k for unseen classes compared with the state-of-the-art methods.
Flow Distances on Open Flow Networks
[article]
2015
arXiv
pre-print
Lou, 1 Peiteng Shi, 2 Jun Wang, 2 Xiaohan Huang, 2 and Jiang Zhang 1, * 1 School of Systems Sciences, Beijing Normal University, Beijing, China 2 Science and Technology on Information Systems Engineering ...
products
5 Agriculture, hunting, forestry and fishing
. . .
32 Electricity, gas and water supply
33 Hotels and restaurants
34 Construction
35 Education
36 Health and social work
Liangzhu Guo, 1 Xiaodan ...
arXiv:1501.06058v1
fatcat:cu5ylvr4dbcard3rxpkcrvtsea
SemEval-2020 Task 5: Counterfactual Recognition
[article]
2020
arXiv
pre-print
We thank Jiaqi Li and Qianyu Zhang for their help in this project. ...
arXiv:2008.00563v1
fatcat:kzjovysh2zb2bcuws37ev7zxbe
Smart Hydrogel Bilayers Prepared by Irradiation
2021
Polymers
Zhang and co-workers constructed a monolithic robust actuator of a binary cooperative Janus, which was synthesized by interfacial polymerization of immiscible hydrophilic and hydrophobic vinyl monomer ...
doi:10.3390/polym13111753
pmid:34072009
fatcat:kbf2xoxm3rftza3crz37b7oc74
« Previous
Showing results 1 — 15 out of 2,216 results