다중혈관 관상동맥 환자에서 y-문합을 이용하여 양쪽 내흉동맥만을 사용한 우회술의 조기 성적

In this work, we revisit atrous convolution, a powerful tool to explicitly adjust filter's field-of-view as well as control the resolution of feature responses computed by Deep Convolutional Neural Networks, in the application of semantic image segmentation. To handle the problem of segmenting objects at multiple scales, we design modules which employ atrous convolution in cascade or in parallel to capture multi-scale context by adopting multiple atrous rates. Furthermore, we propose to augment our previously proposed Atrous Spatial Pyramid Pooling module, which probes convolutional features at multiple scales, with image-level features encoding global context and further boost performance. We also elaborate on implementation details and share our experience on training our system. The proposed `DeepLabv3' system significantly improves over our previous DeepLab versions without DenseCRF post-processing and attains comparable performance with other state-of-art models on the PASCAL VOC 2012 semantic image segmentation benchmark.

Rethinking Atrous Convolution for Semantic Image Segmentation

“Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告

The PASCAL Visual Object Classes Challenge

Semantic segmentation requires both rich spatial information and sizeable receptive field. However, modern approaches usually compromise spatial resolution to achieve real-time inference speed, which leads to poor performance. In this paper, we address this dilemma with a novel Bilateral Segmentation Network (BiSeNet). We first design a Spatial Path with a small stride to preserve the spatial information and generate high-resolution features. Meanwhile, a Context Path with a fast downsampling strategy is employed to obtain sufficient receptive field. On top of the two paths, we introduce a new Feature Fusion Module to combine features efficiently. The proposed architecture makes a right balance between the speed and segmentation performance on Cityscapes, CamVid, and COCO-Stuff datasets. Specifically, for a 2048 \(\times \) 1024 input, we achieve 68.4% Mean IOU on the Cityscapes test dataset with speed of 105 FPS on one NVIDIA Titan XP card, which is significantly faster than the existing methods with comparable performance.

/pdf/bisenet-bilateral-segmentation-network-for-real-time-2pc7rh0tw1.pdf

BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation

The Back-n white neutron source at the China Spallation Neutron Source (CSNS) provides neutrons in the continuous energy region from 0.5 eV to 200 MeV. A spectrometer named Light charged Particle Detector Array (LPDA) is designed for the study of (n, lcp) reactions at Back-n. The main detector of the LPDA spectrometer, a 16-unit ΔE-ΔE-E telescope array, is composed of two arrays of 8-unit ΔE-ΔE-E telescope. Each telescope unit consists of a Low-Pressure Multi-Wire Proportional Chamber (LPMWPC), a Si-PIN detector, and a CsI(Tl) scintillator detector. In 2021, a neutron-proton (n-p) scattering reaction cross-section measurement experiment was accomplished as the first experiment of the telescope array. Protons can be clearly identified in the ΔE-E spectrum (LPMWPC + Si-PIN) and the ΔE-E spectrum (Si-PIN + CsI(Tl)). Cross sections of the n-p scattering reaction in the neutron energy range of several MeV are extracted. The ΔE-E method also provides new measurement opportunities for many-body neutron induced light charged-particle emission reactions.

The light charged particle detector array at the CSNS Back-n white neutron source

Generalized Zero-Shot Learning (GZSL) holds significant research importance as it enables the classification of samples from both seen and unseen classes. A prevailing approach for GZSL is learning transferable representations that can generalize well to both seen and unseen classes during testing. This approach encompasses two key concepts: discriminative representations and semantic-relevant representations. “Semantic-relevant” facilitates the transfer of semantic knowledge using pre-defined semantic descriptors, while “discriminative” is crucial for accurate category discrimination. However, these two concepts are arguably inherently conflicting, as semantic descriptors are not specifically designed for image classification. Existing methods often struggle with balancing these two aspects and neglect the conflict between them, leading to suboptimal representation generalization and transferability to unseen classes. To address this issue, we propose a novel partially-shared multi-task representation learning method, termed PS-GZSL, which jointly preserves complementary and sharable knowledge between these two concepts. Specifically, we first propose a novel perspective that treats the learning of discriminative and semantic-relevant representations as optimizing a discrimination task and a visual-semantic alignment task, respectively. Then, to learn more complete and generalizable representations, PS-GZSL explicitly factorizes visual features into task-shared and task-specific representations and introduces two advanced tasks: an instance-level contrastive discrimination task and a relation-based visual-semantic alignment task. Furthermore, PS-GZSL employs Mixture-of-Experts (MoE) with a dropout mechanism to prevent representation degeneration and integrates a conditional GAN (cGAN) to synthesize unseen features for estimating unseen visual features. Extensive experiments and more competitive results on five widely-used GZSL benchmark datasets validate the effectiveness of our PS-GZSL.

https://www.mdpi.com/2079-9292/12/9/2085/pdf?version=1683789752

Generalized Zero-Shot Image Classification via Partially-Shared Multi-Task Representation Learning

Current state-of-the-art newsvideo retrieval systems mainly focus onautomated speech recognition (ASR)text toperform retrieval. Thisparadigm greatly affects retrieval performance asASRtext alone isnotsufficient toprovide anaccurate representation ofthe entire newsvideo. Inthispaper, we describe ourautomated retrieval framework whichfuses themultimodal features andevent structures present innewsvideo tosupport precise newsvideo retrieval. Thecontributions ofthis paper are: (a)weuncover and employ temporal event clusters toprovide additional information during story level retrieval; and(b)weintegrate other modality features withtextfeatures andincorporate eventclusters for pseudorelevance feedback (PRF)inshotlevel re-ranking. Experiments performed onvideo search task using theTRECVID 2005/06 dataset showthat theproposed approach iseffective.

Sheng Tang

Papers

The light charged particle detector array at the CSNS Back-n white neutron source

Generalized Zero-Shot Image Classification via Partially-Shared Multi-Task Representation Learning

News videoretrievalusingimplicitevent semantics