Tsinghua University

About: Tsinghua University is a education organization based out in Beijing, Beijing, China. It is known for research contribution in the topics: Catalysis & Graphene. The organization has 129978 authors who have published 200506 publications receiving 4549561 citations. The organization is also known as: Tsinghua & THU.

Scalable Person Re-identification: A Benchmark

Abstract: This paper contributes a new high quality dataset for person re-identification, named "Market-1501". Generally, current datasets: 1) are limited in scale, 2) consist of hand-drawn bboxes, which are unavailable under realistic settings, 3) have only one ground truth and one query image for each identity (close environment). To tackle these problems, the proposed Market-1501 dataset is featured in three aspects. First, it contains over 32,000 annotated bboxes, plus a distractor set of over 500K images, making it the largest person re-id dataset to date. Second, images in Market-1501 dataset are produced using the Deformable Part Model (DPM) as pedestrian detector. Third, our dataset is collected in an open system, where each identity has multiple images under each camera. As a minor contribution, inspired by recent advances in large-scale image search, this paper proposes an unsupervised Bag-of-Words descriptor. We view person re-identification as a special task of image search. In experiment, we show that the proposed descriptor yields competitive accuracy on VIPeR, CUHK03, and Market-1501 datasets, and is scalable on the large-scale 500k dataset.

Cleavage of GSDMD by inflammatory caspases determines pyroptotic cell death

Abstract: Inflammatory caspases (caspase-1, -4, -5 and -11) are critical for innate defences. Caspase-1 is activated by ligands of various canonical inflammasomes, and caspase-4, -5 and -11 directly recognize bacterial lipopolysaccharide, both of which trigger pyroptosis. Despite the crucial role in immunity and endotoxic shock, the mechanism for pyroptosis induction by inflammatory caspases is unknown. Here we identify gasdermin D (Gsdmd) by genome-wide clustered regularly interspaced palindromic repeat (CRISPR)-Cas9 nuclease screens of caspase-11- and caspase-1-mediated pyroptosis in mouse bone marrow macrophages. GSDMD-deficient cells resisted the induction of pyroptosis by cytosolic lipopolysaccharide and known canonical inflammasome ligands. Interleukin-1β release was also diminished in Gsdmd(-/-) cells, despite intact processing by caspase-1. Caspase-1 and caspase-4/5/11 specifically cleaved the linker between the amino-terminal gasdermin-N and carboxy-terminal gasdermin-C domains in GSDMD, which was required and sufficient for pyroptosis. The cleavage released the intramolecular inhibition on the gasdermin-N domain that showed intrinsic pyroptosis-inducing activity. Other gasdermin family members were not cleaved by inflammatory caspases but shared the autoinhibition; gain-of-function mutations in Gsdma3 that cause alopecia and skin defects disrupted the autoinhibition, allowing its gasdermin-N domain to trigger pyroptosis. These findings offer insight into inflammasome-mediated immunity/diseases and also change our understanding of pyroptosis and programmed necrosis.

GW151226: observation of gravitational waves from a 22-solar-mass binary black hole coalescence

Abstract: We report the observation of a gravitational-wave signal produced by the coalescence of two stellar-mass black holes. The signal, GW151226, was observed by the twin detectors of the Laser Interferometer Gravitational-Wave Observatory (LIGO) on December 26, 2015 at 03:38:53 UTC. The signal was initially identified within 70 s by an online matched-filter search targeting binary coalescences. Subsequent off-line analyses recovered GW151226 with a network signal-to-noise ratio of 13 and a significance greater than 5 σ. The signal persisted in the LIGO frequency band for approximately 1 s, increasing in frequency and amplitude over about 55 cycles from 35 to 450 Hz, and reached a peak gravitational strain of 3.4+0.7−0.9×10−22. The inferred source-frame initial black hole masses are 14.2+8.3−3.7M⊙ and 7.5+2.3−2.3M⊙ and the final black hole mass is 20.8+6.1−1.7M⊙. We find that at least one of the component black holes has spin greater than 0.2. This source is located at a luminosity distance of 440+180−190 Mpc corresponding to a redshift 0.09+0.03−0.04. All uncertainties define a 90 % credible interval. This second gravitational-wave observation provides improved constraints on stellar populations and on deviations from general relativity.

ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design

Abstract: Currently, the neural network architecture design is mostly guided by the indirect metric of computation complexity, i.e., FLOPs. However, the direct metric, e.g., speed, also depends on the other factors such as memory access cost and platform characterics. Thus, this work proposes to evaluate the direct metric on the target platform, beyond only considering FLOPs. Based on a series of controlled experiments, this work derives several practical guidelines for efficient network design. Accordingly, a new architecture is presented, called ShuffleNet V2. Comprehensive ablation experiments verify that our model is the state-of-the-art in terms of speed and accuracy tradeoff.

Learning Transferable Features with Deep Adaptation Networks

Abstract: Recent studies reveal that a deep neural network can learn transferable features which generalize well to novel tasks for domain adaptation. However, as deep features eventually transition from general to specific along the network, the feature transferability drops significantly in higher layers with increasing domain discrepancy. Hence, it is important to formally reduce the dataset bias and enhance the transferability in task-specific layers. In this paper, we propose a new Deep Adaptation Network (DAN) architecture, which generalizes deep convolutional neural network to the domain adaptation scenario. In DAN, hidden representations of all task-specific layers are embedded in a reproducing kernel Hilbert space where the mean embeddings of different domain distributions can be explicitly matched. The domain discrepancy is further reduced using an optimal multi-kernel selection method for mean embedding matching. DAN can learn transferable features with statistical guarantees, and can scale linearly by unbiased estimate of kernel embedding. Extensive empirical evidence shows that the proposed architecture yields state-of-the-art image classification error rates on standard domain adaptation benchmarks.