arXiv subjects

Siyang Li

Publications and source records attributed to Siyang Li.

63 records · Page 4Linked to original sources

arXiv2019

Characterization of a silicon photomultiplier for the Ultra-Fast Astronomy telescope

We characterized the S13360-3050CS Multi-Pixel Photon Counter (MPPC), a silicon photomultiplier (SiPM) manufactured by Hamamatsu Photonics K.K.. Measurements were obtained inside a light tight dark box using 365 nm, 400 nm, 525 nm, 660 nm, 720 nm, 810 nm, and 900 nm light-emitting diodes (LED) and the Citiroc 1A front-end evaluation system manufactured by Weeroc. At a 2.95V over voltage, we measured a dark count rate of 5.07x$10^{5}$ counts per second at 26$^{\circ}$C, crosstalk probability of 8.7$\%$, photon detection efficiency of 36$\%$ at 400 nm, linear range of 1.8x$10^{7}$ photons per second, and saturation at 5x$10^8$ photons per second. The S13360-3050CS MPPC is a candidate detector for the Ultra-Fast Astronomy (UFA) telescope which will characterize the optical sky in the millisecond to nanosecond timescales using two SiPM arrays operated in coincidence mounted on the 0.7 meter Nazarbayev University Transient Telescope at the Assy-Turgen Astrophysical Observatory (NUTTelA-TAO) located near Almaty, Kazakhstan. One objective of the UFA telescope will be to search for optical counterparts to fast radio bursts (FRB) that can be used to identify the origins of FRB and probe the epoch of reionization and baryonic matter in the interstellar and intergalactic mediums.

astro-ph.IM↗

arXiv2019

Detector Characterization of a Near-Infrared Discrete Avalanche Photodiode 5x5 Array for Astrophysical Observations

We present detector characterization of a state-of-the-art near-infrared (950nm - 1650 nm) Discrete Avalanche Photodiode detector (NIRDAPD) 5x5 array. We designed an experimental setup to characterize the NIRDAPD dark count rate, photon detection efficiency (PDE), and non-linearity. The NIRDAPD array was illuminated using a 1050 nm light-emitting diode (LED) as well as 980 nm, 1310 nm, and 1550 nm laser diodes. We find a dark count rate of 3.3x10$^6$ cps, saturation at 1.2x10$^8$ photons per second, a photon detection efficiency of 14.8% at 1050 nm, and pulse detection at 1 GHz. We characterized this NIRDAPD array for a future astrophysical program that will search for technosignatures and other fast (>1 Ghz) astrophysical transients as part of the Pulsed All-sky Near-infrared Optical Search for Extraterrestrial Intelligence (PANOSETI) project. The PANOSETI program will consist of an all-sky optical (350 - 800 nm) observatory capable of observing the entire northern hemisphere instantaneously and a wide-field NIR (950 - 1650 nm) component capable of drift scanning the entire sky in 230 clear nights. PANOSETI aims to be the first wide-field fast-time response near-infrared transient search.

astro-ph.IM↗

arXiv2018

Unsupervised Video Object Segmentation with Distractor-Aware Online Adaptation

Unsupervised video object segmentation is a crucial application in video analysis without knowing any prior information about the objects. It becomes tremendously challenging when multiple objects occur and interact in a given video clip. In this paper, a novel unsupervised video object segmentation approach via distractor-aware online adaptation (DOA) is proposed. DOA models spatial-temporal consistency in video sequences by capturing background dependencies from adjacent frames. Instance proposals are generated by the instance segmentation network for each frame and then selected by motion information as hard negatives if they exist and positives. To adopt high-quality hard negatives, the block matching algorithm is then applied to preceding frames to track the associated hard negatives. General negatives are also introduced in case that there are no hard negatives in the sequence and experiments demonstrate both kinds of negatives (distractors) are complementary. Finally, we conduct DOA using the positive, negative, and hard negative masks to update the foreground/background segmentation. The proposed approach achieves state-of-the-art results on two benchmark datasets, DAVIS 2016 and FBMS-59 datasets.

cs.CV↗

arXiv2018

Design Pseudo Ground Truth with Motion Cue for Unsupervised Video Object Segmentation

One major technique debt in video object segmentation is to label the object masks for training instances. As a result, we propose to prepare inexpensive, yet high quality pseudo ground truth corrected with motion cue for video object segmentation training. Our method conducts semantic segmentation using instance segmentation networks and, then, selects the segmented object of interest as the pseudo ground truth based on the motion information. Afterwards, the pseudo ground truth is exploited to finetune the pretrained objectness network to facilitate object segmentation in the remaining frames of the video. We show that the pseudo ground truth could effectively improve the segmentation performance. This straightforward unsupervised video object segmentation method is more efficient than existing methods. Experimental results on DAVIS and FBMS show that the proposed method outperforms state-of-the-art unsupervised segmentation methods on various benchmark datasets. And the category-agnostic pseudo ground truth has great potential to extend to multiple arbitrary object tracking.

cs.CV↗

arXiv2018

Interpretable Convolutional Neural Networks via Feedforward Design

The model parameters of convolutional neural networks (CNNs) are determined by backpropagation (BP). In this work, we propose an interpretable feedforward (FF) design without any BP as a reference. The FF design adopts a data-centric approach. It derives network parameters of the current layer based on data statistics from the output of the previous layer in a one-pass manner. To construct convolutional layers, we develop a new signal transform, called the Saab (Subspace Approximation with Adjusted Bias) transform. It is a variant of the principal component analysis (PCA) with an added bias vector to annihilate activation's nonlinearity. Multiple Saab transforms in cascade yield multiple convolutional layers. As to fully-connected (FC) layers, we construct them using a cascade of multi-stage linear least squared regressors (LSRs). The classification and robustness (against adversarial attacks) performances of BP- and FF-designed CNNs applied to the MNIST and the CIFAR-10 datasets are compared. Finally, we comment on the relationship between BP and FF designs.

cs.CV↗

arXiv2018

Instance Embedding Transfer to Unsupervised Video Object Segmentation

We propose a method for unsupervised video object segmentation by transferring the knowledge encapsulated in image-based instance embedding networks. The instance embedding network produces an embedding vector for each pixel that enables identifying all pixels belonging to the same object. Though trained on static images, the instance embeddings are stable over consecutive video frames, which allows us to link objects together over time. Thus, we adapt the instance networks trained on static images to video object segmentation and incorporate the embeddings with objectness and optical flow features, without model retraining or online fine-tuning. The proposed method outperforms state-of-the-art unsupervised segmentation methods in the DAVIS dataset and the FBMS dataset.

cs.CV↗

arXiv2017

Multiple Instance Curriculum Learning for Weakly Supervised Object Detection

When supervising an object detector with weakly labeled data, most existing approaches are prone to trapping in the discriminative object parts, e.g., finding the face of a cat instead of the full body, due to lacking the supervision on the extent of full objects. To address this challenge, we incorporate object segmentation into the detector training, which guides the model to correctly localize the full objects. We propose the multiple instance curriculum learning (MICL) method, which injects curriculum learning (CL) into the multiple instance learning (MIL) framework. The MICL method starts by automatically picking the easy training examples, where the extent of the segmentation masks agree with detection bounding boxes. The training set is gradually expanded to include harder examples to train strong detectors that handle complex images. The proposed MICL method with segmentation in the loop outperforms the state-of-the-art weakly supervised object detectors by a substantial margin on the PASCAL VOC datasets.

cs.CV↗

arXiv2017

A Taught-Obesrve-Ask (TOA) Method for Object Detection with Critical Supervision

Being inspired by child's learning experience - taught first and followed by observation and questioning, we investigate a critically supervised learning methodology for object detection in this work. Specifically, we propose a taught-observe-ask (TOA) method that consists of several novel components such as negative object proposal, critical example mining, and machine-guided question-answer (QA) labeling. To consider labeling time and performance jointly, new evaluation methods are developed to compare the performance of the TOA method, with the fully and weakly supervised learning methods. Extensive experiments are conducted on the PASCAL VOC and the Caltech benchmark datasets. The TOA method provides significantly improved performance of weakly supervision yet demands only about 3-6% of labeling time of full supervision. The effectiveness of each novel component is also analyzed.

cs.CV↗

arXiv2017

Semantic Segmentation with Reverse Attention

Recent development in fully convolutional neural network enables efficient end-to-end learning of semantic segmentation. Traditionally, the convolutional classifiers are taught to learn the representative semantic features of labeled semantic objects. In this work, we propose a reverse attention network (RAN) architecture that trains the network to capture the opposite concept (i.e., what are not associated with a target class) as well. The RAN is a three-branch network that performs the direct, reverse and reverse-attention learning processes simultaneously. Extensive experiments are conducted to show the effectiveness of the RAN in semantic segmentation. Being built upon the DeepLabv2-LargeFOV, the RAN achieves the state-of-the-art mIoU score (48.1%) for the challenging PASCAL-Context dataset. Significant performance improvements are also observed for the PASCAL-VOC, Person-Part, NYUDv2 and ADE20K datasets.

cs.CV↗