scholarly journals SOGNet: Scene Overlap Graph Network for Panoptic Segmentation

2020 ◽  
Vol 34 (07) ◽  
pp. 12637-12644 ◽  
Author(s):  
Yibo Yang ◽  
Hongyang Li ◽  
Xia Li ◽  
Qijie Zhao ◽  
Jianlong Wu ◽  
...  
Keyword(s):  
State Of The Art ◽  
Ground Truth ◽  
The State ◽  
Graph Representation ◽  
Weak Supervision ◽  
Scene Graph ◽  
Art Performance ◽  
Segmentation Task ◽  
Instance Segmentation ◽  
Relation Matrix

The panoptic segmentation task requires a unified result from semantic and instance segmentation outputs that may contain overlaps. However, current studies widely ignore modeling overlaps. In this study, we aim to model overlap relations among instances and resolve them for panoptic segmentation. Inspired by scene graph representation, we formulate the overlapping problem as a simplified case, named scene overlap graph. We leverage each object's category, geometry and appearance features to perform relational embedding, and output a relation matrix that encodes overlap relations. In order to overcome the lack of supervision, we introduce a differentiable module to resolve the overlap between any pair of instances. The mask logits after removing overlaps are fed into per-pixel instance id classification, which leverages the panoptic supervision to assist in the modeling of overlap relations. Besides, we generate an approximate ground truth of overlap relations as the weak supervision, to quantify the accuracy of overlap relations predicted by our method. Experiments on COCO and Cityscapes demonstrate that our method is able to accurately predict overlap relations, and outperform the state-of-the-art performance for panoptic segmentation. Our method also won the Innovation Award in COCO 2019 challenge.

scholarly journals WS-RCNN: Learning to Score Proposals for Weakly Supervised Instance Segmentation

Sensors ◽  
2021 ◽  
Vol 21 (10) ◽  
pp. 3475
Author(s):  
Jia-Rong Ou ◽  
Shu-Le Deng ◽  
Jin-Gang Yu
Keyword(s):  
State Of The Art ◽  
Spatial Relationship ◽  
The State ◽  
Weak Supervision ◽  
Large Margin ◽  
Deep Network ◽  
Heuristic Strategies ◽  
Model Training ◽  
Weakly Supervised ◽  
Instance Segmentation

Weakly supervised instance segmentation (WSIS) provides a promising way to address instance segmentation in the absence of sufficient labeled data for training. Previous attempts on WSIS usually follow a proposal-based paradigm, critical to which is the proposal scoring strategy. These works mostly rely on certain heuristic strategies for proposal scoring, which largely hampers the sustainable advances concerning WSIS. Towards this end, this paper introduces a novel framework for weakly supervised instance segmentation, called Weakly Supervised R-CNN (WS-RCNN). The basic idea is to deploy a deep network to learn to score proposals, under the special setting of weak supervision. To tackle the key issue of acquiring proposal-level pseudo labels for model training, we propose a so-called Attention-Guided Pseudo Labeling (AGPL) strategy, which leverages the local maximal (peaks) in image-level attention maps and the spatial relationship among peaks and proposals to infer pseudo labels. We also suggest a novel training loss, called Entropic OpenSet Loss, to handle background proposals more effectively so as to further improve the robustness. Comprehensive experiments on two standard benchmarking datasets demonstrate that the proposed WS-RCNN can outperform the state-of-the-art by a large margin, with an improvement of 11.6% on PASCAL VOC 2012 and 10.7% on MS COCO 2014 in terms of mAP50, which indicates that learning-based proposal scoring and the proposed WS-RCNN framework might be a promising way towards WSIS.

scholarly journals Automated patch assessment for program repair at scale

2021 ◽  
Vol 26 (2) ◽  
Author(s):  
He Ye ◽  
Matias Martinez ◽  
Martin Monperrus
Keyword(s):  
External Validity ◽  
State Of The Art ◽  
Ground Truth ◽  
The State ◽  
Random Testing ◽  
Program Repair ◽  
Art Performance ◽  
Repair Systems

AbstractIn this paper, we do automatic correctness assessment for patches generated by program repair systems. We consider the human-written patch as ground truth oracle and randomly generate tests based on it, a technique proposed by Shamshiri et al., called Random testing with Ground Truth (RGT) in this paper. We build a curated dataset of 638 patches for Defects4J generated by 14 state-of-the-art repair systems, we evaluate automated patch assessment on this dataset. The results of this study are novel and significant: First, we improve the state of the art performance of automatic patch assessment with RGT by 190% by improving the oracle; Second, we show that RGT is reliable enough to help scientists to do overfitting analysis when they evaluate program repair systems; Third, we improve the external validity of the program repair knowledge with the largest study ever.

scholarly journals Large-scale Semantic Parsing without Question-Answer Pairs

2014 ◽  
Vol 2 ◽  
pp. 377-392 ◽  
Author(s):  
Siva Reddy ◽  
Mirella Lapata ◽  
Mark Steedman
Keyword(s):  
Natural Language ◽  
Large Scale ◽  
Graph Matching ◽  
State Of The Art ◽  
The State ◽  
Semantic Parsing ◽  
Matching Problem ◽  
Weak Supervision ◽  
Benchmark Datasets

In this paper we introduce a novel semantic parsing approach to query Freebase in natural language without requiring manual annotations or question-answer pairs. Our key insight is to represent natural language via semantic graphs whose topology shares many commonalities with Freebase. Given this representation, we conceptualize semantic parsing as a graph matching problem. Our model converts sentences to semantic graphs using CCG and subsequently grounds them to Freebase guided by denotations as a form of weak supervision. Evaluation experiments on a subset of the Free917 and WebQuestions benchmark datasets show our semantic parser improves over the state of the art.

scholarly journals A Graph-based Evolutionary Algorithm for Automated Machine Learning

2020 ◽  
Author(s):  
Fei Qi ◽  
Zhaohui Xia ◽  
Gaoyang Tang ◽  
Hang Yang ◽  
Yu Song ◽  
...  
Keyword(s):  
Machine Learning ◽  
Evolutionary Algorithm ◽  
Parameter Optimization ◽  
State Of The Art ◽  
The State ◽  
Complex Structures ◽  
Architecture Evolution ◽  
Automated Machine Learning ◽  
Art Performance

As an emerging field, Automated Machine Learning (AutoML) aims to reduce or eliminate manual operations that require expertise in machine learning. In this paper, a graph-based architecture is employed to represent flexible combinations of ML models, which provides a large searching space compared to tree-based and stacking-based architectures. Based on this, an evolutionary algorithm is proposed to search for the best architecture, where the mutation and heredity operators are the key for architecture evolution. With Bayesian hyper-parameter optimization, the proposed approach can automate the workflow of machine learning. On the PMLB dataset, the proposed approach shows the state-of-the-art performance compared with TPOT, Autostacker, and auto-sklearn. Some of the optimized models are with complex structures which are difficult to obtain in manual design.

Visual Saliency and Perceptual Quality Assessment of 3D Meshes

2018 ◽  
pp. 38-115
Author(s):  
Anass Nouri ◽  
Christophe Charrier ◽  
Olivier Lezoray
Keyword(s):  
Quality Assessment ◽  
State Of The Art ◽  
Saliency Detection ◽  
Visual Saliency ◽  
Ground Truth ◽  
The State ◽  
Perceptual Quality ◽  
Adaptive Smoothing ◽  
Definition Of ◽  
Mesh Database

This chapter concerns the visual saliency and the perceptual quality assessment of 3D meshes. Firstly, the chapter proposes a definition of visual saliency and describes the state-of-the-art methods for its detection on 3D mesh surfaces. A focus is made on a recent model of visual saliency detection for 3D colored and non-colored meshes whose results are compared with a ground-truth saliency as well as with the literature's methods. Since this model is able to estimate the visual saliency on 3D colored meshes, named colorimetric saliency, a description of the construction of a 3D colored mesh database that was used to assess its relevance is presented. The authors also describe three applications of the detailed model that respond to the problems of viewpoint selection, adaptive simplification and adaptive smoothing. Secondly, two perceptual quality assessment metrics for 3D non-colored meshes are described, analyzed, and compared with the state-of-the-art approaches.

Highly efficient thermophones based on freestanding single-walled carbon nanotube films

2019 ◽  
Vol 4 (5) ◽  
pp. 1158-1163 ◽  
Author(s):  
Stepan A. Romanov ◽  
Ali E. Aliev ◽  
Boris V. Fine ◽  
Anton S. Anisimov ◽  
Albert G. Nasibulin
Keyword(s):  
Carbon Nanotubes ◽  
Carbon Nanotube ◽  
State Of The Art ◽  
Single Walled Carbon Nanotubes ◽  
The State ◽  
Single Walled Carbon Nanotube ◽  
Single Walled Carbon ◽  
Highly Efficient ◽  
Art Performance ◽  
Walled Carbon Nanotubes

We present the state-of-the-art performance of air-coupled thermophones made of thin, freestanding films of randomly oriented single-walled carbon nanotubes (SWCNTs).

scholarly journals Appearance and Motion Enhancement for Video-Based Person Re-Identification

2020 ◽  
Vol 34 (07) ◽  
pp. 11394-11401
Author(s):  
Shuzhao Li ◽  
Huimin Yu ◽  
Haoji Hu
Keyword(s):  
Semantic Information ◽  
State Of The Art ◽  
Complex Model ◽  
The State ◽  
Final Model ◽  
Backbone Network ◽  
Proposed Model ◽  
Art Performance ◽  
Attribute Recognition

In this paper, we propose an Appearance and Motion Enhancement Model (AMEM) for video-based person re-identification to enrich the two kinds of information contained in the backbone network in a more interpretable way. Concretely, human attribute recognition under the supervision of pseudo labels is exploited in an Appearance Enhancement Module (AEM) to help enrich the appearance and semantic information. A Motion Enhancement Module (MEM) is designed to capture the identity-discriminative walking patterns through predicting future frames. Despite a complex model with several auxiliary modules during training, only the backbone model plus two small branches are kept for similarity evaluation which constitute a simple but effective final model. Extensive experiments conducted on three popular video-based person ReID benchmarks demonstrate the effectiveness of our proposed model and the state-of-the-art performance compared with existing methods.

scholarly journals Uncertainty-Aware Few-Shot Image Classification

2021 ◽  
Author(s):  
Zhizheng Zhang ◽  
Cuiling Lan ◽  
Wenjun Zeng ◽  
Zhibo Chen ◽  
Shih-Fu Chang
Keyword(s):  
Neural Network ◽  
Image Classification ◽  
State Of The Art ◽  
Metric Learning ◽  
The State ◽  
Modeling Uncertainty ◽  
Support Set ◽  
Art Performance ◽  
Graph Based Model ◽  
Query Sample

Few-shot image classification learns to recognize new categories from limited labelled data. Metric learning based approaches have been widely investigated, where a query sample is classified by finding the nearest prototype from the support set based on their feature similarities. A neural network has different uncertainties on its calculated similarities of different pairs. Understanding and modeling the uncertainty on the similarity could promote the exploitation of limited samples in few-shot optimization. In this work, we propose Uncertainty-Aware Few-Shot framework for image classification by modeling uncertainty of the similarities of query-support pairs and performing uncertainty-aware optimization. Particularly, we exploit such uncertainty by converting observed similarities to probabilistic representations and incorporate them to the loss for more effective optimization. In order to jointly consider the similarities between a query and the prototypes in a support set, a graph-based model is utilized to estimate the uncertainty of the pairs. Extensive experiments show our proposed method brings significant improvements on top of a strong baseline and achieves the state-of-the-art performance.

scholarly journals An Adversarial and Densely Dilated Network for Connectomes Segmentation

Symmetry ◽  
2018 ◽  
Vol 10 (10) ◽  
pp. 467 ◽  
Author(s):  
Ke Chen ◽  
Dandan Zhu ◽  
Jianwei Lu ◽  
Ye Luo
Keyword(s):  
State Of The Art ◽  
Piriform Cortex ◽  
Receptive Fields ◽  
Ground Truth ◽  
Training Data ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Boundary Map ◽  
Segmentation Task ◽  
The Brain

Automatic reconstructing of neural circuits in the brain is one of the most crucial studies in neuroscience. Connectomes segmentation plays an important role in reconstruction from electron microscopy (EM) images; however, it is rather challenging due to highly anisotropic shapes with inferior quality and various thickness. In our paper, we propose a novel connectomes segmentation framework called adversarial and densely dilated network (ADDN) to address these issues. ADDN is based on the conditional Generative Adversarial Network (cGAN) structure which is the latest advance in machine learning with power to generate images similar to the ground truth especially when the training data is limited. Specifically, we design densely dilated network (DDN) as the segmentor to allow a deeper architecture and larger receptive fields for more accurate segmentation. Discriminator is trained to distinguish generated segmentation from manual segmentation. During training, such adversarial loss function is optimized together with dice loss. Extensive experimental results demonstrate that our ADDN is effective for such connectomes segmentation task, helping to retrieve more accurate segmentation and attenuate the blurry effects of generated boundary map. Our method obtains state-of-the-art performance while requiring less computation on ISBI 2012 EM dataset and mouse piriform cortex dataset.

scholarly journals Improving One-Class Collaborative Filtering via Ranking-Based Implicit Regularizer

2019 ◽  
Vol 33 ◽  
pp. 37-44 ◽  
Author(s):  
Jin Chen ◽  
Defu Lian ◽  
Kai Zheng
Keyword(s):  
Collaborative Filtering ◽  
State Of The Art ◽  
Ground Truth ◽  
The State ◽  
Low Rank ◽  
Model Parameters ◽  
Music Recommendation ◽  
Low Rank Approximation ◽  
The Arts ◽  
Rank Approximation

One-class collaborative filtering (OCCF) problems are vital in many applications of recommender systems, such as news and music recommendation, but suffers from sparsity issues and lacks negative examples. To address this problem, the state-of-the-arts assigned smaller weights to unobserved samples and performed low-rank approximation. However, the ground-truth ratings of unobserved samples are usually set to zero but ill-defined. In this paper, we propose a ranking-based implicit regularizer and provide a new general framework for OCCF, to avert the ground-truth ratings of unobserved samples. We then exploit it to regularize a ranking-based loss function and design efficient optimization algorithms to learn model parameters. Finally, we evaluate them on three realworld datasets. The results show that the proposed regularizer significantly improves ranking-based algorithms and that the proposed framework outperforms the state-of-the-art OCCF algorithms.

Sign in / Sign up

Export Citation Format

Share Document