PsyNet: Self-Supervised Approach to Object Localization Using Point Symmetric Transformation

Existing co-localization techniques significantly lose performance over weakly or fully supervised methods in accuracy and inference time. In this paper, we overcome common drawbacks of co-localization techniques by utilizing self-supervised learning approach. The major technical contributions of the proposed method are two-fold. 1) We devise a new geometric transformation, namely point symmetric transformation and utilize its parameters as an artificial label for self-supervised learning. This new transformation can also play the role of region-drop based regularization. 2) We suggest a heat map extraction method for computing the heat map from the network trained by self-supervision, namely class-agnostic activation mapping. It is done by computing the spatial attention map. Based on extensive evaluations, we observe that the proposed method records new state-of-the-art performance in three fine-grained datasets for unsupervised object localization. Moreover, we show that the idea of the proposed method can be adopted in a modified manner to solve the weakly supervised object localization task. As a result, we outperform the current state-of-the-art technique in weakly supervised object localization by a significant gap.

Download Full-text

Word and pseudoword superiority effects: Evidence from a shallow orthography language

Quarterly Journal of Experimental Psychology ◽

10.1080/17470218.2017.1363791 ◽

2018 ◽

Vol 71 (9) ◽

pp. 1911-1920 ◽

Cited By ~ 1

Author(s):

Enrico Ripamonti ◽

Claudio Luzzatti ◽

Pierluigi Zoccolotti ◽

Daniela Traficante

Keyword(s):

Native Speakers ◽

State Of The Art ◽

Reaction Times ◽

Letter Position ◽

English Speakers ◽

Superiority Effect ◽

Fine Grained ◽

Current State ◽

Shallow Orthography

The word superiority effect (WSE) denotes better recognition of a letter embedded in a word rather than in a pseudoword. Along with WSE, also a pseudoword superiority effect (PSE) has been described: It is easier to recognise a letter in a legal pseudoword than in an unpronounceable nonword. At the current state of the art, both WSE and PSE have been mainly tested with English speakers. This study uses the Reicher–Wheeler paradigm with native speakers of Italian (a shallow orthography language). Different from English and French, we found WSE for reaction times (RTs) only, whereas PSE was significant for both accuracy and RTs. This finding indicates that in the Reicher–Wheeler task, readers of a shallow orthography language can effectively rely on both the lexical and the sublexical routes. As to the effect of letter position, a clear advantage for the first-letter position emerged, a finding suggesting a fine-grained processing of the letter strings with coding of letter position and indicating the role of visual acuity and crowding factors.

Download Full-text

Cross-lingual Projected Expectation Regularization for Weakly Supervised Learning

Transactions of the Association for Computational Linguistics ◽

10.1162/tacl_a_00165 ◽

2014 ◽

Vol 2 ◽

pp. 55-66 ◽

Cited By ~ 10

Author(s):

Mengqiu Wang ◽

Christopher D. Manning

Keyword(s):

Supervised Learning ◽

Model Uncertainty ◽

State Of The Art ◽

New Method ◽

Weakly Supervised Learning ◽

Supervised Methods ◽

Weakly Supervised ◽

Language Boundaries ◽

Standard Chinese ◽

Cross Lingual

We consider a multilingual weakly supervised learning scenario where knowledge from annotated corpora in a resource-rich language is transferred via bitext to guide the learning in other languages. Past approaches project labels across bitext and use them as features or gold labels for training. We propose a new method that projects model expectations rather than labels, which facilities transfer of model uncertainty across language boundaries. We encode expectations as constraints and train a discriminative CRF model using Generalized Expectation Criteria (Mann and McCallum, 2010). Evaluated on standard Chinese-English and German-English NER datasets, our method demonstrates F1 scores of 64% and 60% when no labeled data is used. Attaining the same accuracy with supervised CRFs requires 12k and 1.5k labeled sentences. Furthermore, when combined with labeled examples, our method yields significant improvements over state-of-the-art supervised methods, achieving best reported numbers to date on Chinese OntoNotes and German CoNLL-03 datasets.

Download Full-text

Behavioral Genetics: Concepts for Research and Practice in Language Development and Disorders

Journal of Speech Language and Hearing Research ◽

10.1044/jshr.3805.1126 ◽

1995 ◽

Vol 38 (5) ◽

pp. 1126-1142 ◽

Cited By ~ 14

Author(s):

Jeffrey W. Gilger

Keyword(s):

Language Development ◽

Behavioral Genetics ◽

State Of The Art ◽

Genetic Research ◽

Great Promise ◽

Behavioral Genetic ◽

Fine Grained ◽

Future Goals ◽

Current State ◽

Research Designs

This paper is an introduction to behavioral genetics for researchers and practioners in language development and disorders. The specific aims are to illustrate some essential concepts and to show how behavioral genetic research can be applied to the language sciences. Past genetic research on language-related traits has tended to focus on simple etiology (i.e., the heritability or familiality of language skills). The current state of the art, however, suggests that great promise lies in addressing more complex questions through behavioral genetic paradigms. In terms of future goals it is suggested that: (a) more behavioral genetic work of all types should be done—including replications and expansions of preliminary studies already in print; (b) work should focus on fine-grained, theory-based phenotypes with research designs that can address complex questions in language development; and (c) work in this area should utilize a variety of samples and methods (e.g., twin and family samples, heritability and segregation analyses, linkage and association tests, etc.).

Download Full-text

Centralized Ranking Loss with Weakly Supervised Localization for Fine-Grained Object Retrieval

Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence ◽

10.24963/ijcai.2018/171 ◽

2018 ◽

Cited By ~ 9

Author(s):

Xiawu Zheng ◽

Rongrong Ji ◽

Xiaoshuai Sun ◽

Yongjian Wu ◽

Feiyue Huang ◽

...

Keyword(s):

State Of The Art ◽

Feature Learning ◽

Target Object ◽

Object Retrieval ◽

Unified Framework ◽

Fine Grained ◽

Discriminative Feature ◽

Triplet Loss ◽

Weakly Supervised ◽

Ranking Loss

Fine-grained object retrieval has attracted extensive research focus recently. Its state-of-the-art schemesare typically based upon convolutional neural network (CNN) features. Despite the extensive progress, two issues remain open. On one hand, the deep features are coarsely extracted at image level rather than precisely at object level, which are interrupted by background clutters. On the other hand, training CNN features with a standard triplet loss is time consuming and incapable to learn discriminative features. In this paper, we present a novel fine-grained object retrieval scheme that conquers these issues in a unified framework. Firstly, we introduce a novel centralized ranking loss (CRL), which achieves a very efficient (1,000times training speedup comparing to the triplet loss) and discriminative feature learning by a ?centralized? global pooling. Secondly, a weakly supervised attractive feature extraction is proposed, which segments object contours with top-down saliency. Consequently, the contours are integrated into the CNN response map to precisely extract features ?within? the target object. Interestingly, we have discovered that the combination of CRL and weakly supervised learning can reinforce each other. We evaluate the performance ofthe proposed scheme on widely-used benchmarks including CUB200-2011 and CARS196. We havereported significant gains over the state-of-the-art schemes, e.g., 5.4% over SCDA [Wei et al., 2017]on CARS196, and 3.7% on CUB200-2011.

Download Full-text

Geomorphometry: Today and Tomorrow

10.7287/peerj.preprints.27197v1 ◽

2018 ◽

Author(s):

John P Wilson

Keyword(s):

Content Knowledge ◽

State Of The Art ◽

High Fidelity ◽

Terrain Modeling ◽

Actionable Knowledge ◽

Digital Terrain ◽

Current State ◽

Digital Terrain Modeling ◽

Key Innovations

This paper summarizes the current state-of-the-art in geomorphometry and describes the innovations that are close at hand and will be required to push digital terrain modeling forward in the future. These innovations will draw on concepts and methods from computer science and the spatial sciences and require greater collaboration to produce “actionable” knowledge and outcomes. The key innovations include rediscovering and using what we already know, developing new digital terrain modeling methods, clarifying and strengthening the role of theory, developing high-fidelity DEMs, developing and embracing new visualization methods, adopting new computational approaches, and making better use of provenance, credibility, and application-content knowledge.

Download Full-text

EHSOD: CAM-Guided End-to-End Hybrid-Supervised Object Detection with Cascade Refinement

Proceedings of the AAAI Conference on Artificial Intelligence ◽

10.1609/aaai.v34i07.6707 ◽

2020 ◽

Vol 34 (07) ◽

pp. 10778-10785

Author(s):

Linpu Fang ◽

Hang Xu ◽

Zhili Liu ◽

Sarah Parisot ◽

Zhenguo Li

Keyword(s):

Object Detection ◽

State Of The Art ◽

Detection System ◽

Parameter Tuning ◽

Heat Map ◽

Level Data ◽

End To End ◽

Weakly Supervised ◽

Yield State ◽

Activation Heat

Object detectors trained on fully-annotated data currently yield state of the art performance but require expensive manual annotations. On the other hand, weakly-supervised detectors have much lower performance and cannot be used reliably in a realistic setting. In this paper, we study the hybrid-supervised object detection problem, aiming to train a high quality detector with only a limited amount of fully-annotated data and fully exploiting cheap data with image-level labels. State of the art methods typically propose an iterative approach, alternating between generating pseudo-labels and updating a detector. This paradigm requires careful manual hyper-parameter tuning for mining good pseudo labels at each round and is quite time-consuming. To address these issues, we present EHSOD, an end-to-end hybrid-supervised object detection system which can be trained in one shot on both fully and weakly-annotated data. Specifically, based on a two-stage detector, we proposed two modules to fully utilize the information from both kinds of labels: 1) CAM-RPN module aims at finding foreground proposals guided by a class activation heat-map; 2) hybrid-supervised cascade module further refines the bounding-box position and classification with the help of an auxiliary head compatible with image-level data. Extensive experiments demonstrate the effectiveness of the proposed method and it achieves comparable results on multiple object detection benchmarks with only 30% fully-annotated data, e.g. 37.5% mAP on COCO. We will release the code and the trained models.

Download Full-text

Regularized Instance Embedding for Deep Multi-Instance Learning

Applied Sciences ◽

10.3390/app10010064 ◽

2019 ◽

Vol 10 (1) ◽

pp. 64

Author(s):

Yi Lin ◽

Honggang Zhang

Keyword(s):

Neural Network ◽

Big Data ◽

Supervised Learning ◽

Regularization Method ◽

Gradient Descent ◽

State Of The Art ◽

Stochastic Gradient Descent ◽

Learning Framework ◽

Weakly Supervised ◽

The Cost

In the era of Big Data, multi-instance learning, as a weakly supervised learning framework, has various applications since it is helpful to reduce the cost of the data-labeling process. Due to this weakly supervised setting, learning effective instance representation/embedding is challenging. To address this issue, we propose an instance-embedding regularizer that can boost the performance of both instance- and bag-embedding learning in a unified fashion. Specifically, the crux of the instance-embedding regularizer is to maximize correlation between instance-embedding and underlying instance-label similarities. The embedding-learning framework was implemented using a neural network and optimized in an end-to-end manner using stochastic gradient descent. In experiments, various applications were studied, and the results show that the proposed instance-embedding-regularization method is highly effective, having state-of-the-art performance.

Download Full-text

The growing role of structural mass spectrometry in the discovery and development of therapeutic antibodies

The Analyst ◽

10.1039/c8an00295a ◽

2018 ◽

Vol 143 (11) ◽

pp. 2459-2468 ◽

Cited By ~ 14

Author(s):

Yuwei Tian ◽

Brandon T. Ruotolo

Keyword(s):

Mass Spectrometry ◽

State Of The Art ◽

Therapeutic Antibodies ◽

Critical Importance ◽

Current State ◽

Measurement Science ◽

Structural Mass Spectrometry ◽

Structural Mass

The comprehensive structural characterization of therapeutic antibodies is of critical importance for the successful discovery and development of such biopharmaceuticals, yet poses many challenges to modern measurement science. Here, we review the current state-of-the-art mass spectrometry technologies focusing on the characterization of antibody-based therapeutics.

Download Full-text