Filters








7,407 Hits in 4.7 sec

One-Shot Fine-Grained Instance Retrieval [article]

Hantao Yao, Shiliang Zhang, Yongdong Zhang, Jintao Li, Qi Tian
2017 arXiv   pre-print
Aiming to conquer this issue, we propose a retrieval task named One-Shot Fine-Grained Instance Retrieval (OSFGIR).  ...  "One-Shot" denotes the ability of identifying unseen objects through a fine-grained retrieval task assisted with an incomplete auxiliary training set.  ...  PROBLEM FORMULATION 3.1 One-Shot Fine-Grained Instance Retrieval As illustrated in Fig. 1 , OSFGIR de nes a ne-grained instance retrieval task assisted with a small independent training set.  ... 
arXiv:1707.00811v1 fatcat:zfnpunlofrbspkgpz755xe5p2a

One-Shot Fine-Grained Instance Retrieval

Hantao Yao, Shiliang Zhang, Yongdong Zhang, Jintao Li, Qi Tian
2017 Proceedings of the 2017 ACM on Multimedia Conference - MM '17  
Aiming to conquer this issue, we propose a retrieval task named One-Shot Fine-Grained Instance Retrieval (OSFGIR).  ...  "One-Shot" denotes the ability of identifying unseen objects through a ne-grained retrieval task assisted with an incomplete auxiliary training set.  ...  Motivated to conquer this issue, we present a novel problem named One-Shot Fine-Grained Instance Retrieval (OSFGIR), where "One-Shot" emphasizes the ability of identifying the unseen ne-grained species  ... 
doi:10.1145/3123266.3123278 dblp:conf/mm/YaoZZLT17 fatcat:s6stj7xujzganjypus6l2phive

Fine-Grained Action Retrieval Through Multiple Parts-of-Speech Embeddings

Michael Wray, Gabriela Csurka, Diane Larlus, Dima Damen
2019 2019 IEEE/CVF International Conference on Computer Vision (ICCV)  
We report the first retrieval results on fine-grained actions for the large-scale EPIC dataset, in a generalised zero-shot setting.  ...  We address the problem of cross-modal fine-grained action retrieval between text and video.  ...  Fine-Grained Action Retrieval on EPIC Dataset.  ... 
doi:10.1109/iccv.2019.00054 dblp:conf/iccv/WrayCLD19 fatcat:7g5jonm73fegbhkuqrauidnz4a

Super-Fine Attributes with Crowd Prototyping

Daniel Martinho-Corbishley, Mark Nixon, John N. Carter
2018 IEEE Transactions on Pattern Analysis and Machine Intelligence  
We also find our 3 super-fine traits to outperform 35 binary attributes by 6.5% mAP for subject retrieval in a challenging zero-shot identification scenario.  ...  Inspired by fine-grained and relative attributes, we introduce super-fine attributes, which now describe multiple, integral concepts of a single trait as multi-dimensional perceptual coordinates.  ...  We find subject-level super-fine labels commonly attain the best performance in multi-shot retrieval, and instance-level alternatives to perform better in zero-shot retrieval.  ... 
doi:10.1109/tpami.2018.2836900 pmid:29994759 fatcat:z7cf52y4jrdmnl7fke5yvekshe

Coarse-to-Fine Pseudo-Labeling Guided Meta-Learning for Inexactly-Supervised Few-Shot Classification [article]

Jinhai Yang, Hua Yang, Lin Chen
2020 arXiv   pre-print
In this paper, we present a new problem named inexactly-supervised meta-learning to alleviate such limitation, focusing on tackling few-shot classification tasks with only coarse-grained supervision.  ...  However, most existing meta-learning algorithms require fine-grained supervision, thereby involving prohibitive annotation cost.  ...  Although meta-learning systems have shown their capacity for learning in a low-data regime, most of them still rely heavily on fine-grained annotations.  ... 
arXiv:2007.05675v2 fatcat:czev6hm2mfep7dascne5fioeza

Fine-Grained Action Retrieval Through Multiple Parts-of-Speech Embeddings [article]

Michael Wray, Diane Larlus, Gabriela Csurka, Dima Damen
2019 arXiv   pre-print
We report the first retrieval results on fine-grained actions for the large-scale EPIC dataset, in a generalised zero-shot setting.  ...  We address the problem of cross-modal fine-grained action retrieval between text and video.  ...  Fine-Grained Action Retrieval on EPIC Dataset.  ... 
arXiv:1908.03477v1 fatcat:5po6jw4sczgzhezll4isf7x3my

CLAREL: Classification via retrieval loss for zero-shot learning [article]

Boris N. Oreshkin and Negar Rostamzadeh and Pedro O. Pinheiro and Christopher Pal
2020 arXiv   pre-print
We evaluate our approach on two fine-grained zero-shot learning datasets: CUB and FLOWERS.  ...  We address the problem of learning fine-grained cross-modal representations. We propose an instance-based deep metric learning approach in joint visual and textual space.  ...  Instance-based training loss. Zero-shot learning approaches rely heavily on class-level modality alignment [30] .  ... 
arXiv:1906.11892v3 fatcat:6xt4awflxrbhbdyk7gu77irh7a

Stacked Semantic-Guided Network for Zero-Shot Sketch-Based Image Retrieval [article]

Hao Wang, Cheng Deng, Xinxu Xu, Wei Liu, Xinbo Gao, Dacheng Tao
2019 arXiv   pre-print
(taking auxiliary semantic information as conditional input) and then generates fine-grained instance-specific corresponding features (taking sketch representation as conditional input).  ...  Zero-shot sketch-based image retrieval (ZS-SBIR) is a task of cross-domain image retrieval from a natural image gallery with free-hand sketch under a zero-shot scenario.  ...  To tackle this issue, we elaborate a coarse-to-fine conditional decoder to generate coarse-grained category-specific natural image features first and then generate fine-grained instance-specific features  ... 
arXiv:1904.01971v2 fatcat:uthgdpzqynb75bjcrlcrl5u744

Fine-Grained Image Analysis with Deep Learning: A Survey [article]

Xiu-Shen Wei and Yi-Zhe Song and Oisin Mac Aodha and Jianxin Wu and Yuxin Peng and Jinhui Tang and Jian Yang and Serge Belongie
2021 arXiv   pre-print
image recognition and fine-grained image retrieval.  ...  In this paper we present a systematic survey of these advances, where we attempt to re-define and broaden the field of FGIA by consolidating two fundamental fine-grained research areas -- fine-grained  ...  Given an input query x q , the goal of a fine-grained retrieval system is to rank all instances in a retrieval set Ω = {x (i) } M i=1 (whose label y ∈ Y c ) based on their fine-grained relevance to the  ... 
arXiv:2111.06119v2 fatcat:ninawxsjtnf4lndtqquuwl3weq

Semantically Tied Paired Cycle Consistency for Any-Shot Sketch-based Image Retrieval [article]

Anjan Dutta, Zeynep Akata
2020 arXiv   pre-print
In this paper, we address any-shot, i.e. zero-shot and few-shot, sketch-based image retrieval (SBIR) tasks, where we introduce the few-shot setting for SBIR.  ...  Low-shot sketch-based image retrieval is an emerging task in computer vision, allowing to retrieve natural images relevant to hand-drawn sketch queries that are rarely seen during the training phase.  ...  For fine tuning the model in k-shot setting, we consider k different sketch and image instances from each of the unseen classes and cross-combine according to the coarse-grained and fine-grained settings  ... 
arXiv:2006.11397v1 fatcat:4tkatm4h5jdzjacdx23x7jbd7y

Language Models as Zero-shot Visual Semantic Learners [article]

Yue Jiao, Jonathon Hare, Adam Prügel-Bennett
2021 arXiv   pre-print
Current approaches to VSE heavily rely on static word em-bedding techniques.  ...  We further introduce a zero-shot setting with VSEPs to evaluate a model's ability to associate a novel word with a novel visual category.  ...  fine-grained visual content.  ... 
arXiv:2107.12021v1 fatcat:7ty373ume5e23drdoczoc6engm

A Zero-Shot Framework for Sketch-based Image Retrieval [article]

Sasi Kiran Yelamarthi, Shiva Krishna Reddy, Ashish Mishra, Anurag Mittal
2018 arXiv   pre-print
However, current evaluation methods simply focus only on coarse-grained evaluation where the focus is on retrieving images which belong to the same class as the sketch but not necessarily having the same  ...  better than several state-of-the-art approaches in the proposed zero-shot framework of the coarse-grained SBIR task.  ...  One way to discourage such class specific learning is to employ a fine-grained evaluation.  ... 
arXiv:1807.11724v1 fatcat:l37g3e7oazdthl2rbacocii2b4

Learning Deep Representations of Fine-grained Visual Descriptions [article]

Scott Reed, Zeynep Akata, Bernt Schiele, Honglak Lee
2016 arXiv   pre-print
Our model achieves strong performance on zero-shot text-based image retrieval and significantly outperforms the attribute-based state-of-the-art for zero-shot classification on the Caltech UCSD Birds 200  ...  Our proposed models train end-to-end to align with the fine-grained and category-specific content of images.  ...  Our contribution builds on previous work on characterlevel language models [52] and fine-grained zero-shot learning [1] to train high capacity text encoders from scratch to jointly embed fine-grained  ... 
arXiv:1605.05395v1 fatcat:csh33lsn6zbv7djlah5espgxxq

Dynamic Detection and Recognition of Objects Based on Sequential RGB Images

Shuai Dong, Zhihua Yang, Wensheng Li, Kun Zou
2021 Future Internet  
Aiming at this goal, we design a framework that involves three subtasks: one-class instance segmentation (OCIS), multiobject tracking (MOT), and zero-shot fine-grained recognition of 3D objects (ZSFGR3D  ...  To validate the performance of the proposed methods, a segmentation dataset and a fine-grained classification dataset about objects on a conveyor are established.  ...  In this study, a framework of LROC involving three subtasks (one-class instance segmentation (OCIS), multiobject tracking (MOT), and zero-shot fine-grained recognition of 3D objects (ZSFGR3D)) is developed  ... 
doi:10.3390/fi13070176 fatcat:wm6tolhqyfahjnp6quhubulu6y

A Zero-Shot Framework for Sketch Based Image Retrieval [chapter]

Sasi Kiran Yelamarthi, Shiva Krishna Reddy, Ashish Mishra, Anurag Mittal
2018 Lecture Notes in Computer Science  
However, current evaluation methods simply focus only on coarse-grained evaluation where the focus is on retrieving images which belong to the same class as the sketch but not necessarily having the same  ...  better than several state-of-the-art approaches in the proposed zero-shot framework of the coarse-grained SBIR task.  ...  One way to discourage such class specific learning is to employ a fine-grained evaluation [30, 51] .  ... 
doi:10.1007/978-3-030-01225-0_19 fatcat:zodc2kyrsndbbljuj4th3nufvi
« Previous Showing results 1 — 15 out of 7,407 results