Fine-Grained Recognition as HSnet Search for Informative Image Parts

Lam, Michael; Mahasseni, Behrooz; Todorovic, Sinisa

doi:10.1109/cvpr.2017.688

Cited by 124 publications

(72 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Part Based Fine-grained Image Classification. Learning a diverse collection of discriminative parts in a supervised [52,51] or unsupervised manner [35,53,26] is very popular in fine-grained image classification. Many works [52,51] have been done to build object part models with part bounding box annotations.…”

Section: Related Workmentioning

confidence: 99%

“…Zhang et al in [51] treats objects and semantic parts equally by assigning them in different object classes with R-CNN [14]. Another line of works [35,53,26,45] estimate the part location in a unsupervised setting. In [35], parts are discovered based the neural activation, and then are optimized using a EM similar algorithm.…”

Section: Related Workmentioning

confidence: 99%

“…LSTM network shows its powerfulness in encoding the context information for image classification. In [26], Lam et al address fine-grained image classification by mining informative image parts using a heuristic network, a successor network and a single layer LSTM. The heuristic network is responsible for extracting features from proposals and the successor network is responsible for predicting the new proposal offset.…”

Section: Related Workmentioning

confidence: 99%

“…Our baseline model in this group is a directly fine-tuned GoogleNet model that achieves a classification accuracy of 82.6%. We then add the Stacked LSTM module and train the model with both single loss and multiple losses, which achieves a classification accuracy of 87.6% and 90.3% respectively, outperforming all other algorithms in this comparison [54,49,46,27]. Compared to HSNet, our model does not use any parts annotations in the training stage while HSNet is trained with groundtruth parts annotations.…”

Section: Fine-grained Image Classificationmentioning

confidence: 99%

See 3 more Smart Citations

Weakly Supervised Complementary Parts Models for Fine-Grained Image Classification From the Bottom Up

Lin

2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

280

184

View full text Add to dashboard Cite

Given a training dataset composed of images and corresponding category labels, deep convolutional neural networks show a strong ability in mining discriminative parts for image classification. However, deep convolutional neural networks trained with image level labels only tend to focus on the most discriminative parts while missing other object parts, which could provide complementary information. In this paper, we approach this problem from a different perspective. We build complementary parts models in a weakly supervised manner to retrieve information suppressed by dominant object parts detected by convolutional neural networks. Given image level labels only, we first extract rough object instances by performing weakly supervised object detection and instance segmentation using Mask R-CNN and CRF-based segmentation. Then we estimate and search for the best parts model for each object instance under the principle of preserving as much diversity as possible. In the last stage, we build a bi-directional long short-term memory (LSTM) network to fuze and encode the partial information of these complementary parts into a comprehensive feature for image classification. Experimental results indicate that the proposed method not only achieves significant improvement over our baseline models, but also outperforms state-of-the-art algorithms by a large margin (6.7%, 2.8%, 5.2% respectively) on Stanford Dogs 120, Caltech-UCSD Birds 2011-200 and Caltech 256.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Fine-grained Image Classificationmentioning

confidence: 99%

See 2 more Smart Citations

Weakly Supervised Complementary Parts Models for Fine-Grained Image Classification From the Bottom Up

Lin

2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

280

184

View full text Add to dashboard Cite

show abstract

“…Fine-grained visual categorization State-of-the-art FGVC methods usually follow the pipeline that first discovers discriminative local parts from images of fine-grained categories, and then utilizes the discovered parts for classification. For example, Lam et al [13] search for discriminative parts by iteratively evaluating and generating bounding box proposals with or without the supervision of ground-truth part annotations. Based on off-the-shelf object proposals [24], part detectors are learned in [35] by clustering subregions of object proposals.…”

Section: Related Workmentioning

confidence: 99%

Fine-Grained Visual Categorization Using Meta-learning Optimization with Sample Selection of Auxiliary Data

Zhang

Tang

Jia

2018

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Fine-grained visual categorization (FGVC) is challenging due in part to the fact that it is often difficult to acquire an enough number of training samples. To employ large models for FGVC without suffering from overfitting, existing methods usually adopt a strategy of pretraining the models using a rich set of auxiliary data, followed by finetuning on the target FGVC task. However, the objective of pre-training does not take the target task into account, and consequently such obtained models are suboptimal for fine-tuning. To address this issue, we propose in this paper a new deep FGVC model termed MetaFGNet. Training of MetaFGNet is based on a novel regularized meta-learning objective, which aims to guide the learning of network parameters so that they are optimal for adapting to the target FGVC task. Based on MetaFGNet, we also propose a simple yet effective scheme for selecting more useful samples from the auxiliary data. Experiments on benchmark FGVC datasets show the efficacy of our proposed method.

show abstract

Learning to Navigate for Fine-Grained Classification

Yang

Luo

Wang

et al. 2018

Lecture Notes in Computer Science

509

308

View full text Add to dashboard Cite

Fine-grained classification is challenging due to the difficulty of finding discriminative features. Finding those subtle traits that fully characterize the object is not straightforward. To handle this circumstance, we propose a novel self-supervision mechanism to effectively localize informative regions without the need of bounding-box/part annotations. Our model, termed NTS-Net for Navigator-Teacher-Scrutinizer Network, consists of a Navigator agent, a Teacher agent and a Scrutinizer agent. In consideration of intrinsic consistency between informativeness of the regions and their probability being ground-truth class, we design a novel training paradigm, which enables Navigator to detect most informative regions under the guidance from Teacher. After that, the Scrutinizer scrutinizes the proposed regions from Navigator and makes predictions. Our model can be viewed as a multi-agent cooperation, wherein agents benefit from each other, and make progress together. NTS-Net can be trained end-to-end, while provides accurate fine-grained classification predictions as well as highly informative regions during inference. We achieve state-of-the-art performance in extensive benchmark datasets.

show abstract

Fine-Grained Recognition as HSnet Search for Informative Image Parts

Cited by 124 publications

References 25 publications

Weakly Supervised Complementary Parts Models for Fine-Grained Image Classification From the Bottom Up

Weakly Supervised Complementary Parts Models for Fine-Grained Image Classification From the Bottom Up

Fine-Grained Visual Categorization Using Meta-learning Optimization with Sample Selection of Auxiliary Data

Learning to Navigate for Fine-Grained Classification

Contact Info

Product

Resources

About