Boosted Convolutional Neural Networks

Moghimi, Mohammad Kazem; Belongie, Serge; Saberian, Mohammad; Yang, Jian; Vasconcelos, Nuno; Li, Li-Jia

doi:10.5244/c.30.24

Cited by 113 publications

(91 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Compared with the baselines of pooling-based model B-CNN [17], CBP [6] and LRBP [12], the superior result that we achieve mainly benefits from Anno. Accuracy SPDA-CNN [35] √ 85.1 B-CNN [17] √ 85.1 PN-CNN [2] √ 85.4 STN [9] 84.1 RA-CNN [5] 85.3 MA-CNN [37] 86.5 B-CNN [17] 84.0 CBP [6] 84.0 LRBP [12] 84.2 HIHCA [3] 85.3 Improved B-CNN [16] 85.8 BoostCNN [22] 86.2 KP [4] 86.2 FBP(relu5 3) 85.7 CBP(relu5 3 + relu5 2) 86.7 HBP(relu5 3 + relu5 2 + relu5 1) 87.1…”

Section: Configurations Of Hierarchical Bilinear Poolingmentioning

confidence: 99%

See 1 more Smart Citation

Hierarchical Bilinear Pooling for Fine-Grained Visual Recognition

Zhao

Zheng

et al. 2018

Lecture Notes in Computer Science

281

178

View full text Add to dashboard Cite

Fine-grained visual recognition is challenging because it highly relies on the modeling of various semantic parts and fine-grained feature learning. Bilinear pooling based models have been shown to be effective at fine-grained recognition, while most previous approaches neglect the fact that inter-layer part feature interaction and fine-grained feature learning are mutually correlated and can reinforce each other. In this paper, we present a novel model to address these issues. First, a crosslayer bilinear pooling approach is proposed to capture the inter-layer part feature relations, which results in superior performance compared with other bilinear pooling based approaches. Second, we propose a novel hierarchical bilinear pooling framework to integrate multiple cross-layer bilinear features to enhance their representation capability. Our formulation is intuitive, efficient and achieves state-of-the-art results on the widely used fine-grained recognition datasets.

show abstract

Section: Configurations Of Hierarchical Bilinear Poolingmentioning

confidence: 99%

“…The classification accuracy on FGVC-Aircraft is summarized in Table 6. Still, our model achieves the highest √ 92.6 FCAN [18] 89.1 RA-CNN [5] 92.5 MA-CNN [37] 92.8 B-CNN [17] 90.6 LRBP [12] 90.9 HIHCA [3] 91.7 Improved B-CNN [16] 92.0 BoostCNN [22] 92.1 KP [4] 92.4 HBP 93.7…”

Section: Configurations Of Hierarchical Bilinear Poolingmentioning

confidence: 99%

Hierarchical Bilinear Pooling for Fine-Grained Visual Recognition

Zhao

Zheng

et al. 2018

Lecture Notes in Computer Science

281

178

View full text Add to dashboard Cite

show abstract

“…Our method achieves better performance than those [4,18,30,31,32] using ground-truth bounding boxes or part annotations during training or testing time on three datasets. Compared with BCNN-based methods [8,20,25] our method obtains comparable or even better performance due to accurate attention localization and part sequence modeling. To further enhance the capacity of REAPS, as RA-CNN [9] does, we incorporate one more PSN into our framework, and the 2nd PSN is based on the attended region of the 1st PSN.…”

Section: Experiments and Analysismentioning

confidence: 97%

REAPS: Towards Better Recognition of Fine-Grained Images by Region Attending and Part Sequencing

Zhang

Zhu

Cheng

et al. 2019

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Fine-grained image recognition has been a hot research topic in computer vision due to its various applications. The-state-of-the-art is the part/region-based approaches that first localize discriminative parts/regions, and then learn their fine-grained features. However, these approaches have some inherent drawbacks: 1) the discriminative feature representation of an object is prone to be disturbed by complicated background; 2) it is unreasonable and inflexible to fix the number of salient parts, because the intended parts may be unavailable under certain circumstances due to occlusion or incompleteness, and 3) the spatial correlation among different salient parts has not been thoroughly exploited (if not completely neglected). To overcome these drawbacks, in this paper we propose a new, simple yet robust method by building part sequence model on the attended object region. Concretely, we first try to alleviate the background effect by using a region attention mechanism to generate the attended region from the original image. Then, instead of localizing different salient parts and extracting their features separately, we learn the part representation implicitly by applying a mapping function on the serialized features of the object. Finally, we combine the region attending network and the part sequence learning network into a unified framework that can be trained end-to-end with only image-level labels. Our extensive experiments on three fine-grained benchmarks show that the proposed method achieves the state of the art performance.

show abstract

“…There exist different works that proposed the use of ensemble methods for deep neural networks. Remarkable results are reported in [26], where the authors adopted a boosting strategy on image classification, but also in CoopNet [27] which combines multiple precision models to improve accuracy and inference latency. Even more interesting, the concept of ensemble learning can be found in the internal architecture of the most recent CNN models.…”

Section: Ensembles Learningmentioning

confidence: 99%

TentacleNet: A Pseudo-Ensemble Template for Accurate Binary Convolutional Neural Networks

Mocerino

Calimera

2020

2020 2nd IEEE International Conference on Artificial Intelligence Circuits and Systems (AICAS)

View full text Add to dashboard Cite

Binarization is an attractive strategy for implementing lightweight Deep Convolutional Neural Networks (CNNs). Despite the unquestionable savings offered, memory footprint above all, it may induce an excessive accuracy loss that prevents a widespread use. This work elaborates on this aspect introducing TentacleNet, a new template designed to improve the predictive performance of binarized CNNs via parallelization. Inspired by the ensemble learning theory, it consists of a compact topology that is end-to-end trainable and organized to minimize memory utilization. Experimental results collected over three realistic benchmarks show TentacleNet fills the gap left by classical binary models, ensuring substantial memory savings w.r.t. state-of-the-art binary ensemble methods.

show abstract

Boosted Convolutional Neural Networks

Cited by 113 publications

References 0 publications

Hierarchical Bilinear Pooling for Fine-Grained Visual Recognition

Hierarchical Bilinear Pooling for Fine-Grained Visual Recognition

REAPS: Towards Better Recognition of Fine-Grained Images by Region Attending and Part Sequencing

TentacleNet: A Pseudo-Ensemble Template for Accurate Binary Convolutional Neural Networks

Contact Info

Product

Resources

About