Picking Deep Filter Responses for Fine-Grained Image Recognition

Zhang, Xiaopeng; Xiong, Hongkai; Zhou, Wengang; Lin, Weiyao; Tian, Qi

doi:10.1109/cvpr.2016.128

Cited by 323 publications

(222 citation statements)

References 18 publications

Supporting

Mentioning

220

Contrasting

Order By: Relevance

“…[28], [37]) try to learn more robust representations via distance metric learning. [38] unifies deep CNN features with spatially weighted Fisher vectors to capture important details and eliminate background disturbance. [25] incorporates deep CNNs into a generic boosting framework to combine the strength of multiple weaker learners, which improves the classification accuracy of a single model and simplifies the network design.…”

Section: Representation Learningmentioning

confidence: 99%

“…In general, RLA tries to attend and amplify the key region for capturing detailed visual representation while avoiding background disturbance. On the other hand, PL usually first localizes discriminative parts via some sophisticated part selection mechanisms such as part attentions [9,32,39] and convolutional responses [33,38], and then extracts the visual representations of the selected parts by using multiple independent feature extractors. Fig.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

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

Section: Representation Learningmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

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

show abstract

“…This is because expert human annotations can be cumbersome to obtain and are often error-prone [35]. More recent research has therefore concentrated on realizing parts in an unsupervised fashion [7], [9], [22], [30], [34], [41], [49]. These approaches have been shown to yield performances on par or even exceeding those that relied on manual annotations, owing to their ability of mining discriminative parts that are otherwise missing or inaccurate in human labelled data.…”

Section: Introductionmentioning

confidence: 99%

“…In this paper, we follow the same motivation as above [38], [49], [50] to address the unique challenges of fine-grained classification. We importantly differ in that we do not attempt to introduce any explicit network components for discriminate part discovery.…”

Section: Introductionmentioning

confidence: 99%

The Devil is in the Channels: Mutual-Channel Loss for Fine-Grained Image Classification

Chang

Ding

Xie

et al. 2020

IEEE Trans. on Image Process.

316

102

View full text Add to dashboard Cite

Key for solving fine-grained image categorization is finding discriminate and local regions that correspond to subtle visual traits. Great strides have been made, with complex networks designed specifically to learn part-level discriminate feature representations. In this paper, we show it is possible to cultivate subtle details without the need for overly complicated network designs or training mechanisms -a single loss is all it takes. The main trick lies with how we delve into individual feature channels early on, as opposed to the convention of starting from a consolidated feature map. The proposed loss function, termed as mutual-channel loss (MC-Loss), consists of two channel-specific components: a discriminality component and a diversity component. The discriminality component forces all feature channels belonging to the same class to be discriminative, through a novel channel-wise attention mechanism. The diversity component additionally constraints channels so that they become mutually exclusive on spatial-wise. The end result is therefore a set of feature channels that each reflects different locally discriminative regions for a specific class. The MC-Loss can be trained end-to-end, without the need for any bounding-box/part annotations, and yields highly discriminative regions during inference. Experimental results show our MC-Loss when implemented on top of common base networks can achieve state-of-the-art performance on all four fine-grained categorization datasets (CUB-Birds, FGVC-Aircraft, Flowers-102, and Stanford-Cars). Ablative studies further demonstrate the superiority of MC-Loss when compared with other recently proposed general-purpose losses for visual classification, on two different base networks. Code available at https://github.com/ dongliangchang/Mutual-Channel-Loss

show abstract

“…It is not sufficient for common users to find very fine-grained and personalized photos. For example, tagging different bird species [76,77], flower types [78,79], car models [80,81], or even human sentiment [82] have attracted extensive attention. This task is very challenging as some fine-grained categories (e.g., eared grebe, and horned grebe) can only be recognized by domain experts.…”

Section: D) Photo App On Ios 10mentioning

confidence: 99%