Small Object Detection using Context and Attention

Lim, Jeong-Seon; Astrid, Marcella; Yoon, Hyunjin; Lee, Seung-Ik

doi:10.48550/arxiv.1912.06319

Cited by 5 publications

(3 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The attention mechanism is used in deep learning to simulate the characteristics of human attention to things [22]. It can be broadly understood as focusing on part of the input for a specific task rather than seeing the entire input [23]. in 2018, Wang et al proposed a method that presented non-local operations as a generic family of building blocks for capturing long-range dependencies [24].…”

Section: Visual Attentionmentioning

confidence: 99%

A few-shot fine-grained image recognition method

Wang,

Chen

2023

Bulletin of the Polish Academy of Sciences Technical Sciences

View full text Add to dashboard Cite

Deep learning methods benefit from data sets with comprehensive coverage (e.g., ImageNet, COCO, etc.), which can be regarded as a description of the distribution of real-world data. The models trained on these datasets are considered to be able to extract general features and migrate to a domain not seen in downstream. However, in the open scene, the labeled data of the target data set are often insufficient. The depth models trained under a small amount of sample data have poor generalization ability. The identification of new categories or categories with a very small amount of sample data is still a challenging task. This paper proposes a few-shot fine-grained image recognition method. Feature maps are extracted by a CNN module with an embedded attention network to emphasize the discriminative features. A channel-based feature expression is applied to the base class and novel class followed by an improved cosine similarity-based measurement method to get the similarity score to realize the classification. Experiments are performed on main few-shot benchmark datasets to verify the efficiency and generality of our model, such as Stanford Dogs, CUB-200, and so on. The experimental results show that our method has more advanced performance on fine-grained datasets.

show abstract

Section: Visual Attentionmentioning

confidence: 99%

A few-shot fine-grained image recognition method

Wang,

Chen

2023

Bulletin of the Polish Academy of Sciences Technical Sciences

View full text Add to dashboard Cite

show abstract

“…Attention has been used in classification, recognition and localization tasks, as in [8,23,37]. The authors of [7] propose an attention model for object detection and counting on drones, while [28] uses attention for small object detection. Other examples of attention models used for image classification are [38,29,12,45].…”

Section: Attention Modelsmentioning

confidence: 99%

Explaining Autonomous Driving by Learning End-to-End Visual Attention

Cultrera

Seidenari

Becattini

et al. 2020

2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

View full text Add to dashboard Cite

Current deep learning based autonomous driving approaches yield impressive results also leading to inproduction deployment in certain controlled scenarios. One of the most popular and fascinating approaches relies on learning vehicle controls directly from data perceived by sensors. This end-to-end learning paradigm can be applied both in classical supervised settings and using reinforcement learning. Nonetheless the main drawback of this approach as also in other learning problems is the lack of explainability. Indeed, a deep network will act as a black-box outputting predictions depending on previously seen driving patterns without giving any feedback on why such decisions were taken.While to obtain optimal performance it is not critical to obtain explainable outputs from a learned agent, especially in such a safety critical field, it is of paramount importance to understand how the network behaves. This is particularly relevant to interpret failures of such systems.In this work we propose to train an imitation learning based agent equipped with an attention model. The attention model allows us to understand what part of the image has been deemed most important. Interestingly, the use of attention also leads to superior performance in a standard benchmark using the CARLA driving simulator.

show abstract

“…Attention-based approaches have found decent popularity in the computer vision community (Woo et al 2018;Li et al 2020). Their ability to focus selectively on an image is helpful in cases where features of interest span a small number of pixels and their occurrences are rare (Lim et al 2019;Bai et al 2020;Zhang et al 2020).…”

Section: Introductionmentioning

confidence: 99%

Accurate and Clear Quantitative Precipitation Nowcasting Based on a Deep Learning Model with Consecutive Attention and Rain-Map Discrimination

Ashesh

Chang

Chen

et al. 2022

Artificial Intelligence for the Earth Systems

View full text Add to dashboard Cite

Deep learning models are developed for high-resolution quantitative precipitation nowcasting (QPN) in Taiwan up to 3 h ahead. Many recent works aim to accurately predict relatively rare high-rainfall events with the help of deep learning. This rarity is often addressed by formulations that reweight the rare events. However, these formulations often carry a side effect of producing blurry rain-map nowcasts that overpredict in low-rainfall regions. Such nowcasts are visually less trustworthy and practically less useful for forecasters. We fix the trust issue by introducing a discriminator that encourages the model to generate realistic rain maps without sacrificing the predictive accuracy of rainfall extremes. Moreover, with consecutive attention across different hours, we extend the nowcasting time frame from typically 1 to 3 h to further address the needs for socioeconomic weather-dependent decision-making. By combining the discriminator and the attention techniques, the proposed model based on the convolutional recurrent neural network is trained with a dataset containing radar reflectivity and rain rates at a granularity of 10 min and predicts the hourly accumulated rainfall in the next three hours. Model performance is evaluated from both statistical and case-study perspectives. Statistical verification shows that the new model outperforms the current operational QPN techniques. Case studies further show that the model can capture the motion of rainbands in a frontal case and also provide an effective warning of urban-area torrential rainfall in an afternoon-thunderstorm case, implying that deep learning has great potential and is useful in 0–3-h nowcasting.

show abstract

Small Object Detection using Context and Attention

Cited by 5 publications

References 17 publications

A few-shot fine-grained image recognition method

A few-shot fine-grained image recognition method

Explaining Autonomous Driving by Learning End-to-End Visual Attention

Accurate and Clear Quantitative Precipitation Nowcasting Based on a Deep Learning Model with Consecutive Attention and Rain-Map Discrimination

Contact Info

Product

Resources

About