Swin transformer-based supervised hashing

Peng, Liangkang; Qian, Jiangbo; Wang, Chong; Liu, Baisong; Dong, Yihong

doi:10.1007/s10489-022-04410-6

Cited by 9 publications

(5 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Where the information is available, we also show the change in accuracy and parameter count these models achieve in comparison to the highest accuracy nontransformer structure described in the original works. By adopting the SwinV2 transformer [216], the authors of [264] demonstrate significant improvements to event-based object tracking. [261] offers many comparisons to other works by accuracy and parameter count, however, the authors neglect to include both metrics for any one task.…”

Section: E Need Of Transformersmentioning

confidence: 99%

Event Cameras in Automotive Sensing: A Review

Shariff,

Dilmaghani,

Kielty

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Event cameras (EC) represent a paradigm shift and are emerging as valuable tools in the automotive industry, particularly for in-cabin and out-of-cabin monitoring. These cameras capture pixel intensity changes as "events" with ultra-low latency, making them suitable for real-time applications. In the context of in-cabin monitoring, EC offer solution for driver and passenger tracking, enhancing safety and comfort. For out-of-cabin monitoring, they excel in tracking objects and detecting potential hazards on the road. This article explores the applications, benefits, and challenges of event cameras in these two critical domains within the automotive industry. This review also highlights relevant datasets and methodologies, enabling researchers to make informed decisions tailored to their specific vehicular-technology and place their work in the broader context of EC sensing. Through an exploration of the hardware, the complexities of data processing, and customized algorithms for both in-cabin and out-of-cabin surveillance, this paper outlines a framework encompassing methodologies, tools, and datasets critical for the implementation of event camera sensing in automotive systems. INDEX TERMSNeuromorphic Event Camera, Event based Vision, Driver Monitoring System, Out-of-cabin Monitoring, In-Cabin Monitoring.

show abstract

Section: E Need Of Transformersmentioning

confidence: 99%

Event Cameras in Automotive Sensing: A Review

Shariff,

Dilmaghani,

Kielty

et al. 2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…This quantization error can be measured either by Euclidean or Angle distance, as illustrated in Figure 3. Precisely, we measure the quantization error of the database by Euclidean distance (19), squared Euclidean distance (20), and the angle θ znhn between the continuous hash code z n and the discrete hash code h n (21).…”

Section: ) Quantization Errormentioning

confidence: 99%

“…Learning to hash can also leverage deep learning to become deep hashing, which shows much more performance than conventional methods. With the rise of deep learning [9], many powerful yet efficient neuron network architectures have been proposed [10], [11], [12], [13], [14] and rapidly incorporated into deep hashing [15], [16], [17], [18], [19]. As a result, deep hashing can encode compact binary codes representing complex, high-level features.…”

Section: Introductionmentioning

confidence: 99%

RelaHash: Deep Hashing With Relative Position

et al. 2023

View full text Add to dashboard Cite

Deep hashing has been widely used as a solution to encoding binary hash code for approximating nearest neighbor problem. It has been showing superior performance in terms of its ability to index high-level features by learning compact binary code. Many recent state-of-the-art deep hashing methods often use multiple loss terms at once, thus introducing optimization difficulty and may result in sub-optimal hash codes. OrthoHash [1] was proposed to replace those losses with just a single loss function. However, the quantization error minimization problem in OrthoHash is still not addressed effectively. In this paper, we take one step further -propose a single-loss model that can effectively minimize the quantization error without explicit loss terms. Specifically, we introduce a new way to measure the similarity between the relaxed codes with centroids, called relative similarity. The relative similarity is the similarity between the relative position representation of continuous codes and the normalized centroids. The resulting model outperforms many state-of-the-art deep hashing models on popular benchmark datasets.

show abstract

“…It employs a hierarchical Windows mechanism as a feature extractor [27], which can support higher resolution image processing tasks [28] and deeper deep learning network architectures. Compared with the traditional vision transformer (VIT) network, Swin transformer performs better in tasks such as image perception and classification [29,30], so it has great potential to be applied to the fault diagnosis of motor equipment.…”

Section: Introductionmentioning

confidence: 99%

A fault diagnosis method for motor vibration signals incorporating Swin transformer with locally sensitive hash attention

Zeng,

Ren,

2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

Identification of motor vibration signals is one of the important tasks in motor fault diagnosis and predictive maintenance, and wavelet time-frequency diagram is a commonly used signal analysis method to extract the frequency and time characteristics of signals. In this paper, a method based on LSH-Swin Transformer network is proposed for identifying the wavelet time-frequency diagrams of motor vibration signals to analyze the fault types.The traditional Swin Transformer model is difficult to improve the accuracy due to the smoothing of the attention distribution when dealing with data with sparse features, while the method proposed in this paper reduces the smoothing of the computed attention and enables the network to learn the key features better by introducing locally-sensitive hash attention in the network model, dividing the sequences in the input attention into multiple hash buckets, calculating the attention weights of only some of the vectors with a high degree of hash similarity, and by sampling discrete samples with the use of the Gumbel Softmax. The experimental results show that the method proposed in this paper has better recognition accuracy and higher computational efficiency compared with the traditional network when processing wavelet time-frequency maps of motor vibration signals, and its validation accuracy reaches 99.7%, the number of parameters also has a decrease of about 10%, and the training network to reach converged epochs is also faster. The method in this paper can provide an effective solution for the analysis and processing of motor vibration signals, and has certain application value in practical engineering.

show abstract

Swin transformer-based supervised hashing

Cited by 9 publications

References 32 publications

Event Cameras in Automotive Sensing: A Review

Event Cameras in Automotive Sensing: A Review

RelaHash: Deep Hashing With Relative Position

A fault diagnosis method for motor vibration signals incorporating Swin transformer with locally sensitive hash attention

Contact Info

Product

Resources

About