Ev-TTA: Test-Time Adaptation for Event-Based Object Recognition

Kim, Junho; Hwang, Inwoo; Kim, Young Min

doi:10.1109/cvpr52688.2022.01722

Cited by 16 publications

(3 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This method offers advantages over traditional frame-based classification techniques due to its high temporal resolution and low latency. In the domain of object recognition, researchers have developed approaches that leverage the temporal nature of event streams to efficiently detect and classify objects in dynamic scenes [7][8][9] . From other perspectives, object classification methods in event-based vision can be categorized into asynchronous events-based and event-frame based approaches 1 .…”

Section: Event-based Classificationmentioning

confidence: 99%

Language-guided Object Classification Via Neuromorphic Vision

Huang,

Sajwani,

Hay

et al. 2024

Preprint

View full text Add to dashboard Cite

Through training on large-scale image-text pairs, vision-language models (VLMs) have gained the ability to align visual information with semantic understanding using natural language, thus leading to better performance on downstream tasks on unseen data. Due to a lack of large-scale neuromorphic vision datasets that also include natural language, training with large-scale datasets to achieve generalized understanding is not feasible. Therefore, this work introduces a neuromorphic adapter neural network that leverages CLIP-based semantic understanding with neuromorphic-inspired feature extraction, thereby enhancing the robustness and efficiency of object classification in real-world scenarios. Specifically, by incorporating the temporal information of neuromorphic vision and the multimodal strengths of CLIP, our approach excels in few-shot learning, effectively extending comprehension across object classification tasks. We evaluate our approach on three public datasets: N-Cars, N-Caltech, and N-ImageNet, yielding encouraging classification accuracy after few-shot learning compared to the state-of-the-art models. Moreover, compared to zero-shot inference, our approach achieves +9.92%, +33.65%, and +42.63% improvements under 1-shot, 15-shot, and 20-shot settings in classification accuracy, respectively. Consequently, it demonstrates the effectiveness of adapting pre-trained language-vision models for event data, enabling effective learning and inference even with limited annotated data.

show abstract

Section: Event-based Classificationmentioning

confidence: 99%

Language-guided Object Classification Via Neuromorphic Vision

Huang,

Sajwani,

Hay

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Test-time Domain Adaptation (TTDA) aims to adapt models on the target domain only in test time. It is firstly proposed in TTT [37] and has been applied to many fields such as instance tracking [9], object detections [16] and reinforcement learning [12]. The early works (TTT [37] and its extensions [20,22]) require an extra training process on source data, making it inapplicable when only the source model is available.…”

Section: Related Workmentioning

confidence: 99%

Dynamically Instance-Guided Adaptation: A Backward-free Approach for Test-Time Domain Adaptive Semantic Segmentation

Wang,

Zhong,

Wang

et al. 2023

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

encourage the model to capture robust representation. SAM combines the historical prototypes with instance-level prototypes to adjust semantic predictions, which can be associated with the parametric classifier to mutually benefit the final results. Extensive experiments evaluated on five target domains demonstrate the effectiveness and efficiency of the proposed method. Our DIGA establishes new state-of-theart performance in TTDA-Seg. Source code is available at: https://github.com/Waybaba/DIGA.

show abstract

“…Models trained on the simulated dataset generalize well on the real data. More recently, N-ImageNet [117] serves as the first It also deserves to adapt the model trained on synthetic data to realworld event data [140], [141]. Another research direction could focus on leveraging large amounts of unlabeled data or active learning, where the classifier can request additional labeled data as needed in order to improve its performance.…”

Section: Scene Understanding and 3d Visionmentioning

confidence: 99%

Pan‐risk factor for a comprehensive cardiovascular health management

Zheng

et al. 2022

Journal of Diabetes

View full text Add to dashboard Cite

Cardiovascular diseases (CVDs) have become the leading cause of death in China. CVDs are mainly caused by multiple well‐known modifiable risk factors that are affected by socioeconomic and environmental determinants, lifestyle and behavioral choices, and familial and genetic predispositions. With more risk factors proved to be associated with CVD occurrence, the concept “pan‐risk factor” is proposed in this review to indicate all discovered and yet‐to‐be‐discovered CVD risk factors for comprehensive primary prevention of CVD. Recognizing more factors and their roles in CVD development and progression is the first step in reducing the ever‐increasing burden of CVD. This review is an overview of the pan‐risk factor whose associations with CVD outcomes have been established. Along with the accumulation of scientific evidence, an increasing number of risk factors will be discovered and included in the list of pan‐risk factors.

show abstract

Ev-TTA: Test-Time Adaptation for Event-Based Object Recognition

Cited by 16 publications

References 22 publications

Language-guided Object Classification Via Neuromorphic Vision

Language-guided Object Classification Via Neuromorphic Vision

Dynamically Instance-Guided Adaptation: A Backward-free Approach for Test-Time Domain Adaptive Semantic Segmentation

Pan‐risk factor for a comprehensive cardiovascular health management

Contact Info

Product

Resources

About