Jinfeng Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Jinfeng Zhang has a total of 3 co-authors. Here are the top co-authors by number of shared publications:
- Tianpeng Liu
National university of defense technology, Changsha, China
2 shared publications - Jiehua Zhang
College of Electronic Science and Technology, National University of Defense Technology (NUDT), Changsha, China
1 shared publication - Li Liu
National University of Defense Technology (NUDT)
1 shared publication
Latest Publications
- Open Access
- 11 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-5
BA-ViT: Bound-Aware Quantized Vision Transformers for ORSI Salient Object Detection
- 11 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-5
Open AccessBA-ViT: Bound-Aware Quantized Vision Transformers for ORSI Salient Object Detection
- 18 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 22 (1545598X) , 1-5
TS-BiT: Two-Stage Binary Transformer for ORSI Salient Object Detection
Vision Transformers (ViTs) have demonstrated superior performance in various remote sensing tasks, such as Optical Remote Sensing Images Salient Object Detection (ORSI-SOD). However, the high resolution of remote sensing images and the substantial computational costs pose significant challenges for deploying existing methods on resource-constrained devices. Model binarization significantly reduces computational costs and storage requirements by constraining weights and activations to 1-bit representations, which has been widely explored in Convolutional Neural Networks (CNNs). However, directly applying binary methods to ViTs poses challenges since quantization errors hinder the ability to capture the similarity between tokens, resulting in significant performance degradation in detecting salient objects in complex ORSI scenarios. To address this issue, we propose TS-BiT for the ORSI-SOD task to preserve information of salient objects under 1-bit representation. Specifically, we design a two-stage central-aware softmax binarization strategy (TCSB) to reduce quantization errors arising from substantial discrepancies in the long-tail distribution of multi-head attention. Furthermore, we develop a scalable hyperbolic tangent function to approximate the gradients of the Sign function within each binarization group, substantially mitigating quantization errors during the binarization of softmax attention. Extensive experiments demonstrate that our method outperforms existing binary ViT approaches on ORSSD, EORSSD, and ORSI-4199 datasets.
- 18 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 22 (1545598X) , 1-5
TS-BiT: Two-Stage Binary Transformer for ORSI Salient Object Detection
Vision Transformers (ViTs) have demonstrated superior performance in various remote sensing tasks, such as Optical Remote Sensing Images Salient Object Detection (ORSI-SOD). However, the high resolution of remote sensing images and the substantial computational costs pose significant challenges for deploying existing methods on resource-constrained devices. Model binarization significantly reduces computational costs and storage requirements by constraining weights and activations to 1-bit representations, which has been widely explored in Convolutional Neural Networks (CNNs). However, directly applying binary methods to ViTs poses challenges since quantization errors hinder the ability to capture the similarity between tokens, resulting in significant performance degradation in detecting salient objects in complex ORSI scenarios. To address this issue, we propose TS-BiT for the ORSI-SOD task to preserve information of salient objects under 1-bit representation. Specifically, we design a two-stage central-aware softmax binarization strategy (TCSB) to reduce quantization errors arising from substantial discrepancies in the long-tail distribution of multi-head attention. Furthermore, we develop a scalable hyperbolic tangent function to approximate the gradients of the Sign function within each binarization group, substantially mitigating quantization errors during the binarization of softmax attention. Extensive experiments demonstrate that our method outperforms existing binary ViT approaches on ORSSD, EORSSD, and ORSI-4199 datasets.