Fluid Dynamics-Inspired Network for Infrared Small Target Detection

Authors: Tianxiang Chen, Qi Chu, Bin Liu, Nenghai Yu

IJCAI 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experiments on IRSTD-1k and SIRST demonstrate that our method achieves SOTA performance in terms of evaluation metrics. Our method outperforms others on IRSTD-1k and SIRST in terms of evaluation metrics.
Researcher Affiliation Academia Tianxiang Chen , Qi Chu , Bin Liu and Nenghai Yu School of Cyber Science and Technology, University of Science and Technology of China, China
Pseudocode No The paper does not contain structured pseudocode or algorithm blocks.
Open Source Code No The paper does not provide any statement regarding the release of source code or a link to a code repository for the methodology described.
Open Datasets Yes We choose IRSTD-1k and SIRST as benchmarks. IRSTD-1k consists of 1,000 real infrared images of 512 512 in size, containing various kinds of small targets and scenes. SIRST contains 427 infrared images.
Dataset Splits No The paper mentions 'Training on SIRST and IRSTD-1k takes 600 epochs and 400 epochs respectively.' but does not explicitly state specific dataset splits for training, validation, and testing.
Hardware Specification Yes A Titan Xp GPU is used for training, with batch size set to 4.
Software Dependencies No The algorithm is implemented in Pytorch, with Adaptive Gradient (Ada Grad) as optimizer, initial learning rate set to 0.05 and weight decay coefficient to 0.0004. However, specific version numbers for PyTorch or other libraries are not provided.
Experiment Setup Yes The algorithm is implemented in Pytorch, with Adaptive Gradient (Ada Grad) as optimizer, initial learning rate set to 0.05 and weight decay coefficient to 0.0004. A Titan Xp GPU is used for training, with batch size set to 4. Training on SIRST and IRSTD-1k takes 600 epochs and 400 epochs respectively.