Dynamic Feature Fusion for Semantic Edge Detection
Authors: Yuan Hu, Yunpeng Chen, Xiang Li, Jiashi Feng
IJCAI 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We show that our model with the novel dynamic feature fusion is superior to fixed weight fusion and also the na ıve location-invariant weight fusion methods, via comprehensive experiments on benchmarks Cityscapes and SBD. In particular, our method outperforms all existing well established methods and achieves new state-of-the-art. |
| Researcher Affiliation | Academia | Yuan Hu1,2 , Yunpeng Chen3 , Xiang Li1,2 and Jiashi Feng3 1Institute of Remote Sensing and Digital Earth, CAS, Beijing 100094, China 2University of Chinese Academy of Sciences, Beijing 100049, China 3National University of Singapore |
| Pseudocode | No | No explicit pseudocode or algorithm blocks (e.g., labeled 'Algorithm' or 'Pseudocode') are present in the paper. |
| Open Source Code | No | 1Codes will be released soon. |
| Open Datasets | Yes | We evaluate our proposed method on two popular benchmarks for semantic edge detection: Cityscapes [Cordts et al., 2016] and SBD [Hariharan et al., 2011]. |
| Dataset Splits | Yes | During training, we use random mirroring and random cropping on both Cityscapes and SBD. During testing, the images with original image size are used for Cityscapes and the images are padded to 512 x 512 for SBD. We compare the proposed DFF model with state-of-the-arts on SBD validation set in Table 4. |
| Hardware Specification | Yes | All experiments are performed using 4 NVIDIA TITAN Xp(12GB) GPUs with synchronized batch normalization [Zhang et al., 2018]. |
| Software Dependencies | No | The paper mentions 'Py Torch [Paszke et al., 2017]' but does not provide a specific version number for it or any other software dependencies. |
| Experiment Setup | Yes | We set the base learning rate to 0.08 and 0.05 for Cityscapes and SBD respectively; the poly policy is used for learning rate decay. The crop size, batch size, training epoch, momentum, weight decay are set to 640 640 / 352 352, 8 / 16, 200 / 10, 0.9, 1e 4 for Cityscapes and SBD respectively. |