Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in [1].
Activation Modulation and Recalibration Scheme for Weakly Supervised Semantic Segmentation
Authors: Jie Qin, Jie Wu, Xuefeng Xiao, Lujun Li, Xingang Wang2117-2125
AAAI 2022 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive experiments show that AMR establishes a new state-of-the-art performance on the PASCAL VOC 2012 dataset, surpassing not only current methods trained with the image-level of supervision but also some methods relying on stronger supervision, such as saliency label. Experiments also reveal that our scheme is plug-and-play and can be incorporated with other approaches to boost their performance. Our code is available at: https://github.com/jieqin-ai/AMR. |
| Researcher Affiliation | Collaboration | Jie Qin1,2,3*, Jie Wu2, Xuefeng Xiao2, Lujun Li3, Xingang Wang3 1 School of Arti๏ฌcial Intelligence, University of Chinese Academy of Sciences 2 Byte Dance Inc 3 Institute of Automation, Chinese Academy of Sciences |
| Pseudocode | No | The paper does not include any explicit pseudocode or algorithm blocks. |
| Open Source Code | Yes | Our code is available at: https://github.com/jieqin-ai/AMR. |
| Open Datasets | Yes | We evaluate our approach on the PASCAL VOC2012 dataset (Everingham et al. 2015). |
| Dataset Splits | Yes | Following the common methods (Wei et al. 2017; Wang et al. 2020b), we use 10,582 images for training, 1,449 images for validation, and 1,456 ones for testing. |
| Hardware Specification | No | The paper does not specify any particular hardware (e.g., GPU model, CPU type) used for running the experiments. |
| Software Dependencies | No | The paper mentions using ResNet50 and Deep Lab-v2 backbones, but does not list specific version numbers for software dependencies such as Python, PyTorch, or CUDA. |
| Experiment Setup | Yes | We train the network for 8 epochs with a batch size of 16. The initial learning rate is set to 0.01 with a momentum of 0.9. We leverage the stochastic gradient descent algorithm for network optimization with a 0.0001 weight decay. |