Fairness Continual Learning Approach to Semantic Scene Understanding in Open-World Environments
Authors: Thanh-Dat Truong, Hoang-Quan Nguyen, Bhiksha Raj, Khoa Luu
NeurIPS 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Our proposed approach has achieved State-of-the-Art performance on three standard scene understanding benchmarks, i.e., ADE20K, Cityscapes, and Pascal VOC, and promoted the fairness of the segmentation model. In this section, we first describe the datasets and metrics used in our experiments. Then, we present the ablation studies to illustrate the effectiveness of our proposed method. Finally, we compare our approach with prior CSS methods to demonstrate our SOTA performance. |
| Researcher Affiliation | Academia | 1CVIU Lab, University of Arkansas, Fayetteville, AR, 72701 2Carnegie Mellon University, Pittsburgh, PA, 15213 3Mohammed bin Zayed University of AI, Abu Dhabi, UAE {tt032, hn016, khoaluu}@uark.edu, bhiksha@cs.cmu.edu |
| Pseudocode | Yes | Algorithm 1 in the supplementary illustrates an overview of computing the prototypical contrastive clustering loss while updating the class prototypes. |
| Open Source Code | No | The paper does not contain any explicit statement about making source code publicly available, nor does it provide a link to a code repository. |
| Open Datasets | Yes | ADE20K [49] is a semantic segmentation dataset that consists of more than 20K scene images of 150 semantic categories. Each image has been densely annotated with pix-level objects and objects parts labels. Cityscapes [10] is a real-world autonomous driving dataset collected in European. This dataset includes 3,975 urban images with high-quality, dense labels of 30 semantic categories. PASCAL VOC [13] is a common dataset that consists of more than 10K images of 20 classes. |
| Dataset Splits | Yes | Following [12], we focus on the overlapped CSS evaluation. Our proposed method is evaluated on several settings for each dataset, i.e., ADA20K 100-50 (2 steps), ADA20K 100-10 (6 steps), ADA20K 100-5 (11 steps), Cityscapes 11-5 (3 steps), Cityscapes 11-1 (11 steps), Cityscapes 1-1 (21 steps), Pascal VOC 15-1 (3 steps), and Pascal VOC 10-1 (11 steps). |
| Hardware Specification | No | The paper acknowledges 'the Arkansas High-Performance Computing Center for providing GPUs' but does not specify any particular GPU models, CPU types, memory amounts, or other detailed hardware specifications used for running the experiments. |
| Software Dependencies | No | The paper mentions using 'Deep Lab-V3' and 'Seg Former' with specific backbones but does not provide specific version numbers for any software dependencies, libraries, or frameworks used in the implementation or experimentation. |
| Experiment Setup | No | The paper states that 'Further details of our implementation will be available in our supplementary', but it does not provide specific experimental setup details such as hyperparameter values (e.g., learning rate, batch size, number of epochs) or optimizer settings within the main text. |