PR] One paper has been accepted

2023/06/27 03:18
1 more property
One paper has been accepted to Pattern Recognition (IF 8.518).
Title: ENInst: Enhancing Weakly-supervised Low-shot Instance Segmentation [Paper][arXiv]
Authors: Moon Ye-Bin (POSTECH), Dongmin Choi (KAIST), Yongjin Kwon (ETRI), Junsik Kim (Harvard University), Tae-Hyun Oh (POSTECH)
We address a weakly-supervised low-shot instance segmentation, an annotation-efficient training method to deal with novel classes effectively. Since it is an under-explored problem, we first investigate the difficulty of the problem and identify the performance bottleneck by conducting systematic analyses of model components and individual sub-tasks with a simple baseline model. Based on the analyses, we propose ENInst with sub-task enhancement methods: instance-wise mask refinement for enhancing pixel localization quality and novel classifier composition for improving classification accuracy. Our proposed method lifts the overall performance by enhancing the performance of each sub-task. We demonstrate that our ENInst is 7.5 times more efficient in achieving comparable performance to the existing fully-supervised few-shot models and even outperforms them at times.
Illustration of our ENInst (left) and the proposed enhancement methods developed by our analysis (right). 1) We train the whole network in the base training phase (gray region), 2) fine-tune the prediction heads (blue region), where the classification head for novel classes is parameterized by a linear combination of base classifiers and random vectors, named as the novel classifier composition (NCC; pink region), and its coefficients are fine-tuned with Manifold Mixup (Verma et al., 2019), 3) and then conduct inference with instance-wise mask refinement (IMR; yellow region) in a test-time optimization manner.
Label efficiency of ENInst on MS-COCO (Lin et al., 2014). Our ENInst needs much fewer clicks to achieve similar performance to fully-supervised MTFA (Ganea et al., 2021), where F denotes fully-supervised setting with mask, and W denotes weak one with bounding box for novel classes adaption.