paper-with-me

홈 › Papers

Tendency-driven Mutual Exclusivity for Weakly Supervised Incremental Semantic Segmentation

2024-04-18 · Chongjie Si, Xuehui Wang, Xiaokang Yang, Wei Shen

Weakly Incremental Learning for Semantic Segmentation (WILSS) leverages a pre-trained segmentation model to segment new classes using cost-effective and readily available image-level labels. A prevailing way to solve WILSS is the generation of seed areas for each new class, serving as a form of pixel-level supervision. However, a scenario usually arises where a pixel is concurrently predicted as an old class by the pre-trained segmentation model and a new class by the seed areas. Such a scenario becomes particularly problematic in WILSS, as the lack of pixel-level annotations on new classes makes it intractable to ascertain whether the pixel pertains to the new class or not. To surmount this issue, we propose an innovative, tendency-driven relationship of mutual exclusivity, meticulously tailored to govern the behavior of the seed areas and the predictions generated by the pre-trained segmentation model. This relationship stipulates that predictions for the new and old classes must not conflict whilst prioritizing the preservation of predictions for the old classes, which not only addresses the conflicting prediction issue but also effectively mitigates the inherent challenge of incremental learning - catastrophic forgetting. Furthermore, under the auspices of this tendency-driven mutual exclusivity relationship, we generate pseudo masks for the new classes, allowing for concurrent execution with model parameter updating via the resolution of a bi-level optimization problem. Extensive experiments substantiate the effectiveness of our framework, resulting in the establishment of new benchmarks and paving the way for further research in this field.

📄 PDF Abstract BibTeX arXiv:2404.11981

Code (0)

등록된 구현이 없습니다.

Tasks

Incremental LearningSegmentationSemantic Segmentation

Similar Papers 제목 키워드 기반

Deep daxes: Mutual exclusivity arises through both learning biases and pragmatic strategies in neural networks

2020-04-08 · Kristina Gulordava, Thomas Brochhagen, Gemma Boleda

Children's tendency to associate novel words with novel referents has been taken to reflect a bias toward mutual exclusivity. This tendency may be advantageous both as (1) an ad-hoc referent selection heuristic to single…

Mutual Exclusivity Training and Primitive Augmentation to Induce Compositionality

2022-11-28 · Yichen Jiang, Xiang Zhou, Mohit Bansal

Recent datasets expose the lack of the systematic generalization ability in standard sequence-to-sequence models. In this work, we analyze this behavior of seq2seq models and identify two contributing factors: a lack of …

Data AugmentationInductive BiasSystematic Generalization

Mutual exclusivity as a challenge for deep neural networks

2019-06-24 · NeurIPS 2020 12 · Kanishk Gandhi, Brenden M. Lake

Strong inductive biases allow children to learn in fast and adaptable ways. Children use the mutual exclusivity (ME) bias to help disambiguate how words map to referents, assuming that if an object has one label then it …

Lifelong learningMachine TranslationObject RecognitionTranslation

BeWith: A Between-Within Method to Discover Relationships between Cancer Modules via Integrated Analysis of Mutual Exclusivity, Co-occurrence and Functional Interactions

2017-04-28

The analysis of the mutational landscape of cancer, including mutual exclusivity and co-occurrence of mutations, has been instrumental in studying the disease. We hypothesized that exploring the interplay between co-occu…

Low-shot Object Learning with Mutual Exclusivity Bias

2023-12-06 · NeurIPS 2023 11 · Anh Thai, Ahmad Humayun, Stefan Stojanov, Zixuan Huang 외

This paper introduces Low-shot Object Learning with Mutual Exclusivity Bias (LSME), the first computational framing of mutual exclusivity bias, a phenomenon commonly observed in infants during word learning. We provide a…

Object