paper-with-me

홈 › Papers

CoMBO: Conflict Mitigation via Branched Optimization for Class Incremental Segmentation

2025-01-01 · CVPR 2025 1 · Kai Fang, Anqi Zhang, Guangyu Gao, Jianbo Jiao, Chi Harold Liu, Yunchao Wei

Effective Class Incremental Segmentation (CIS) requires simultaneously mitigating catastrophic forgetting and ensuring sufficient plasticity to integrate new classes. The inherent conflict above often leads to a back-and-forth, which turns the objective into finding the balance between the performance of previous (old) and incremental (new) classes. To address this conflict, we introduce a novel approach, Conflict Mitigation via Branched Optimization (CoMBO). Within this approach, we present the Query Conflict Reduction module, designed to explicitly refine queries for new classes through lightweight, class-specific adapters. This module provides an additional branch for the acquisition of new classes while preserving the original queries for distillation. Moreover, we develop two strategies to further mitigate the conflict following the branched structure, i.e., the Half-Learning Half-Distillation (HDHL) over classification probabilities, and the Importance-Based Knowledge Distillation (IKD) over query features. HDHL selectively engages in learning for classification probabilities of queries that match the ground truth of new classes, while aligning unmatched ones to the corresponding old probabilities, thus ensuring retention of old knowledge while absorbing new classes via learning negative samples. Meanwhile, IKD assesses the importance of queries based on their matching degree to old classes, prioritizing the distillation of important features and allowing less critical features to evolve. Extensive experiments in Class Incremental Panoptic and Semantic Segmentation settings have demonstrated the superior performance of CoMBO. Project page: https://guangyu-ryan.github.io/CoMBO.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Knowledge DistillationSemantic Segmentation

Methods 이 논문이 사용한 방법론

Knowledge Distillation A very simple way to improve the performance of almost any machine learning algorithm is to train many different models on the same data and then to average their predictions.…

Similar Papers 제목 키워드 기반

DriveCombo: Benchmarking Compositional Traffic Rule Reasoning in Autonomous Driving

2026-03-02 · Enhui Ma, Jiahuan Zhang, Guantian Zheng, Tao Tang 외 arxiv

Multimodal Large Language Models (MLLMs) are rapidly becoming the intelligence brain of end-to-end autonomous driving systems. A key challenge is to assess whether MLLMs can truly understand and follow complex real-world…

Traffic Sign RecognitionAutonomous DrivingScene GenerationVisual Reasoning

Merging Generated and Retrieved Knowledge for Open-Domain QA

2023-10-22 · Yunxiang Zhang, Muhammad Khalifa, Lajanugen Logeswaran, Moontae Lee 외

Open-domain question answering (QA) systems are often built with retrieval modules. However, retrieving passages from a given source is known to suffer from insufficient knowledge coverage. Alternatively, prompting large…

DecoderOpen-Domain Question AnsweringQuestion AnsweringRetrieval

Combinatorial Bayesian Optimization using the Graph Cartesian Product

2019-02-01 · NeurIPS 2019 12 · Changyong Oh, Jakub M. Tomczak, Efstratios Gavves, Max Welling

This paper focuses on Bayesian Optimization (BO) for objectives on combinatorial search spaces, including ordinal and categorical variables. Despite the abundance of potential applications of Combinatorial BO, including …

Bayesian OptimizationNeural Architecture SearchVariable Selection

Recon: Reducing Conflicting Gradients from the Root for Multi-Task Learning

2023-02-22 · Guangyuan Shi, Qimai Li, Wenlong Zhang, Jiaxin Chen 외

A fundamental challenge for multi-task learning is that different tasks may conflict with each other when they are solved jointly, and a cause of this phenomenon is conflicting gradients during optimization. Recent works…

Multi-Task Learning

Combining Machine Learning Models using combo Library

2019-09-21 · Yue Zhao, Xuejian Wang, Cheng Cheng, Xueying Ding

Model combination, often regarded as a key sub-field of ensemble learning, has been widely used in both academic research and industry applications. To facilitate this process, we propose and implement an easy-to-use Pyt…

Anomaly DetectionBIG-bench Machine LearningClusteringEnsemble Learning