paper-with-me

Papers

Hierarchical Neural Collapse Detection Transformer for Class Incremental Object Detection

2025-06-10 · Duc Thanh Pham, Hong Dang Nguyen, Nhat Minh Nguyen Quoc, Linh Ngo Van, Sang Dinh Viet, Duc Anh Nguyen

Recently, object detection models have witnessed notable performance improvements, particularly with transformer-based models. However, new objects frequently appear in the real world, requiring detection models to continually learn without suffering from catastrophic forgetting. Although Incremental Object Detection (IOD) has emerged to address this challenge, these existing models are still not practical due to their limited performance and prolonged inference time. In this paper, we introduce a novel framework for IOD, called Hier-DETR: Hierarchical Neural Collapse Detection Transformer, ensuring both efficiency and competitive performance by leveraging Neural Collapse for imbalance dataset and Hierarchical relation of classes' labels.

📄 PDF Abstract BibTeX arXiv:2506.08562

Code (0)

등록된 구현이 없습니다.

Tasks

Class-Incremental Object DetectionObjectobject-detectionObject Detection

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Position-Wise Feed-Forward Layer 설명 없음
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Adam 설명 없음
Attention 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…

Similar Papers 제목 키워드 기반

Beyond Point-wise Neural Collapse: A Topology-Aware Hierarchical Classifier for Class-Incremental Learning

2026-05-12 · Huiyu Yi, Zhiming Xu, Dunwei Tu, Zhicheng Wang 외 arxiv

The Nearest Class Mean (NCM) classifier is widely favored in Class-Incremental Learning (CIL) for its superior resistance to catastrophic forgetting compared to Fully Connected layers. While Neural Collapse (NC) theory s…

class-incremental learning

Hierarchical Vector Quantized Transformer for Multi-class Unsupervised Anomaly Detection

2023-10-22 · NeurIPS 2023 11 · Ruiying Lu, Yujie Wu, Long Tian, Dongsheng Wang 외

Unsupervised image Anomaly Detection (UAD) aims to learn robust and discriminative representations of normal samples. While separate solutions per class endow expensive computation and limited generalizability, this pape…

Anomaly DetectionMulti-class Anomaly DetectionQuantizationUnsupervised Anomaly Detection

Neural Collapse Terminus: A Unified Solution for Class Incremental Learning and Its Variants

2023-08-03 · Yibo Yang, Haobo Yuan, Xiangtai Li, Jianlong Wu 외

How to enable learnability for new classes while keeping the capability well on old classes has been a crucial challenge for class incremental learning. Beyond the normal case, long-tail class incremental learning and fe…

class-incremental learningClass Incremental LearningFew-Shot Class-Incremental LearningIncremental Learning

Neural Collapse Inspired Feature-Classifier Alignment for Few-Shot Class Incremental Learning

2023-02-06 · Yibo Yang, Haobo Yuan, Xiangtai Li, Zhouchen Lin 외

Few-shot class-incremental learning (FSCIL) has been a challenging problem as only a few training samples are accessible for each novel class in the new sessions. Finetuning the backbone or adjusting the classifier proto…

class-incremental learningClass Incremental LearningFew-Shot Class-Incremental LearningIncremental Learning

Neural Collapse Inspired Feature-Classifier Alignment for Few-Shot Class-Incremental Learning

2023-02-02 · ICLR 2023 2 · Yibo Yang, Haobo Yuan, Xiangtai Li, Zhouchen Lin 외

Few-shot class-incremental learning (FSCIL) has been a challenging problem as only a few training samples are accessible for each novel class in the new sessions. Finetuning the backbone or adjusting the classifier proto…

class-incremental learningClass Incremental LearningFew-Shot Class-Incremental LearningIncremental Learning