paper-with-me

Papers

Sylph: A Hypernetwork Framework for Incremental Few-shot Object Detection

2022-03-25 · CVPR 2022 1 · Li Yin, Juan M Perez-Rua, Kevin J Liang

We study the challenging incremental few-shot object detection (iFSD) setting. Recently, hypernetwork-based approaches have been studied in the context of continuous and finetune-free iFSD with limited success. We take a closer look at important design choices of such methods, leading to several key improvements and resulting in a more accurate and flexible framework, which we call Sylph. In particular, we demonstrate the effectiveness of decoupling object classification from localization by leveraging a base detector that is pretrained for class-agnostic localization on a large-scale dataset. Contrary to what previous results have suggested, we show that with a carefully designed class-conditional hypernetwork, finetune-free iFSD can be highly effective, especially when a large number of base categories with abundant data are available for meta-training, almost approaching alternatives that undergo test-time-training. This result is even more significant considering its many practical advantages: (1) incrementally learning new classes in sequence without additional training, (2) detecting both novel and seen classes in a single pass, and (3) no forgetting of previously seen classes. We benchmark our model on both COCO and LVIS, reporting as high as 17% AP on the long-tail rare classes on LVIS, indicating the promise of hypernetwork-based iFSD.

📄 PDF Abstract BibTeX arXiv:2203.13903

Code (1)

facebookresearch/sylph-few-shot-detection 공식 구현 pytorch

Tasks

Few-Shot Object Detectionobject-detectionObject Detection

Methods 이 논문이 사용한 방법론

BASE 설명 없음

Similar Papers 제목 키워드 기반

Hypernetworks for Zero-shot Transfer in Reinforcement Learning

2022-11-28 · Sahand Rezaei-Shoshtari, Charlotte Morissette, Francois Robert Hogan, Gregory Dudek 외

In this paper, hypernetworks are trained to generate behaviors across a range of unseen task conditions, via a novel TD-based training objective and data from a set of near-optimal RL solutions for training tasks. This w…

continuous-controlContinuous Controlreinforcement-learningReinforcement Learning+2

HyperCLIP: Adapting Vision-Language models with Hypernetworks

2024-12-21 · Victor Akinwande, Mohammad Sadegh Norouzzadeh, Devin Willmott, Anna Bair 외

Self-supervised vision-language models trained with contrastive objectives form the basis of current state-of-the-art methods in AI vision tasks. The success of these models is a direct consequence of the huge web-scale …

HyperPlanes: Hypernetwork Approach to Rapid NeRF Adaptation

2024-02-02 · Paweł Batorski, Dawid Malarz, Marcin Przewięźlikowski, Marcin Mazur 외

Neural radiance fields (NeRFs) are a widely accepted standard for synthesizing new 3D object views from a small number of base images. However, NeRFs have limited generalization properties, which means that we need to us…

Few-Shot LearningNeRFObject

HyperShot: Few-Shot Learning by Kernel HyperNetworks

2022-03-21 · Marcin Sendera, Marcin Przewięźlikowski, Konrad Karanowski, Maciej Zięba 외

Few-shot models aim at making predictions using a minimal number of labeled examples from a given task. The main challenge in this area is the one-shot setting where only one element represents each class. We propose Hyp…

Few-Shot Image ClassificationFew-Shot Learning

SHIELD: Secure Hypernetworks for Incremental Expansion Learning Defense

2025-06-09 · Patryk Krukowski, Łukasz Gorczyca, Piotr Helm, Kamil Książek 외

Traditional deep neural networks suffer from several limitations, including catastrophic forgetting. When models are adapted to new datasets, they tend to quickly forget previously learned knowledge. Another significant …

Continual Learning