paper-with-me

홈 › Papers

A Simple-but-effective Baseline for Training-free Class-Agnostic Counting

2024-03-03 · YuHao Lin, HaiMing Xu, Lingqiao Liu, Javen Qinfeng Shi

Class-Agnostic Counting (CAC) seeks to accurately count objects in a given image with only a few reference examples. While previous methods achieving this relied on additional training, recent efforts have shown that it's possible to accomplish this without training by utilizing pre-existing foundation models, particularly the Segment Anything Model (SAM), for counting via instance-level segmentation. Although promising, current training-free methods still lag behind their training-based counterparts in terms of performance. In this research, we present a straightforward training-free solution that effectively bridges this performance gap, serving as a strong baseline. The primary contribution of our work lies in the discovery of four key technologies that can enhance performance. Specifically, we suggest employing a superpixel algorithm to generate more precise initial point prompts, utilizing an image encoder with richer semantic knowledge to replace the SAM encoder for representing candidate objects, and adopting a multiscale mechanism and a transductive prototype scheme to update the representation of reference examples. By combining these four technologies, our approach achieves significant improvements over existing training-free methods and delivers performance on par with training-based ones.

📄 PDF Abstract BibTeX arXiv:2403.01418

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

SAM 설명 없음

Similar Papers 제목 키워드 기반

A Simple Baseline that Questions the Use of Pretrained-Models in Continual Learning

2022-10-10 · Paul Janson, Wenxuan Zhang, Rahaf Aljundi, Mohamed Elhoseiny

With the success of pretraining techniques in representation learning, a number of continual learning methods based on pretrained models have been proposed. Some of these methods design continual learning mechanisms on t…

Continual LearningExemplar-FreeRepresentation Learning

SuS-X: Training-Free Name-Only Transfer of Vision-Language Models

2022-11-28 · ICCV 2023 1 · Vishaal Udandarao, Ankush Gupta, Samuel Albanie

Contrastive Language-Image Pre-training (CLIP) has emerged as a simple yet effective way to train large-scale vision-language models. CLIP demonstrates impressive zero-shot classification and retrieval on diverse downstr…

Retrievalzero-shot-classificationZero-Shot Learning

RELOCATE: A Simple Training-Free Baseline for Visual Query Localization Using Region-Based Representations

2024-12-02 · CVPR 2025 1 · Savya Khosla, Sethuraman T V, Alexander Schwing, Derek Hoiem

We present RELOCATE, a simple training-free baseline designed to perform the challenging task of visual query localization in long videos. To eliminate the need for task-specific training and efficiently handle long vide…

Object Localization

Learning with Free Object Segments for Long-Tailed Instance Segmentation

2022-02-22 · Cheng Zhang, Tai-Yu Pan, Tianle Chen, Jike Zhong 외

One fundamental challenge in building an instance segmentation model for a large number of classes in complex scenes is the lack of training examples, especially for rare objects. In this paper, we explore the possibilit…

Instance SegmentationObjectSemantic Segmentation

Molecular Topological Profile (MOLTOP) - Simple and Strong Baseline for Molecular Graph Classification

2024-10-17 · European Conference on Artificial Intelligence (ECAI) 2024 2024 10 · Jakub Adamczyk, Wojciech Czech

We revisit the effectiveness of topological descriptors for molecular graph classification and design a simple, yet strong baseline. We demonstrate that a simple approach to feature engineering - employing histogram aggr…

Feature EngineeringGraph Classification