paper-with-me

Papers

Zero-shot counting with a dual-stream neural network model

2024-05-16 · Jessica A. F. Thompson, Hannah Sheahan, Tsvetomira Dumbalska, Julian Sandbrink, Manuela Piazza, Christopher Summerfield

Deep neural networks have provided a computational framework for understanding object recognition, grounded in the neurophysiology of the primate ventral stream, but fail to account for how we process relational aspects of a scene. For example, deep neural networks fail at problems that involve enumerating the number of elements in an array, a problem that in humans relies on parietal cortex. Here, we build a 'dual-stream' neural network model which, equipped with both dorsal and ventral streams, can generalise its counting ability to wholly novel items ('zero-shot' counting). In doing so, it forms spatial response fields and lognormal number codes that resemble those observed in macaque posterior parietal cortex. We use the dual-stream network to make successful predictions about behavioural studies of the human gaze during similar counting tasks.

📄 PDF Abstract BibTeX arXiv:2405.09953

Code (0)

등록된 구현이 없습니다.

Tasks

Object RecognitionZero-Shot Counting

Similar Papers 제목 키워드 기반

Enhancing Zero-shot Counting via Language-guided Exemplar Learning

2024-02-08 · Mingjie Wang, Jun Zhou, Yong Dai, Eric Buys 외

Recently, Class-Agnostic Counting (CAC) problem has garnered increasing attention owing to its intriguing generality and superior efficiency compared to Category-Specific Counting (CSC). This paper proposes a novel Expre…

Object CountingZero-Shot CountingZero-Shot Learning

Text-promptable Object Counting via Quantity Awareness Enhancement

2025-07-09 · Miaojing Shi, Xiaowen Zhang, Zijie Yue, Yong Luo 외 arxiv

Recent advances in large vision-language models (VLMs) have shown remarkable progress in solving the text-promptable object counting problem. Representative methods typically specify text prompts with object category inf…

Object Counting

SAVE: Self-Attention on Visual Embedding for Zero-Shot Generic Object Counting

2025-02-10 · journal 2025 2 · Ahmed Zgaren, Wassim Bouachir, Nizar Bouguila

Zero-shot counting is a subcategory of Generic Visual Object Counting, which aims to count objects from an arbitrary class in a given image. While few-shot counting relies on delivering exemplars to the model to count si…

Exemplar-Free CountingObjectObject CountingZero-Shot Counting

CountCLIP -- [Re] Teaching CLIP to Count to Ten

2024-06-05 · Harshvardhan Mestha, Tejas Agrawal, Karan Bania, Shreyas V 외

Large vision-language models (VLMs) are shown to learn rich joint image-text representations enabling high performances in relevant downstream tasks. However, they fail to showcase their quantitative understanding of obj…

zero-shot-classificationZero-Shot CountingZero-Shot Learning

CLIP-Count: Towards Text-Guided Zero-Shot Object Counting

2023-05-12 · Ruixiang Jiang, Lingbo Liu, Changwen Chen

Recent advances in visual-language models have shown remarkable zero-shot text-image matching ability that is transferable to downstream tasks such as object detection and segmentation. Adapting these models for object c…

Cross-Part Crowd CountingCross-Part EvaluationCrowd CountingObject+4