Zero-shot counting with a dual-stream neural network model
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Object RecognitionZero-Shot CountingSimilar Papers 제목 키워드 기반
Enhancing Zero-shot Counting via Language-guided Exemplar Learning
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 LearningText-promptable Object Counting via Quantity Awareness Enhancement
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 CountingSAVE: Self-Attention on Visual Embedding for Zero-Shot Generic Object Counting
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 CountingCountCLIP -- [Re] Teaching CLIP to Count to Ten
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 LearningCLIP-Count: Towards Text-Guided Zero-Shot Object Counting
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