A solution to generalized learning from small training sets found in infant repeated visual experiences of individual objects
One-year-old infants rapidly form and generalize categories of the everyday objects they encounter. Here we provide evidence on infants daily-life visual experiences for 8 early-learned object categories. Using a corpus of infant head-camera images recorded at mealtimes (87 mealtimes captured by 14 infants), we measure the frequency of the unique instances of each category and the variability of the visual experiences of each instance. The distribution of instances is highly skewed, containing, for each infant and category, many images of the same few objects along with fewer images of other instances. Graph theoretic measures of the similarity structure for individual categories reveal a lumpy mix of high similarity and high variability, organized into multiple but interconnected clusters of high-similarity images. In computational experiments, we show that artificially-created training sets characterized by a lumpy distribution of similarities support generalization to novel instances after very few training experiences. We discuss implications for visual object recognition, and for learning more generally, by both humans and machines.
Code (0)
등록된 구현이 없습니다.
Tasks
Object RecognitionSimilar Papers 제목 키워드 기반
One ticket to win them all: generalizing lottery ticket initializations across datasets and optimizers
The success of lottery ticket initializations (Frankle and Carbin, 2019) suggests that small, sparsified networks can be trained so long as the network is initialized appropriately. Unfortunately, finding these "winning …
AllGlobal Sum Pooling: A Generalization Trick for Object Counting with Small Datasets of Large Images
In this paper, we explore the problem of training one-look regression models for counting objects in datasets comprising a small number of high-resolution, variable-shaped images. We illustrate that conventional global a…
Crowd CountingObject CountingThe topology of large Open Connectome networks for the human brain
The structural human connectome (i.e.\ the network of fiber connections in the brain) can be analyzed at ever finer spatial resolution thanks to advances in neuroimaging. Here we analyze several large data sets for the h…
Model SelectionTolerance Principle and Small Language Model Learning
Modern language models like GPT-3, BERT, and LLaMA require massive training data, yet with sufficient training they reliably learn to distinguish grammatical from ungrammatical sentences. Children aged as young as 14 mon…
Hi-gMISnet: generalized medical image segmentation using DWT based multilayer fusion and dual mode attention into high resolution pGAN
Objective. Automatic medical image segmentation is crucial for accurately isolating target tissue areas in the image from background tissues, facilitating precise diagnoses and procedures. While the proliferation of publ…
Generative Adversarial NetworkImage SegmentationMedical Image SegmentationSegmentation+2