提出分层抽象机制让模型像人一样识别3D物体

Both humans and deep learning models can recognize objects from 3D shapes depicted with sparse visual information, such as a set of points randomly sampled from the surfaces of 3D objects (termed a point cloud). Although deep learning models achieve human-like performance in recognizing objects from 3D shapes, it remains unclear whether these models develop 3D shape representations similar to those used by human vision for object recognition. We hypothesize that training with 3D shapes enables models to form representations of local geometric structures in 3D shapes. However, their representations of global 3D object shapes may be limited. We conducted two human experiments systematically manipulating point density and object orientation (Experiment 1), and local geometric structure (Experiment 2). Humans consistently performed well across all experimental conditions. We compared two types of deep learning models, one based on a convolutional neural network (DGCNN) and the other on visual transformers (point transformer), with human performance. We found that the point transformer model provided a better account of human performance than the convolution-based model. The advantage mainly results from the mechanism in the point transformer model that supports hierarchical abstraction of 3D shapes.