Current machine learning methods struggle to solve Bongard problems, which
are a type of IQ test that requires deriving an abstract "concept" from a set
of positive and negative "support" images, and then classifying whether or not
a new query image depicts the key concept. On Bongard-HOI, a benchmark for
natural-image Bongard problems, existing methods have only reached 66% accuracy
(where chance is 50%). Low accuracy is often attributed to neural nets' lack of
ability to find human-like symbolic rules. In this work, we point out that many
existing methods are forfeiting accuracy due to a much simpler problem: they do
not incorporate information contained in the support set as a whole, and rely
instead on information extracted from individual supports. This is a critical
issue, because unlike in few-shot learning tasks concerning object
classification, the "key concept" in a typical Bongard problem can only be
distinguished using multiple positives and multiple negatives. We explore a
variety of simple methods to take this cross-image context into account, and
demonstrate substantial gains over prior methods, leading to new
state-of-the-art performance on Bongard-LOGO (75.3%) and Bongard-HOI (72.45%)
and strong performance on the original Bongard problem set (60.84%).

现有的机器学习方法在解决博加德问题方面存在困难，不仅是因为神经网络缺乏人类化的符号规则找寻能力，更因为许多方法仅仅依靠从个体支持集中提取的信息而未整合整个支持集所包含的信息，而我们探索了多种简单的方法来考虑这种跨图像的上下文，并展示了相较之前的方法有着显著提高的结果，在博加德 - LOGO（75.3%）和博加德 - HOI（72.45%）上达到了新的最先进表现，并在原始博加德问题集上表现出强大的性能（60.84%）。