Revisiting Image Reconstruction for Semi-supervised Semantic Segmentation

Autoencoding, which aims to reconstruct the input images through a bottleneck latent representation, is one of the classic feature representation learning strategies. While it has proven effective as an auxiliary task for semi-supervised learning, its popularity has waned with the advent of more sophisticated methods in recent years. In this paper, we revisit the idea of using image reconstruction as the auxiliary task and incorporate it with a modern semi-supervised semantic segmentation framework. Surprisingly, we discover that such an old idea in semi-supervised learning can produce results competitive with state-of-the-art semantic segmentation algorithms. By visualizing the intermediate layer activations of the image reconstruction module, we show that the feature map channels exhibit a strong correlation with semantic concepts. This observation explains why joint training with the reconstruction task proves beneficial for the segmentation task. Motivated by our observation, we further proposed a modification to the image reconstruction task, aiming to further disentangle the object clue from the background patterns. From experiment evaluation on various datasets, we show that using reconstruction as auxiliary loss can lead to consistent improvements in various datasets and methods. The proposed method can further lead to significant improvement in object-centric segmentation tasks.