Masked Cross-image Encoding for Few-shot Segmentation
It addresses the problem of dense prediction with limited labeled data for computer vision researchers, offering an incremental improvement over prior methods that ignored cross-image dependencies.
The paper tackles few-shot segmentation by proposing Masked Cross-Image Encoding (MCE) to capture common visual properties and bidirectional dependencies between support and query images, achieving state-of-the-art results on PASCAL-5^i and COCO-20^i benchmarks.
Few-shot segmentation (FSS) is a dense prediction task that aims to infer the pixel-wise labels of unseen classes using only a limited number of annotated images. The key challenge in FSS is to classify the labels of query pixels using class prototypes learned from the few labeled support exemplars. Prior approaches to FSS have typically focused on learning class-wise descriptors independently from support images, thereby ignoring the rich contextual information and mutual dependencies among support-query features. To address this limitation, we propose a joint learning method termed Masked Cross-Image Encoding (MCE), which is designed to capture common visual properties that describe object details and to learn bidirectional inter-image dependencies that enhance feature interaction. MCE is more than a visual representation enrichment module; it also considers cross-image mutual dependencies and implicit guidance. Experiments on FSS benchmarks PASCAL-$5^i$ and COCO-$20^i$ demonstrate the advanced meta-learning ability of the proposed method.