Few-shot semantic segmentation (FSS) aims to segment novel classes with only a few annotated samples. Existing methods to FSS generally combine the annotated mask and the corresponding support image to generate the class-specific representation, and perform the segmentation for the query image by matching the features of the query image to these representations. However, the segmentation performance could be fragile for the lack of an effective method to handle the inappropriate use of query features and the neglection of correlation between features in support and query images. In this work, we propose a novel Disentanglement and Recombination Network (DRNet) to alleviate this problem. Concretely, we first apply the self-attention on both support foreground features and query foreground features. Then, the foreground features of the support and query branches are recombined using the cross-attention after self-attention computation, which can encourage the foreground feature alignment between branches. Finally, the prototypes are generated from the recombined foreground features and support background features, and are utilized to guide the segmentation for given images. Considering the sensitivity of prototypes related to the subtle differences among objects from different classes and the same class, we further introduce a joint learning strategy to derive accurate segmentation of both seen and unseen objects in the support image and the query image respectively. Extensive experiments on the PASCAL-5 ⁱ and COCO-20 ⁱ datasets demonstrate the superiority of our DRNet comparing with the recent popular methods. The code is released on https://github.com/GS-Chang-Hn/DRNet-fss.

The ever-increasing demands for intuitive interactions in virtual reality have led to surging interests in facial expression recognition (FER). There are however several issues commonly seen in existing methods, including narrow receptive fields and homogenous supervisory signals. To address these issues, we propose in this paper a novel multimodal supervision-steering transformer for facial expression recognition in the wild, referred to as FER-former. Specifically, to address the limitation of narrow receptive fields, a hybrid feature extraction pipeline is designed by cascading both prevailing CNNs and transformers. To deal with the issue of homogenous supervisory signals, a heterogeneous domain-steering supervision module is proposed to incorporate text-space semantic correlations to enhance image features, based on the similarity between image and text features. Additionally, a FER-specific transformer encoder is introduced to characterize conventional one-hot label-focusing and CLIP-based text-oriented tokens in parallel for final classification. Based on the collaboration of multifarious token heads, global receptive fields with multimodal semantic cues are captured, delivering superb learning capability. Extensive experiments on popular benchmarks demonstrate the superiority of the proposed FER-former over the existing state-of-the-art methods. Our code will be released at this https URL.