Sihan Chen

Yichen Yan, Xingjian He, Wenxuan Wang et al.

Referring image segmentation (RIS) aims to segment an object mentioned in natural language from an image. The main challenge is text-to-pixel fine-grained correlation. In the previous methods, the final results are obtained by convolutions with a fixed kernel, which follows a similar pattern as traditional image segmentation. These methods lack explicit alignment of language and vision features in the segmentation stage, resulting in suboptimal correlation. In this paper, we introduce EAVL, a method explicitly aligning vision and language features. In contrast to fixed convolution kernels, we introduce a Vision-Language Aligner that aligns features in the segmentation stage using dynamic convolution kernels based on the input image and sentence. Specifically, we generate multiple queries representing different emphases of language expression. These queries are transformed into a series of query-based convolution kernels, which are applied in the segmentation stage to produce a series of masks. The final result is obtained by aggregating all masks. Our method harnesses the potential of the multi-modal features in the segmentation stage and aligns language features of different emphases with image features to achieve fine-grained text-to-pixel correlation. We surpass previous state-of-the-art methods on RefCOCO, RefCOCO+, and G-Ref by large margins. Additionally, our method is designed to be a generic plug-and-play module for cross-modality alignment in RIS task, making it easy to integrate with other RIS models for substantial performance improvements.

Yanyuan Qiao, Zheng Yu, Longteng Guo et al.

Multimodal large language models (MLLMs) have attracted widespread interest and have rich applications. However, the inherent attention mechanism in its Transformer structure requires quadratic complexity and results in expensive computational overhead. Therefore, in this work, we propose VL-Mamba, a multimodal large language model based on state space models, which have been shown to have great potential for long-sequence modeling with fast inference and linear scaling in sequence length. Specifically, we first replace the transformer-based backbone language model such as LLama or Vicuna with the pre-trained Mamba language model. Then, we empirically explore how to effectively apply the 2D vision selective scan mechanism for multimodal learning and the combinations of different vision encoders and variants of pretrained Mamba language models. The extensive experiments on diverse multimodal benchmarks with competitive performance show the effectiveness of our proposed VL-Mamba and demonstrate the great potential of applying state space models for multimodal learning tasks.