SCASeg: Strip Cross-Attention for Efficient Semantic Segmentation

The Vision Transformer (ViT) has achieved notable success in computer vision, with its variants extensively validated across various downstream tasks, including semantic segmentation. However, designed as general-purpose visual encoders, ViT backbones often overlook the specific needs of task decoders, revealing opportunities to design decoders tailored to efficient semantic segmentation. This paper proposes Strip Cross-Attention (SCASeg), an innovative decoder head explicitly designed for semantic segmentation. Instead of relying on the simple conventional skip connections, we employ lateral connections between the encoder and decoder stages, using encoder features as Queries for the cross-attention modules. Additionally, we introduce a Cross-Layer Block that blends hierarchical feature maps from different encoder and decoder stages to create a unified representation for Keys and Values. To further boost computational efficiency, SCASeg compresses queries and keys into strip-like patterns to optimize memory usage and inference speed over the traditional vanilla cross-attention. Moreover, the Cross-Layer Block incorporates the local perceptual strengths of convolution, enabling SCASeg to capture both global and local context dependencies across multiple layers. This approach facilitates effective feature interaction at different scales, improving the overall performance. Experiments show that the adaptable decoder of SCASeg produces competitive performance across different setups, surpassing leading segmentation architectures on all benchmark datasets, including ADE20K, Cityscapes, COCO-Stuff 164k, and Pascal VOC2012, even under varying computational limitations.

VLMPC: Vision-Language Model Predictive Control for Robotic Manipulation

Although Model Predictive Control (MPC) can effectively predict the future states of a system and thus is widely used in robotic manipulation tasks, it does not have the capability of environmental perception, leading to the failure in some complex scenarios. To address this issue, we introduce Vision-Language Model Predictive Control (VLMPC), a robotic manipulation framework which takes advantage of the powerful perception capability of vision language model (VLM) and integrates it with MPC. Specifically, we propose a conditional action sampling module which takes as input a goal image or a language instruction and leverages VLM to sample a set of candidate action sequences. Then, a lightweight action-conditioned video prediction model is designed to generate a set of future frames conditioned on the candidate action sequences. VLMPC produces the optimal action sequence with the assistance of VLM through a hierarchical cost function that formulates both pixel-level and knowledge-level consistence between the current observation and the goal image. We demonstrate that VLMPC outperforms the state-of-the-art methods on public benchmarks. More importantly, our method showcases excellent performance in various real-world tasks of robotic manipulation. Code is available at~\url{https://github.com/PPjmchen/VLMPC}.

Nowhere to Go: Benchmarking Multi-robot Collaboration in Target Trapping Environment

Collaboration is one of the most important factors in multi-robot systems. Considering certain real-world applications and to further promote its development, we propose a new benchmark to evaluate multi-robot collaboration in Target Trapping Environment (T2E). In T2E, two kinds of robots (called captor robot and target robot) share the same space. The captors aim to catch the target collaboratively, while the target will try to escape from the trap. Both the trapping and escaping process can use the environment layout to help achieve the corresponding objective, which requires high collaboration between robots and the utilization of the environment. For the benchmark, we present and evaluate multiple learning-based baselines in T2E, and provide insights into regimes of multi-robot collaboration. We also make our benchmark publicly available and encourage researchers from related robotics disciplines to propose, evaluate, and compare their solutions in this benchmark. Our project is released at https://github.com/Dr-Xiaogaren/T2E.

HAM: Hierarchical Attention Model with High Performance for 3D Visual Grounding

This paper tackles an emerging and challenging vision-language task, namely 3D visual grounding on point clouds. Many recent works benefit from Transformer with the well-known attention mechanism, leading to a tremendous breakthrough for this task. However, we find that they realize the achievement by using various pre-training or multi-stage processing. To simplify the pipeline, we carefully investigate 3D visual grounding and summarize three fundamental problems about how to develop an end-to-end model with high performance for this task. To address these problems, we especially introduce a novel Hierarchical Attention Model (HAM), offering multi-granularity representation and efficient augmentation for both given texts and multi-modal visual inputs. Extensive experimental results demonstrate the superiority of our proposed HAM model. Specifically, HAM ranks first on the large-scale ScanRefer challenge, which outperforms all the existing methods by a significant margin. Codes will be released after acceptance.