VSCode: General Visual Salient and Camouflaged Object Detection with 2D Prompt Learning
This addresses the need for efficient and unified models in computer vision for object detection tasks, reducing redundancy and improving performance, though it is incremental as it builds on existing foundation models.
The paper tackles the problem of redundant task-specific models for salient and camouflaged object detection by introducing VSCode, a generalist model with 2D prompt learning, which outperforms state-of-the-art methods across six tasks on 26 datasets and shows zero-shot generalization to unseen tasks like RGB-D COD.
Salient object detection (SOD) and camouflaged object detection (COD) are related yet distinct binary mapping tasks. These tasks involve multiple modalities, sharing commonalities and unique cues. Existing research often employs intricate task-specific specialist models, potentially leading to redundancy and suboptimal results. We introduce VSCode, a generalist model with novel 2D prompt learning, to jointly address four SOD tasks and three COD tasks. We utilize VST as the foundation model and introduce 2D prompts within the encoder-decoder architecture to learn domain and task-specific knowledge on two separate dimensions. A prompt discrimination loss helps disentangle peculiarities to benefit model optimization. VSCode outperforms state-of-the-art methods across six tasks on 26 datasets and exhibits zero-shot generalization to unseen tasks by combining 2D prompts, such as RGB-D COD. Source code has been available at https://github.com/Sssssuperior/VSCode.