Focusing on what to decode and what to train: Efficient Training with HOI Split Decoders and Specific Target Guided DeNoising

Recent one-stage transformer-based methods achieve notable gains in the Human-object Interaction Detection (HOI) task by leveraging the detection of DETR. However, the current methods redirect the detection target of the object decoder, and the box target is not explicitly separated from the query embeddings, which leads to long and hard training. Furthermore, matching the predicted HOI instances with the ground-truth is more challenging than object detection, simply adapting training strategies from the object detection makes the training more difficult. To clear the ambiguity between human and object detection and share the prediction burden, we propose a novel one-stage framework (SOV), which consists of a subject decoder, an object decoder, and a verb decoder. Moreover, we propose a novel Specific Target Guided (STG) DeNoising strategy, which leverages learnable object and verb label embeddings to guide the training and accelerates the training convergence. In addition, for the inference part, the label-specific information is directly fed into the decoders by initializing the query embeddings from the learnable label embeddings. Without additional features or prior language knowledge, our method (SOV-STG) achieves higher accuracy than the state-of-the-art method in one-third of training epochs. The code is available at \url{https://github.com/cjw2021/SOV-STG}.