End-to-End Video Object Detection with Spatial-Temporal Transformers

Abstract

Recently, DETR and Deformable DETR have been proposed to eliminate the need for many hand-designed components in object detection while demonstrating good performance as previous complex hand-crafted detectors. However, their performance on Video Object Detection (VOD) has not been well explored. In this paper, we present TransVOD, an end-to-end video object detection model based on a spatial-temporal Transformer architecture. The goal of this paper is to streamline the pipeline of VOD, effectively removing the need for many hand-crafted components for feature aggregation, e.g., optical flow, recurrent neural networks, relation networks. Besides, benefited from the object query design in DETR, our method does not need complicated post-processing methods such as Seq-NMS or Tubelet rescoring, which keeps the pipeline simple and clean. In particular, we present temporal Transformer to aggregate both the spatial object queries and the feature memories of each frame. Our temporal Transformer consists of three components: Temporal Deformable Transformer Encoder (TDTE) to encode the multiple frame spatial details, Temporal Query Encoder (TQE) to fuse object queries, and Temporal Deformable Transformer Decoder to obtain current frame detection results. These designs boost the strong baseline deformable DETR by a significant margin (3%-4% mAP) on the ImageNet VID dataset. TransVOD yields comparable results performance on the benchmark of ImageNet VID. We hope our TransVOD can provide a new perspective for video object detection. Code will be made publicly available at https://github.com/SJTU-LuHe/TransVOD.

References in corpus (18)

• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• R-FCN: Object Detection via Region-based Fully Convolutional Networks
• Deformable DETR: Deformable Transformers for End-to-End Object Detection
• Focal Loss for Dense Object Detection
• T-CNN: Tubelets with Convolutional Neural Networks for Object Detection from Videos
• Deformable Convolutional Networks
• TransTrack: Multiple Object Tracking with Transformer
• Seq-NMS for Video Object Detection
• Flow-Guided Feature Aggregation for Video Object Detection
• Sparse R-CNN: End-to-End Object Detection with Learnable Proposals
• End-to-End Video Instance Segmentation with Transformers
• MAMBA: Multi-level Aggregation via Memory Bank for Video Object Detection
• Sequence Level Semantics Aggregation for Video Object Detection
• Dual Semantic Fusion Network for Video Object Detection
• Relation Distillation Networks for Video Object Detection
• Progressive Sparse Local Attention for Video object detection
• Object Detection in Video with Spatial-temporal Context Aggregation