Beyond Boxes: Mask-Guided Spatio-Temporal Feature Aggregation for Video Object Detection

• URL: http://arxiv.org/abs/2412.04915v1
• Date: Fri, 06 Dec 2024 10:12:10 GMT
• Title: Beyond Boxes: Mask-Guided Spatio-Temporal Feature Aggregation for Video Object Detection
• Authors: Khurram Azeem Hashmi, Talha Uddin Sheikh, Didier Stricker, Muhammad Zeshan Afzal,
• Abstract summary: We present FAIM, a new VOD method that enhances temporal Feature Aggregation by leveraging Instance Mask features. Using YOLOX as a base detector, FAIM achieves 87.9% mAP on the ImageNet VID dataset at 33 FPS on a single 2080Ti GPU.
• Score: 12.417754433715903
• License:
• Abstract: The primary challenge in Video Object Detection (VOD) is effectively exploiting temporal information to enhance object representations. Traditional strategies, such as aggregating region proposals, often suffer from feature variance due to the inclusion of background information. We introduce a novel instance mask-based feature aggregation approach, significantly refining this process and deepening the understanding of object dynamics across video frames. We present FAIM, a new VOD method that enhances temporal Feature Aggregation by leveraging Instance Mask features. In particular, we propose the lightweight Instance Feature Extraction Module (IFEM) to learn instance mask features and the Temporal Instance Classification Aggregation Module (TICAM) to aggregate instance mask and classification features across video frames. Using YOLOX as a base detector, FAIM achieves 87.9% mAP on the ImageNet VID dataset at 33 FPS on a single 2080Ti GPU, setting a new benchmark for the speed-accuracy trade-off. Additional experiments on multiple datasets validate that our approach is robust, method-agnostic, and effective in multi-object tracking, demonstrating its broader applicability to video understanding tasks.

Related papers

• Learning Motion and Temporal Cues for Unsupervised Video Object Segmentation [49.113131249753714]
  We propose an efficient algorithm, termed MTNet, which concurrently exploits motion and temporal cues. MTNet is devised by effectively merging appearance and motion features during the feature extraction process within encoders. We employ a cascade of decoders all feature levels across all feature levels to optimally exploit the derived features.
  arXiv  Detail & Related papers  (2025-01-14T03:15:46Z)
• Appearance-Based Refinement for Object-Centric Motion Segmentation [85.2426540999329]
  We introduce an appearance-based refinement method that leverages temporal consistency in video streams to correct inaccurate flow-based proposals. Our approach involves a sequence-level selection mechanism that identifies accurate flow-predicted masks as exemplars. Its performance is evaluated on multiple video segmentation benchmarks, including DAVIS, YouTube, SegTrackv2, and FBMS-59.
  arXiv  Detail & Related papers  (2023-12-18T18:59:51Z)
• BoxMask: Revisiting Bounding Box Supervision for Video Object Detection [11.255962936937744]
  We propose BoxMask, which learns discriminative representations by incorporating class-aware pixel-level information. The proposed module can be effortlessly integrated into any region-based detector to boost detection.
  arXiv  Detail & Related papers  (2022-10-12T08:25:27Z)
• DFA: Dynamic Feature Aggregation for Efficient Video Object Detection [15.897168900583774]
  We propose a vanilla dynamic aggregation module that adaptively selects the frames for feature enhancement. We extend the vanilla dynamic aggregation module to a more effective and reconfigurable deformable version. On the ImageNet VID benchmark, integrated with our proposed methods, FGFA and SELSA can improve the inference speed by 31% and 76% respectively.
  arXiv  Detail & Related papers  (2022-10-02T17:54:15Z)
• Video Mask Transfiner for High-Quality Video Instance Segmentation [102.50936366583106]
  Video Mask Transfiner (VMT) is capable of leveraging fine-grained high-resolution features thanks to a highly efficient video transformer structure. Based on our VMT architecture, we design an automated annotation refinement approach by iterative training and self-correction. We compare VMT with the most recent state-of-the-art methods on the HQ-YTVIS, as well as the Youtube-VIS, OVIS and BDD100K MOTS.
  arXiv  Detail & Related papers  (2022-07-28T11:13:37Z)
• Tag-Based Attention Guided Bottom-Up Approach for Video Instance Segmentation [83.13610762450703]
  Video instance is a fundamental computer vision task that deals with segmenting and tracking object instances across a video sequence. We introduce a simple end-to-end train bottomable-up approach to achieve instance mask predictions at the pixel-level granularity, instead of the typical region-proposals-based approach. Our method provides competitive results on YouTube-VIS and DAVIS-19 datasets, and has minimum run-time compared to other contemporary state-of-the-art performance methods.
  arXiv  Detail & Related papers  (2022-04-22T15:32:46Z)
• Human Instance Segmentation and Tracking via Data Association and Single-stage Detector [17.46922710432633]
  Human video instance segmentation plays an important role in computer understanding of human activities. Most current VIS methods are based on Mask-RCNN framework. We develop a new method for human video instance segmentation based on single-stage detector.
  arXiv  Detail & Related papers  (2022-03-31T11:36:09Z)
• Generating Masks from Boxes by Mining Spatio-Temporal Consistencies in Videos [159.02703673838639]
  We introduce a method for generating segmentation masks from per-frame bounding box annotations in videos. We use our resulting accurate masks for weakly supervised training of video object segmentation (VOS) networks. The additional data provides substantially better generalization performance leading to state-of-the-art results in both the VOS and more challenging tracking domain.
  arXiv  Detail & Related papers  (2021-01-06T18:56:24Z)
• PointINS: Point-based Instance Segmentation [117.38579097923052]
  Mask representation in instance segmentation with Point-of-Interest (PoI) features is challenging because learning a high-dimensional mask feature for each instance requires a heavy computing burden. We propose an instance-aware convolution, which decomposes this mask representation learning task into two tractable modules. Along with instance-aware convolution, we propose PointINS, a simple and practical instance segmentation approach.
  arXiv  Detail & Related papers  (2020-03-13T08:24:58Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.