Contrastive Learning through Auxiliary Branch for Video Object Detection

• URL: http://arxiv.org/abs/2508.20551v1
• Date: Thu, 28 Aug 2025 08:43:03 GMT
• Title: Contrastive Learning through Auxiliary Branch for Video Object Detection
• Abstract summary: We introduce a Contrastive Learning through Auxiliary Branch (CLAB) method to improve robustness to image degradation without additional computational load during inference.<n>CLAB reaches a performance of 84.0% mAP and 85.2% mAP with ResNet-101 and ResNeXt-101, respectively, on the ImageNet VID dataset.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Video object detection is a challenging task because videos often suffer from image deterioration such as motion blur, occlusion, and deformable shapes, making it significantly more difficult than detecting objects in still images. Prior approaches have improved video object detection performance by employing feature aggregation and complex post-processing techniques, though at the cost of increased computational demands. To improve robustness to image degradation without additional computational load during inference, we introduce a straightforward yet effective Contrastive Learning through Auxiliary Branch (CLAB) method. First, we implement a constrastive auxiliary branch using a contrastive loss to enhance the feature representation capability of the video object detector's backbone. Next, we propose a dynamic loss weighting strategy that emphasizes auxiliary feature learning early in training while gradually prioritizing the detection task as training converges. We validate our approach through comprehensive experiments and ablation studies, demonstrating consistent performance gains. Without bells and whistles, CLAB reaches a performance of 84.0% mAP and 85.2% mAP with ResNet-101 and ResNeXt-101, respectively, on the ImageNet VID dataset, thus achieving state-of-the-art performance for CNN-based models without requiring additional post-processing methods.

Related papers

• Search and Detect: Training-Free Long Tail Object Detection via Web-Image Retrieval [46.944526377710346]
  We introduce SearchDet, a training-free long-tail object detection framework. Our proposed method is simple and training-free, yet achieves over 48.7% mAP improvement on ODinW and 59.1% mAP improvement on LVIS.
  arXiv  Detail & Related papers  (2024-09-26T05:14:19Z)
• Rethinking Image-to-Video Adaptation: An Object-centric Perspective [61.833533295978484]
  We propose a novel and efficient image-to-video adaptation strategy from the object-centric perspective. Inspired by human perception, we integrate a proxy task of object discovery into image-to-video transfer learning.
  arXiv  Detail & Related papers  (2024-07-09T13:58:10Z)
• Video Dynamics Prior: An Internal Learning Approach for Robust Video Enhancements [83.5820690348833]
  We present a framework for low-level vision tasks that does not require any external training data corpus. Our approach learns neural modules by optimizing over a corrupted sequence, leveraging the weights of the coherence-temporal test and statistics internal statistics.
  arXiv  Detail & Related papers  (2023-12-13T01:57:11Z)
• Unified Perception: Efficient Depth-Aware Video Panoptic Segmentation with Minimal Annotation Costs [2.7920304852537536]
  We present a new approach titled Unified Perception that achieves state-of-the-art performance without requiring video-based training. Our method employs a simple two-stage cascaded tracking algorithm that (re)uses object embeddings computed in an image-based network.
  arXiv  Detail & Related papers  (2023-03-03T15:00:12Z)
• Video Salient Object Detection via Contrastive Features and Attention Modules [106.33219760012048]
  We propose a network with attention modules to learn contrastive features for video salient object detection. A co-attention formulation is utilized to combine the low-level and high-level features. We show that the proposed method requires less computation, and performs favorably against the state-of-the-art approaches.
  arXiv  Detail & Related papers  (2021-11-03T17:40:32Z)
• Adaptive Remote Sensing Image Attribute Learning for Active Object Detection [43.029857143916345]
  This paper takes adaptive brightness adjustment and scale adjustment as examples, and proposes an active object detection method based on deep reinforcement learning. The goal of adaptive image attribute learning is to maximize the detection performance.
  arXiv  Detail & Related papers  (2021-01-16T11:37:50Z)
• Progressive Self-Guided Loss for Salient Object Detection [102.35488902433896]
  We present a progressive self-guided loss function to facilitate deep learning-based salient object detection in images. Our framework takes advantage of adaptively aggregated multi-scale features to locate and detect salient objects effectively.
  arXiv  Detail & Related papers  (2021-01-07T07:33:38Z)
• Robust and efficient post-processing for video object detection [9.669942356088377]
  This work introduces a novel post-processing pipeline that overcomes some of the limitations of previous post-processing methods. Our method improves the results of state-of-the-art specific video detectors, specially regarding fast moving objects. And applied to efficient still image detectors, such as YOLO, provides comparable results to much more computationally intensive detectors.
  arXiv  Detail & Related papers  (2020-09-23T10:47:24Z)
• Auto-Rectify Network for Unsupervised Indoor Depth Estimation [119.82412041164372]
  We establish that the complex ego-motions exhibited in handheld settings are a critical obstacle for learning depth. We propose a data pre-processing method that rectifies training images by removing their relative rotations for effective learning. Our results outperform the previous unsupervised SOTA method by a large margin on the challenging NYUv2 dataset.
  arXiv  Detail & Related papers  (2020-06-04T08:59:17Z)
• One-Shot Object Detection without Fine-Tuning [62.39210447209698]
  We introduce a two-stage model consisting of a first stage Matching-FCOS network and a second stage Structure-Aware Relation Module. We also propose novel training strategies that effectively improve detection performance. Our method exceeds the state-of-the-art one-shot performance consistently on multiple datasets.
  arXiv  Detail & Related papers  (2020-05-08T01:59:23Z)

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.