BoxMask: Revisiting Bounding Box Supervision for Video Object Detection

10/12/2022
by   Khurram Azeem Hashmi, et al.
0

We present a new, simple yet effective approach to uplift video object detection. We observe that prior works operate on instance-level feature aggregation that imminently neglects the refined pixel-level representation, resulting in confusion among objects sharing similar appearance or motion characteristics. To address this limitation, we propose BoxMask, which effectively learns discriminative representations by incorporating class-aware pixel-level information. We simply consider bounding box-level annotations as a coarse mask for each object to supervise our method. The proposed module can be effortlessly integrated into any region-based detector to boost detection. Extensive experiments on ImageNet VID and EPIC KITCHENS datasets demonstrate consistent and significant improvement when we plug our BoxMask module into numerous recent state-of-the-art methods.

READ FULL TEXT

page 2

page 4

page 6

page 7

research
11/20/2020

Joint Representation of Temporal Image Sequences and Object Motion for Video Object Detection

In this paper, we propose a new video object detector (VoD) method refer...
research
03/15/2018

Pseudo Mask Augmented Object Detection

In this work, we present a novel and effective framework to facilitate o...
research
05/09/2022

Beyond Bounding Box: Multimodal Knowledge Learning for Object Detection

Multimodal supervision has achieved promising results in many visual lan...
research
04/27/2015

Mid-level Elements for Object Detection

Building on the success of recent discriminative mid-level elements, we ...
research
08/25/2021

Layer-wise Customized Weak Segmentation Block and AIoU Loss for Accurate Object Detection

The anchor-based detectors handle the problem of scale variation by buil...
research
03/26/2021

Few-Shot Learning for Video Object Detection in a Transfer-Learning Scheme

Different from static images, videos contain additional temporal and spa...
research
03/11/2008

Spatio-activity based object detection

We present the SAMMI lightweight object detection method which has a hig...

Please sign up or login with your details

Forgot password? Click here to reset