To miss-attend is to misalign! Residual Self-Attentive Feature Alignment for Adapting Object Detectors

Khindkar, Vaishnavi and Arora, Chetan and Balasubramanian, Vineeth N and Subramanian, Anbumani and Saluja, Rohit and Jawahar, C. V. (2022) To miss-attend is to misalign! Residual Self-Attentive Feature Alignment for Adapting Object Detectors. In: 22nd IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2022, 4 January 2022 through 8 January 2022, Waikoloa.

Text
Proceedings_2022_IEEE_CVF2.pdf - Published Version
Restricted to Registered users only
Download (1MB) | Request a copy

Abstract

Advancements in adaptive object detection can lead to tremendous improvements in applications like autonomous navigation, as they alleviate the distributional shifts along the detection pipeline. Prior works adopt adversarial learning to align image features at global and local levels, yet the instance-specific misalignment persists. Also, adaptive object detection remains challenging due to visual diversity in background scenes and intricate combinations of objects. Motivated by structural importance, we aim to attend prominent instance-specific regions, overcoming the feature misalignment issue. We propose a novel resIduaL seLf-attentive featUre alignMEnt (ILLUME) method for adaptive object detection. ILLUME comprises Self-Attention Feature Map (SAFM) module that enhances structural attention to object-related regions and thereby generates domain invariant features. Our approach significantly reduces the domain distance with the improved feature alignment of the instances. Qualitative results demonstrate the ability of ILLUME to attend important object instances required for alignment. Experimental results on several benchmark datasets show that our method outperforms the existing state-of-the-art approaches. © 2022 IEEE.

[error in script]

IITH Creators:

IITH Creators	ORCiD
Balasubramanian, Vineeth N	https://orcid.org/0000-0003-2656-0375

Item Type:

Conference or Workshop Item (Paper)

Additional Information:

This work was partly funded by IHub-Data at IIIT Hyderabad, and DST through the IMPRINT program.

Uncontrolled Keywords:

Adversarial Attack and Defense Methods; Adversarial Learning; Deep Learning; Few-shot; Object Detection/Recognition/Categorization; Semi- and Un- supervised Learning Deep Learning; Transfer; Vision Systems and Applications

Subjects:

Computer science

Divisions:

Department of Computer Science & Engineering

Depositing User:

. LibTrainee 2021

Date Deposited:

23 Jul 2022 08:15

Last Modified:

23 Jul 2022 08:15

URI:

http://raiithold.iith.ac.in/id/eprint/9884