Sorry, you need to enable JavaScript to visit this website.

CROSS-LAYER AGGREGATION WITH TRANSFORMERS FOR MULTI-LABEL IMAGE CLASSIFICATION

Citation Author(s):
Submitted by:
Weibo Zhang
Last updated:
8 May 2022 - 11:17pm
Document Type:
Poster
Document Year:
2022
Event:
Presenters:
Weibo Zhang
Paper Code:
MLSP-12.6

Abstract

Multi-label image classification task aims to predict multiple object labels in a given image and faces the challenge of variable-sized objects. Limited by the size of CNN convolution kernels, existing CNN-based methods have difficulty
capturing global dependencies and effectively fusing multiple layers features, which is critical for this task. Recently, transformers have utilized multi-head attention to extract feature with long range dependencies. Inspired by this, this
paper proposes a Cross-layer Aggregation with Transformers (CAT) framework, which leverages transformers to capture the long range dependencies of CNN-based features with Long Range Dependencies module and aggregate the features layer by layer with Cross-Layer Fusion module. To make the framework efficient, a multi-head pre-max attention is designed to reduce the computation cost when fusing the high-resolution features of lower-layers. On two widely-used benchmarks (i.e., VOC2007 and MS-COCO), CAT provides a stable improvement over the baseline and produces a competitive performance.

up
0 users have voted:

Files

icassp poster A0 .pdf

(32)