Using Feature Alignment Can Improve Clean Average Precision and Adversarial Robustness in Object Detection

2020-12-08 · Weipeng Xu, Hongcheng Huang, Shaoyou Pan

The 2D object detection in clean images has been a well studied topic, but its vulnerability against adversarial attack is still worrying. Existing work has improved robustness of object detectors by adversarial training, at the same time, the average precision (AP) on clean images drops significantly. In this paper, we propose that using feature alignment of intermediate layer can improve clean AP and robustness in object detection. Further, on the basis of adversarial training, we present two feature alignment modules: Knowledge-Distilled Feature Alignment (KDFA) module and Self-Supervised Feature Alignment (SSFA) module, which can guide the network to generate more effective features. We conduct extensive experiments on PASCAL VOC and MS-COCO datasets to verify the effectiveness of our proposed approach. The code of our experiments is available at https://github.com/grispeut/Feature-Alignment.git.

📄 PDF Abstract BibTeX arXiv:2012.04382

Code (1)

grispeut/Feature-Alignment 공식 구현 pytorch

Tasks

2D Object Detection Adversarial Attack Adversarial RobustnessObjectobject-detection Object Detection

Robust and Accurate Object Detection via Self-Knowledge Distillation

2021-11-14 · Weipeng Xu, Pengzhi Chu, Renhao Xie, Xiongziyan Xiao 외

Object detection has achieved promising performance on clean datasets, but how to achieve better tradeoff between the adversarial robustness and clean precision is still under-explored. Adversarial training is the mainst…

Adversarial Robustness Knowledge Distillation object-detection Object Detection+2

Tucker Bilinear Attention Network for Multi-scale Remote Sensing Object Detection

2023-03-09 · Tao Chen, Ruirui Li, Jiafeng Fu, Daguang Jiang

Object detection on VHR remote sensing images plays a vital role in applications such as urban planning, land resource management, and rescue missions. The large-scale variation of the remote-sensing targets is one of th…

Management Object object-detection Object Detection

English-Malay Cross-Lingual Embedding Alignment using Bilingual Lexicon Augmentation

2022-05-01 · ACL 2022 5 · Ying Hao Lim, Jasy Suet Yan Liew

As high-quality Malay language resources are still a scarcity, cross lingual word embeddings make it possible for richer English resources to be leveraged for downstream Malay text classification tasks. This paper focuse…

Cross-Lingual Word Embeddings Machine Translation text-classification Text Classification+1

EchoDistill:Alignment Noisy-to-Clean Self-Distillation for Robust Audio LLMs

2026-05-11 · Liang Lin, Chunxi Luo, Kaiwen Luo, Jie Zhang 외 arxiv

Audio Large Language Models (ALLMs) are highly vulnerable to real-world noise, which often induces severe semantic drift and hallucinations. Existing robustness methods primarily rely on waveform-level acoustic enhanceme…

Fusion of linguistic, neural and sentence-transformer features for improved term alignment

2022-06-01 · LREC (BUCC) 2022 6 · Andraz Repar, Senja Pollak, Matej Ulčar, Boshko Koloski

Crosslingual terminology alignment task has many practical applications. In this work, we propose an aligning method for the shared task of the 15th Workshop on Building and Using Comparable Corpora. Our method combines …

Sentence