English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Transformer-based object detectors (DETR) have shown significant performanceacross machine vision tasks, ultimately in object detection. This detector isbased on a self-attention mechanism along with the transformer encoder-decoderarchitecture to capture the global context in the image. The critical issue tobe addressed is how this model architecture can handle different imagenuisances, such as occlusion and adversarial perturbations. We studied thisissue by measuring the performance of DETR with different experiments andbenchmarking the network with convolutional neural network (CNN) baseddetectors like YOLO and Faster-RCNN. We found that DETR performs well when itcomes to resistance to interference from information loss in occlusion images.Despite that, we found that the adversarial stickers put on the image requirethe network to produce a new unnecessary set of keys, queries, and values,which in most cases, results in a misdirection of the network. DETR alsoperformed poorer than YOLOv5 in the image corruption benchmark. Furthermore, wefound that DETR depends heavily on the main query when making a prediction,which leads to imbalanced contributions between queries since the main queryreceives most of the gradient flow.

Investigating the Robustness and Properties of Detection Transformers (DETR) Toward Difficult Images