SegMix: Co-occurrence Driven Mixup for Semantic Segmentation and Adversarial Robustness
In this paper, we present a strategy for training convolutional neural networks to effectively resolve interference arising from competing hypotheses relating to inter-categorical information throughout the network. The premise is based on the notion of feature binding, which is defined as the process by which activations spread across space and layers in the network are successfully integrated to arrive at a correct inference decision. In our work, this is accomplished for the task of dense image labelling by blending images based on (i) categorical clustering or (ii) the co-occurrence likelihood of categories. We then train a feature binding network which simultaneously segments and separates the blended images. Subsequent feature denoising to suppress noisy activations reveals additional desirable properties and high degrees of successful predictions. Through this process, we reveal a general mechanism, distinct from any prior methods, for boosting the performance of the base segmentation and saliency network while simultaneously increasing robustness to adversarial attacks.
Code (0)
등록된 구현이 없습니다.
Tasks
Adversarial RobustnessDenoisingSemantic SegmentationSimilar Papers 제목 키워드 기반
SegMix: A Simple Structure-Aware Data Augmentation Method
Interpolation-based Data Augmentation (DA) methods (Mixup) linearly interpolate the inputs and labels of two or more training examples. Mixup has more recently been adapted to the field of Natural Language Processing (NL…
Data Augmentationnamed-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)+2SegMix: A Simple Structure-Aware Data Augmentation Method
Many Natural Language Processing tasks involve predicting structures, such as Syntax Parsing and Relation Extraction (RE). One central challenge in supervised structured prediction is the lack of high-quality annotated d…
Data Augmentationnamed-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)+3USegMix: Unsupervised Segment Mix for Efficient Data Augmentation in Pathology Images
In computational pathology, researchers often face challenges due to the scarcity of labeled pathology datasets. Data augmentation emerges as a crucial technique to mitigate this limitation. In this study, we introduce a…
Cancer ClassificationData AugmentationSuperpixelsLabel-Occurrence-Balanced Mixup for Long-tailed Recognition
Mixup is a popular data augmentation method, with many variants subsequently proposed. These methods mainly create new examples via convex combination of random data pairs and their corresponding one-hot labels. However,…
Data AugmentationSegMix:Shuffle-based Feedback Learning for Semantic Segmentation of Pathology Images
Segmentation is a critical task in computational pathology, as it identifies areas affected by disease or abnormal growth and is essential for diagnosis and treatment. However, acquiring high-quality pixel-level supervis…
Semantic Segmentation