Search Results for author:
Found 8 papers, 2 papers with code
S$^3$AD: Semi-supervised Small Apple Detection in Orchard Environments
However, crop detection, e. g., apple detection in orchard environments remains challenging due to a lack of large-scale datasets and the small relative size of the crops in the image.
High-Level Parallelism and Nested Features for Dynamic Inference Cost and Top-Down Attention
Our proposed topology also comes with a built-in top-down attention mechanism, which allows processing to be directly influenced by either enhancing or inhibiting category-specific high-level features, drawing parallels to the selective attention mechanism observed in human cognition.
Small, but important: Traffic light proposals for detecting small traffic lights and beyond
Traffic light detection is a challenging problem in the context of self-driving cars and driver assistance systems.
Segmenting Medical Instruments in Minimally Invasive Surgeries using AttentionMask
Our evaluation in an object proposal generation framework shows that our adapted AttentionMask system is robust to image degradations, generalizes well to unseen types of surgeries, and copes well with small instruments.
Localizing Small Apples in Complex Apple Orchard Environments
Since the apples are very small objects in such scenarios, we tackle this problem by adapting the object proposal generation system AttentionMask that focuses on small objects.
DeepFH Segmentations for Superpixel-based Object Proposal Refinement
Class-agnostic object proposal generation is an important first step in many object detection pipelines.
Superpixel-based Refinement for Object Proposal Generation
Precise segmentation of objects is an important problem in tasks like class-agnostic object proposal generation or instance segmentation.
AttentionMask: Attentive, Efficient Object Proposal Generation Focusing on Small Objects
We propose a novel approach for class-agnostic object proposal generation, which is efficient and especially well-suited to detect small objects.
