In interactive instance segmentation, users give feedback to iteratively refine segmentation masks. The user-provided clicks are transformed into guidance maps which provide the network with necessary cues on the whereabouts of the object of interest. Guidance maps used in current systems are purely distance-based and are either too localized or non-informative. We propose a novel transformation of user clicks to generate scale-aware guidance maps that leverage the hierarchical structural information present in an image. Using our guidance maps, even the most basic FCNs are able to outperform existing approaches that require state-of-the-art segmentation networks pre-trained on large scale segmentation datasets. We demonstrate the effectiveness of our proposed transformation strategy through comprehensive experimentation in which we significantly raise state-of-the-art on four standard interactive segmentation benchmarks.

No abstract

Segmenting objects of interest in an image is an essential building block of applications such as photo-editing and image analysis. Under interactive settings, one should achieve good segmentations while minimizing user input. Current deep learning-based interactive segmentation approaches use early fusion and incorporate user cues at the image input layer. Since segmentation CNNs have many layers, early fusion may weaken the influence of user interactions on the final prediction results. As such, we propose a new multi-stage guidance framework for interactive segmentation. By incorporating user cues at different stages of the network, we allow user interactions to impact the final segmentation output in a more direct way. Our proposed framework has a negligible increase in parameter count compared to early-fusion frameworks. We perform extensive experimentation on the standard interactive instance segmentation and one-click segmentation benchmarks and report state-of-the-art performance.

Spectral imaging technique plays a very vital role in the field of chemical detection and identification. Conventional spectroscopic imaging techniques suffer from massive acquisition time. This limitation sometimes restricts it from many practical applications. The acquisition of a full spectral image requires huge acquisition time. In this Letter, a compressive sensing‐based single‐pixel camera architecture has been realised to acquire spectral images that can be used for non‐destructive testing and classification of explosive materials. The compressive measurements for all the spectral images are done simultaneously thus reducing the acquisition time significantly. The spectro‐spatial images were reconstructed using the basis pursuit algorithm and compared with least square solutions, which resulted in fast acquisition and improved image quality. The maximum compression rate achieved was 95.84%.

No abstract