Sequentially Generated Instance-Dependent Image Representations for Classification
In this paper, we investigate a new framework for image classification that adaptively generates spatial representations. Our strategy is based on a sequential process that learns to explore the different regions of any image in order to infer its category. In particular, the choice of regions is specific to each image, directed by the actual content of previously selected regions.The capacity of the system to handle incomplete image information as well as its adaptive region selection allow the system to perform well in budgeted classification tasks by exploiting a dynamicly generated representation of each image. We demonstrate the system's abilities in a series of image-based exploration and classification tasks that highlight its learned exploration and inference abilities.
Code (0)
등록된 구현이 없습니다.
Tasks
ClassificationGeneral Classificationimage-classificationImage ClassificationSimilar Papers 제목 키워드 기반
Recurrent Instance Segmentation
Instance segmentation is the problem of detecting and delineating each distinct object of interest appearing in an image. Current instance segmentation approaches consist of ensembles of modules that are trained independ…
Instance SegmentationOcclusion HandlingPlant PhenotypingSegmentation+1Recurrent Neural Networks for Semantic Instance Segmentation
We present a recurrent model for semantic instance segmentation that sequentially generates binary masks and their associated class probabilities for every object in an image. Our proposed system is trainable end-to-end …
Instance SegmentationObjectSegmentationSemantic SegmentationInstance-aware Image and Sentence Matching with Selective Multimodal LSTM
Effective image and sentence matching depends on how to well measure their global visual-semantic similarity. Based on the observation that such a global similarity arises from a complex aggregation of multiple local sim…
Semantic SimilaritySemantic Textual SimilaritySentenceTask-Independent Knowledge Makes for Transferable Representations for Generalized Zero-Shot Learning
Generalized Zero-Shot Learning (GZSL) targets recognizing new categories by learning transferable image representations. Existing methods find that, by aligning image representations with corresponding semantic labels, t…
Contrastive LearningGeneralized Zero-Shot LearningZero-Shot LearningAutomated Learning of Semantic Embedding Representations for Diffusion Models
Generative models capture the true distribution of data, yielding semantically rich representations. Denoising diffusion models (DDMs) exhibit superior generative capabilities, though efficient representation learning fo…
DenoisingRepresentation Learning