Ask the Image: Supervised Pooling to Preserve Feature Locality
In this paper we propose a weighted supervised pooling method for visual recognition systems. We combine a standard Spatial Pyramid Representation which is commonly adopted to encode spatial information, with an appropriate Feature Space Representation favoring semantic information in an appropriate feature space. For the latter, we propose a weighted pooling strategy exploiting data supervision to weigh each local descriptor coherently with its likelihood to belong to a given object class. The two representations are then combined adaptively with Multiple Kernel Learning. Experiments on common benchmarks (Caltech-256 and PASCAL VOC-2007) show that our image representation improves the current visual recognition pipeline and it is competitive with similar state-of-art pooling methods. We also evaluate our method on a real Human-Robot Interaction setting, where the pure Spatial Pyramid Representation does not provide sufficient discriminative power, obtaining a remarkable improvement.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Efficient Image Categorization with Sparse Fisher Vector
In object recognition, Fisher vector (FV) representation is one of the state-of-art image representations ways at the expense of dense, high dimensional features and increased computation time. A simplification of FV is …
Image CategorizationObject RecognitionA Graph Encoder-Decoder Network for Unsupervised Anomaly Detection
A key component of many graph neural networks (GNNs) is the pooling operation, which seeks to reduce the size of a graph while preserving important structural information. However, most existing graph pooling strategies …
Anomaly DetectionDecoderUnsupervised Anomaly DetectionLocality Matters for Training-Free Audio Token Compression in Audio-Language Models
Audio-language models (ALMs) are increasingly used for audio captioning, question answering, and open-ended audio understanding, but their inference cost remains high when audio inputs are represented as long prefix-toke…
Question AnsweringAudio captioningA Self-Supervised Gait Encoding Approach with Locality-Awareness for 3D Skeleton Based Person Re-Identification
Person re-identification (Re-ID) via gait features within 3D skeleton sequences is a newly-emerging topic with several advantages. Existing solutions either rely on hand-crafted descriptors or supervised gait representat…
Contrastive LearningPerson Re-IdentificationRepresentation LearningSelf-Supervised LearningSimPool: Towards Topology Based Graph Pooling with Structural Similarity Features
Deep learning methods for graphs have seen rapid progress in recent years with much focus awarded to generalising Convolutional Neural Networks (CNN) to graph data. CNNs are typically realised by alternating convolutiona…
Graph ClassificationGraph Neural Network