Adaptive Region Pooling for Fine-Grained Representation Learning
Fine-grained recognition aims to discriminate the sub-categories of the images within one general category. It is fundamentally difficult due to the requirement to extract fine-grained features from subtle regions. Nonetheless, a Convolutional Neural Network typically applies strided operations to downsample the representation, which would excessively spoil the feature resolution and lead to a significant loss of fine-grained information. In this paper, we propose Adaptive Region Pooling (ARP): a novel downsampling algorithm that makes the network only focus on a smaller but more critical region, and simultaneously increase the resolution of sub-sampled feature. ARP owns a trade-off mechanism that allows users to actively balance the scale of receptive field and the granularity of feature. Also, without any learning-based parameters, ARP provides the network a stabler training process and an earlier convergence. Extensive experiments qualitatively and quantitatively validate the effectiveness and efficiency of the proposed pooling operation and show superior performance against the state-of-the-arts in both the tasks of image classification and image retrieval.
Code (0)
등록된 구현이 없습니다.
Tasks
image-classificationImage ClassificationImage RetrievalRepresentation LearningRetrievalSimilar Papers 제목 키워드 기반
PAPooling: Graph-based Position Adaptive Aggregation of Local Geometry in Point Clouds
Fine-grained geometry, captured by aggregation of point features in local regions, is crucial for object recognition and scene understanding in point clouds. Nevertheless, existing preeminent point cloud backbones usuall…
3D Shape Classificationgraph constructionObject RecognitionPosition+2DRAN: Detailed Region-Adaptive Normalization for Conditional Image Synthesis
In recent years, conditional image synthesis has attracted growing attention due to its controllability in the image generation process. Although recent works have achieved realistic results, most of them have difficulty…
Facial Makeup TransferImage GenerationStyle TransferTexture SynthesisPVAFN: Point-Voxel Attention Fusion Network with Multi-Pooling Enhancing for 3D Object Detection
The integration of point and voxel representations is becoming more common in LiDAR-based 3D object detection. However, this combination often struggles with capturing semantic information effectively. Moreover, relying …
3D Object DetectionObjectobject-detectionObject DetectionGlobal to Local: Topology-Preserving Adaptive Graph Pooling via Granular-Ball
Graph pooling aims to compress the graph, including both node embeddings and their underlying topological patterns, into a more compact representation. Previous works focus primarily on the overly fine-grained representa…
Graph ClassificationSpatial-Scale Aligned Network for Fine-Grained Recognition
Existing approaches for fine-grained visual recognition focus on learning marginal region-based representations while neglecting the spatial and scale misalignments, leading to inferior performance. In this paper, we pro…
Fine-Grained Visual Recognition