Volumetric Transformer Networks
Existing techniques to encode spatial invariance within deep convolutional neural networks (CNNs) apply the same warping field to all the feature channels. This does not account for the fact that the individual feature channels can represent different semantic parts, which can undergo different spatial transformations w.r.t. a canonical configuration. To overcome this limitation, we introduce a learnable module, the volumetric transformer network (VTN), that predicts channel-wise warping fields so as to reconfigure intermediate CNN features spatially and channel-wisely. We design our VTN as an encoder-decoder network, with modules dedicated to letting the information flow across the feature channels, to account for the dependencies between the semantic parts. We further propose a loss function defined between the warped features of pairs of instances, which improves the localization ability of VTN. Our experiments show that VTN consistently boosts the features' representation power and consequently the networks' accuracy on fine-grained image recognition and instance-level image retrieval.
Code (0)
등록된 구현이 없습니다.
Tasks
DecoderFine-Grained Image RecognitionImage RetrievalRetrievalSimilar Papers 제목 키워드 기반
SuperFormer: Volumetric Transformer Architectures for MRI Super-Resolution
This paper presents a novel framework for processing volumetric medical information using Visual Transformers (ViTs). First, We extend the state-of-the-art Swin Transformer model to the 3D medical domain. Second, we prop…
Super-ResolutionVTP: Volumetric Transformer for Multi-view Multi-person 3D Pose Estimation
This paper presents Volumetric Transformer Pose estimator (VTP), the first 3D volumetric transformer framework for multi-view multi-person 3D human pose estimation. VTP aggregates features from 2D keypoints in all camera…
3D Human Pose Estimation3D Multi-Person Pose Estimation3D Pose EstimationPose Estimation3D UX-Net: A Large Kernel Volumetric ConvNet Modernizing Hierarchical Transformer for Medical Image Segmentation
The recent 3D medical ViTs (e.g., SwinUNETR) achieve the state-of-the-art performances on several 3D volumetric data benchmarks, including 3D medical image segmentation. Hierarchical transformers (e.g., Swin Transformers…
Image SegmentationMedical Image SegmentationSegmentationSemantic Segmentation+1Scaling Self-Supervised and Cross-Modal Pretraining for Volumetric CT Transformers
We introduce SPECTRE, a fully transformer-based foundation model for volumetric computed tomography (CT). Our Self-Supervised & Cross-Modal Pretraining for CT Representation Extraction (SPECTRE) approach utilizes scalabl…
Contrastive LearningVolDiT: Controllable Volumetric Medical Image Synthesis with Diffusion Transformers
Diffusion models have become a leading approach for high-fidelity medical image synthesis. However, most existing methods for 3D medical image generation rely on convolutional U-Net backbones within latent diffusion fram…
Medical Image Generation