REVIEW 6 cited by
Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Although using convolutional neural networks (CNNs) as backbones achieves great successes in computer vision, this work investigates a simple backbone network useful for many dense prediction tasks without convolutions. Unlike the recently-proposed Transformer model (e.g., ViT) that is specially designed for image classification, we propose Pyramid Vision Transformer~(PVT), which overcomes the difficulties of porting Transformer to various dense prediction tasks. PVT has several merits compared to prior arts. (1) Different from ViT that typically has low-resolution outputs and high computational and memory cost, PVT can be not only trained on dense partitions of the image to achieve high output resolution, which is important for dense predictions but also using a progressive shrinking pyramid to reduce computations of large feature maps. (2) PVT inherits the advantages from both CNN and Transformer, making it a unified backbone in various vision tasks without convolutions by simply replacing CNN backbones. (3) We validate PVT by conducting extensive experiments, showing that it boosts the performance of many downstream tasks, e.g., object detection, semantic, and instance segmentation. For example, with a comparable number of parameters, RetinaNet+PVT achieves 40.4 AP on the COCO dataset, surpassing RetinNet+ResNet50 (36.3 AP) by 4.1 absolute AP. We hope PVT could serve as an alternative and useful backbone for pixel-level predictions and facilitate future researches. Code is available at https://github.com/whai362/PVT.
Forward citations
Cited by 6 Pith papers
-
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
Swin Transformer reaches 87.3% ImageNet accuracy and sets new records on COCO detection and ADE20K segmentation by replacing global self-attention with shifted-window local attention inside a hierarchical pyramid.
-
Modality-Agnostic Prompt Learning for Multi-Modal Camouflaged Object Detection
A framework uses modality-agnostic prompts to adapt SAM for multi-modal camouflaged object detection, with a mask refine module for better boundaries.
-
TimeProVe: Propose, then Verify for Efficient Long Video Temporal Reasoning in Activities of Daily Living
TimeProVe proposes a propose-then-verify framework using lightweight action-based candidate evidence generation followed by targeted VLM verification for efficient long video temporal reasoning, achieving 7.3% improve...
-
Deep Attention Reweighting: Post-Hoc Attention-Based Feature Aggregation in CNNs for Disentangling Core and Spurious Features under Spurious Correlations
DAR replaces GAP with an attention-based aggregation module retrained jointly with the classifier head to disentangle core from spurious features and outperforms DFR on multiple datasets.
-
Accuracy Improvement of Cell Image Segmentation Using Feedback Former
Feedback Former improves cell image segmentation accuracy by feeding detailed feature maps back from near the output to lower transformer layers, outperforming non-feedback baselines with lower computational cost on t...
-
Graph-Based Uncertainty Modeling and Multimodal Fusion for Salient Object Detection
DUP-MCRNet introduces dynamic uncertainty graph convolution and learnable multimodal gating, reporting SOD benchmark improvements that are weakened by evaluation mismatches and table errors.
Discussion (0). Sign in to comment.