REVIEW 2 cited by
ICPC: Instance-Conditioned Prompting with Contrastive Learning for Semantic Segmentation
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
Modern supervised semantic segmentation methods are usually finetuned based on the supervised or self-supervised models pre-trained on ImageNet. Recent work shows that transferring the knowledge from CLIP to semantic segmentation via prompt learning can achieve promising performance. The performance boost comes from the feature enhancement with multimodal alignment, i.e., the dot product between vision and text embeddings. However, how to improve the multimodal alignment for better transfer performance in dense tasks remains underexplored. In this work, we focus on improving the quality of vision-text alignment from two aspects of prompting design and loss function, and present an instance-conditioned prompting with contrastive learning (ICPC) framework. First, compared with the static prompt designs, we reveal that dynamic prompting conditioned on image content can more efficiently utilize the text encoder for complex dense tasks. Second, we propose an align-guided contrastive loss to refine the alignment of vision and text embeddings. We further propose lightweight multi-scale alignment for better performance. Extensive experiments on three large-scale datasets (ADE20K, COCO-Stuff10k, and ADE20K-Full) demonstrate that ICPC brings consistent improvements across diverse backbones. Taking ResNet-50 as an example, ICPC outperforms the state-of-the-art counterpart by 1.71%, 1.05%, and 1.41% mIoU on the three datasets, respectively.
Forward citations
Cited by 2 Pith papers
-
BEVCon: Advancing Bird's Eye View Perception with Contrastive Learning
A contrastive learning framework with instance-level and perspective-level losses consistently improves multiple BEV detection models on nuScenes by up to 2.4 mAP.
-
Achieving Precise and Reliable Locomotion with Differentiable Simulation-Based System Identification
Estimating robot dynamics parameters from trajectory data alone inside a differentiable simulator, inside the reinforcement learning loop, is claimed to improve trajectory following in bipedal locomotion.
Discussion (0). Continue with ORCID to comment.