REVIEW 6 cited by
SPTNet: An Efficient Alternative Framework for Generalized Category Discovery with Spatial Prompt Tuning
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
SPTNet: An Efficient Alternative Framework for Generalized Category Discovery with Spatial Prompt Tuning
read the original abstract
Generalized Category Discovery (GCD) aims to classify unlabelled images from both `seen' and `unseen' classes by transferring knowledge from a set of labelled `seen' class images. A key theme in existing GCD approaches is adapting large-scale pre-trained models for the GCD task. An alternate perspective, however, is to adapt the data representation itself for better alignment with the pre-trained model. As such, in this paper, we introduce a two-stage adaptation approach termed SPTNet, which iteratively optimizes model parameters (i.e., model-finetuning) and data parameters (i.e., prompt learning). Furthermore, we propose a novel spatial prompt tuning method (SPT) which considers the spatial property of image data, enabling the method to better focus on object parts, which can transfer between seen and unseen classes. We thoroughly evaluate our SPTNet on standard benchmarks and demonstrate that our method outperforms existing GCD methods. Notably, we find our method achieves an average accuracy of 61.4% on the SSB, surpassing prior state-of-the-art methods by approximately 10%. The improvement is particularly remarkable as our method yields extra parameters amounting to only 0.117% of those in the backbone architecture. Project page: https://visual-ai.github.io/sptnet.
Forward citations
Cited by 6 Pith papers
-
Identifying Latent Concepts and Structures for Generalized Category Discovery
CPF-GCD enforces low-rank compositional structure on vision backbone features via spatial primitive fields so that novel categories emerge as new activation patterns over a shared vocabulary of reusable visual primitives.
-
PACO: Proxy-Task Alignment and Online Calibration for On-the-Fly Category Discovery
PACO provides a hierarchical online decision system with proxy-simulated initial thresholds and adaptive updates from mature prototypes to enable consistent category discovery in streaming sequences.
-
MedXplore: Towards Reliable and Unbiased Generalized Category Discovery in Medical Imaging
A frequency-based attention module plus adaptive margins raises generalized category discovery accuracy on four medical imaging benchmarks by an average of 8.5 points over prior methods.
-
DP-BOA: Dirichlet-Process Birth-or-Assign for On-the-Fly Category Discovery
DP-BOA replaces fixed match thresholds in on-the-fly category discovery with an online Dirichlet-process Gaussian mixture that compares posterior-predictive evidence for assigning a sample to an existing category vers...
-
SECOS: Semantic Capture for Rigorous Classification in Open-World Semi-Supervised Learning
SECOS enables direct semantic label prediction in open-world semi-supervised learning by aligning representations with external knowledge for novel classes, outperforming prior methods by up to 5.4% even without post-...
-
Sparsity Hurts: Simple Linear Adapter Can Boost Generalized Category Discovery
LAGCD inserts residual linear adapters into each ViT block plus a distribution alignment loss to improve generalized category discovery by increasing model flexibility while reducing bias between seen and novel classes.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.