- Rating
- 3
- Confidence
- 2
- Informativeness
- 3
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper introduces the Test-Time Generalized Category Discovery (TT-GCD), which unifies test-time domain adaptation, known-class recognition, and unknown-class discovery, and proposes PACT(Prototype Assignment for Category discovery at Test time), which addresses this problem through confidence-weighted feature realignment and unified visual prototype assignment, achieving significant improvements on five benchmarks.
Critical strengths
A meaningful and practically relevant problem formulation. This paper defines a new, real-world task and introduces Test-Time Generalized Category Discovery (TT-GCD), which effectively addresses distribution shifts, known-class recognition, and new-class discovery under fully unsupervised test-time conditions. PACT combines lightweight, Layernorm-based feature realignment, unified visual prototype assignment, and online updates to provide a simple and effective solution for this challenging setting. The PACT method proposed in this paper has been extensively tested on five benchmarks, demonstrating significant performance improvements and clearly outperforming the current state-of-the-art TTA and GCD methods. With a processing time of just 128 samples per batch, it outperforms other comparison models in terms of both performance and efficiency.
Critical weaknesses
I am particularly interested in the implementation details and theoretical foundations of the paper. Equation (8) assigns samples to their nearest prototypes, whereas Equations (9)–(10) use different criteria to update known and novel prototypes. The paper does not clearly explain how samples with conflicting zero-shot predictions and prototype assignments are handled.
Questions for authors
Could the authors provide more detailed implementation information regarding the prototype assignment and update procedures in Equations (8)–(10)?
We thank the reviewer for the positive assessment. We are encouraged that the reviewer finds TT-GCD "a meaningful and practically relevant problem formulation", and PACT "a simple and effective solution for this challenging setting" that outperforms the compared methods "in terms of both performance and efficiency". We address the requested details below.
W1 & Q1: Assignment and update procedures of Eq. (8)–(10). The two update rules read different signals by design, and we now state this explicitly in the revised manuscript. For each incoming batch: (i) every sample is assigned by Eq. (8) to the most similar prototype among the active Known prototypes μk and the Novel prototypes νl jointly, and all assignments are computed before any update; (ii) each Known prototype μk is updated by Eq. (9) from the samples whose zero-shot prediction (Eq. 1, re-aligned encoder) is class k, weighted by their confidence, with rate 0.05; (iii) each Novel prototype νl is updated by Eq. (10) from the samples that Eq. (8) assigned to it, with rate 0.10.
A conflicting sample, whose zero-shot prediction is Known class k and whose nearest prototype is νl, is predicted as Novel category l, contributes to μk with its confidence weight, and contributes to νl. There is no arbitration between the two rules. The Known prototypes are the only component tied to a class name, and updating them from the text prediction keeps each μk anchored to its name. Updating them from their own nearest-prototype assignments would instead let a Known prototype drift towards a neighbouring Novel cluster, with no signal to pull it back. The Novel prototypes have no text, so they follow the feature geometry alone.
On the theoretical foundations, Eq. (8) is the MAP assignment under a mixture of von Mises–Fisher components with shared concentration and uniform priors [r1], and Eqs. (9)-(10) are the corresponding online spherical k-means updates, where each prototype is an exponential moving average of the normalized mean of its supporting samples.
[r1] Banerjee et al., Clustering on the unit hypersphere using von Mises-Fisher distributions, JMLR'05.