Papers › Zero-Shot Logit Adjustment

Zero-Shot Logit Adjustment

25 Apr 2022arXiv:2204.11822archive 2025-07-28

Dubing Chen, Yuming Shen, Haofeng Zhang, Philip H. S. Torr

Semantic-descriptor-based Generalized Zero-Shot Learning (GZSL) poses challenges in recognizing novel classes in the test phase. The development of generative models enables current GZSL techniques to probe further into the semantic-visual link, culminating in a two-stage form that includes a generator and a classifier. However, existing generation-based methods focus on enhancing the generator's effect while neglecting the improvement of the classifier. In this paper, we first analyze of two properties of the generated pseudo unseen samples: bias and homogeneity. Then, we perform variational Bayesian inference to back-derive the evaluation metrics, which reflects the balance of the seen and unseen classes. As a consequence of our derivation, the aforementioned two properties are incorporated into the classifier training as seen-unseen priors via logit adjustment. The Zero-Shot Logit Adjustment further puts semantic-based classifiers into effect in generation-based GZSL. Our experiments demonstrate that the proposed technique achieves state-of-the-art when combined with the basic generator, and it can improve various generative Zero-Shot Learning frameworks. Our codes are available on https://github.com/cdb342/IJCAI-2022-ZLA.

Paper PDF Code

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

cdb342/ijcai-2022-zla officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Bayesian Inference Generalized Zero-Shot Learning Zero-Shot Image Classification Zero-Shot Learning

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Generalized Zero-Shot Learning	AwA2	WGAN+ZLAP	Accuracy Seen	82.2	#4 of 4	Archive leaderboard	report
Generalized Zero-Shot Learning	AwA2	WGAN+ZLAP	Accuracy Unseen	65.4	#4 of 4	Archive leaderboard	report
Generalized Zero-Shot Learning	AwA2	WGAN+ZLAP	H	72.8	#4 of 4	Archive leaderboard	report
Generalized Zero-Shot Learning	Caltech-UCSD Birds 200 - 2011	WGAN+ZLAP	H	68.7	#1 of 1	Archive leaderboard	report
Generalized Zero-Shot Learning	SUN Attribute	WGAN+ZLAP	H	43.2	#9 of 9	Archive leaderboard	report
Generalized Zero-Shot Learning	aPY	WGAN+ZLAP	H	46	#1 of 1	Archive leaderboard	report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections