Papers › Synthetic Sample Selection for Generalized Zero-Shot Learning

Synthetic Sample Selection for Generalized Zero-Shot Learning

6 Apr 2023arXiv:2304.02846archive 2025-07-28

Shreyank N Gowda

Generalized Zero-Shot Learning (GZSL) has emerged as a pivotal research domain in computer vision, owing to its capability to recognize objects that have not been seen during training. Despite the significant progress achieved by generative techniques in converting traditional GZSL to fully supervised learning, they tend to generate a large number of synthetic features that are often redundant, thereby increasing training time and decreasing accuracy. To address this issue, this paper proposes a novel approach for synthetic feature selection using reinforcement learning. In particular, we propose a transformer-based selector that is trained through proximal policy optimization (PPO) to select synthetic features based on the validation classification accuracy of the seen classes, which serves as a reward. The proposed method is model-agnostic and data-agnostic, making it applicable to both images and videos and versatile for diverse applications. Our experimental results demonstrate the superiority of our approach over existing feature-generating methods, yielding improved overall performance on multiple benchmarks.

PaperPDF

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

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

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

Tasks

Generalized Zero-Shot LearningZero-Shot Action RecognitionZero-Shot Learningfeature selection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Generalized Zero-Shot Learning CUB-200-2011 SPOT (DAA) Harmonic mean 67.0 #2 of 3 Archive leaderboard report
Generalized Zero-Shot Learning Oxford 102 Flower SPOT (FREE) Harmonic mean 75.9 #1 of 2 Archive leaderboard report
Generalized Zero-Shot Learning SUN Attribute SPOT (CMC-GAN) Harmonic mean 46.4 #2 of 9 Archive leaderboard report
Zero-Shot Action Recognition HMDB51 SPOT Top-1 Accuracy 35.9 #18 of 29 Archive leaderboard report
Zero-Shot Action Recognition Olympics SPOT Top-1 Accuracy 68.7 #1 of 9 Archive leaderboard report
Zero-Shot Action Recognition UCF101 SPOT Top-1 Accuracy 40.9 #22 of 35 Archive leaderboard report
Zero-Shot Learning CUB-200-2011 SPOT average top-1 classification accuracy 62.9 #7 of 14 Archive leaderboard report
Zero-Shot Learning Oxford 102 Flower SPOT average top-1 classification accuracy 71.9 #1 of 2 Archive leaderboard report
Zero-Shot Learning SUN Attribute SPOT (VAEGAN) average top-1 classification accuracy 66.04 #2 of 9 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.

Methods

Feature Selection

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