Papers › Resolving Semantic Confusions for Improved Zero-Shot Detection

Resolving Semantic Confusions for Improved Zero-Shot Detection

12 Dec 2022British Machine Vision Conference 2022 11arXiv:2212.06097archive 2025-07-28

Sandipan Sarma, Sushil Kumar, Arijit Sur

Zero-shot detection (ZSD) is a challenging task where we aim to recognize and localize objects simultaneously, even when our model has not been trained with visual samples of a few target ("unseen") classes. Recently, methods employing generative models like GANs have shown some of the best results, where unseen-class samples are generated based on their semantics by a GAN trained on seen-class data, enabling vanilla object detectors to recognize unseen objects. However, the problem of semantic confusion still remains, where the model is sometimes unable to distinguish between semantically-similar classes. In this work, we propose to train a generative model incorporating a triplet loss that acknowledges the degree of dissimilarity between classes and reflects them in the generated samples. Moreover, a cyclic-consistency loss is also enforced to ensure that generated visual samples of a class highly correspond to their own semantics. Extensive experiments on two benchmark ZSD datasets - MSCOCO and PASCAL-VOC - demonstrate significant gains over the current ZSD methods, reducing semantic confusion and improving detection for the unseen classes.

Paper PDF Conference PDF Code

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

Code

sandipan211/ZSD-SC-Resolver officialmentioned in paperpytorch 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

Generalized Zero-Shot Object Detection Object Detection Transfer Learning Zero-Shot Learning Zero-Shot Object Detection

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Zero-Shot Object Detection	MS-COCO	ZSD-SCR	Recall	65.10	#3 of 9	Archive leaderboard	report
Zero-Shot Object Detection	MS-COCO	ZSD-SCR	mAP	20.10	#3 of 9	Archive leaderboard	report
Zero-Shot Object Detection	PASCAL VOC'07	ZSD-SCR	mAP	62.70	#4 of 7	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

Convolution Faster R-CNN RPN RoIPool Softmax Triplet Loss WGAN

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