Papers › The Ikshana Hypothesis of Human Scene Understanding

The Ikshana Hypothesis of Human Scene Understanding

21 Jan 2021arXiv:2101.10837archive 2025-07-28

Venkata Satya Sai Ajay Daliparthi

In recent years, deep neural networks (DNNs) achieved state-of-the-art performance on several computer vision tasks. However, the one typical drawback of these DNNs is the requirement of massive labeled data. Even though few-shot learning methods address this problem, they often use techniques such as meta-learning and metric-learning on top of the existing methods. In this work, we address this problem from a neuroscience perspective by proposing a hypothesis named Ikshana, which is supported by several findings in neuroscience. Our hypothesis approximates the refining process of conceptual gist in the human brain while understanding a natural scene/image. While our hypothesis holds no particular novelty in neuroscience, it provides a novel perspective for designing DNNs for vision tasks. By following the Ikshana hypothesis, we design a novel neural-inspired CNN architecture named IkshanaNet. The empirical results demonstrate the effectiveness of our method by outperforming several baselines on the entire and subsets of the Cityscapes and the CamVid semantic segmentation benchmarks.

PaperPDFCode

Code

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

Representation LearningScene UnderstandingSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Semantic Segmentation Cityscapes test IkshanaNet-1 Category mIoU 82.22% #103 of 105 Archive leaderboard report
Semantic Segmentation Cityscapes test IkshanaNet-1 Mean IoU (class) 54.82% #103 of 105 Archive leaderboard report
Semantic Segmentation Cityscapes test IkshanaNet-2 Category mIoU 76.73% #104 of 105 Archive leaderboard report
Semantic Segmentation Cityscapes test IkshanaNet-2 Mean IoU (class) 45.02% #104 of 105 Archive leaderboard report
Semantic Segmentation Cityscapes test IkshanaNet-3 Category mIoU 75.61% #105 of 105 Archive leaderboard report
Semantic Segmentation Cityscapes test IkshanaNet-3 Mean IoU (class) 42.07% #105 of 105 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

Introduced by this paper: IkshanaNet

1x1 ConvolutionBatch NormalizationConvolutionIkshanaNetReLUSGD with Momentum

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